{"task":"Use yyl-benchmark-breakdown","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"feedback":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","outcome_api":"https://www.openagentskill.com/api/agent/outcome","method":"POST","selected_skill_slug":"jeinlee1991-chinese-llm-benchmark","selected_skill_name":"Chinese Llm Benchmark","alternative_skill_slugs":["clovaai-deep-text-recognition-benchmark","affaan-m-benchmark-methodology","addyosmani-planning-and-task-breakdown","embeddings-benchmark-mteb"],"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"report_after":["After trying the selected skill, report whether it solved the task.","Mark blocked_by_risk when audit, license, credentials, shell, or network risk prevents safe use.","Mark setup_required when the skill looks relevant but needs missing keys, data, or manual configuration.","Mark not_relevant when the selected skill does not match the task after inspection.","Include output_quality, error_type, workspace, human_review_required, evidence_url, and time_to_useful_ms when available."],"json_example":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_f9145679-f463-426f-a518-2e2380ffcca5\" --skill \"jeinlee1991-chinese-llm-benchmark\" --task \"Use yyl-benchmark-breakdown\" --agent \"codex\" --outcome success"},"agent_feedback_loop":{"version":"openagentskill-agent-feedback-loop-v3","status":"active","purpose":"Report the result of one resolved skill run so Trust Score v5 and future Resolve rankings learn from real use.","event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","selected_skill_slug":"jeinlee1991-chinese-llm-benchmark","selected_skill_name":"Chinese Llm Benchmark","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","idempotency":"Retrying the same event_id updates the previous outcome.","dry_run":{"supported":true,"instruction":"Set dry_run=true to validate a payload before wiring a new agent integration."},"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"error_types":["install_failed","runtime_error","not_relevant","permission_blocked","risk_blocked","setup_required","low_quality_output","missing_dependency","timeout","other"],"workspaces":["sandbox","local","ci","production","unknown"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url"],"payload_template":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_f9145679-f463-426f-a518-2e2380ffcca5\" --skill \"jeinlee1991-chinese-llm-benchmark\" --task \"Use yyl-benchmark-breakdown\" --agent \"codex\" --outcome success","ranking_inputs_updated":["Trust Score v5 outcome confidence","Resolve ranking outcome evidence","Skill detail outcome signal block","Outcome leaderboard"]},"install_receipt":{"version":"openagentskill-install-receipt-v2","receipt_id":"receipt_f9145679-f463-426f-a518-2e2380ffcca5","resolve_event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","generated_at":"2026-09-08T09:01:33.805Z","task":"Use yyl-benchmark-breakdown","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"urls":{"web":"https://www.openagentskill.com/resolve?task=Use+yyl-benchmark-breakdown&agent=codex&max_risk=medium","json":"https://www.openagentskill.com/api/agent/receipt?task=Use+yyl-benchmark-breakdown&agent=codex&max_risk=medium","text":"https://www.openagentskill.com/api/agent/receipt?task=Use+yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","resolve_json":"https://www.openagentskill.com/api/agent/resolve?task=Use+yyl-benchmark-breakdown&agent=codex&max_risk=medium","resolve_text":"https://www.openagentskill.com/api/agent/resolve?task=Use+yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text"},"selected_skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","description":"非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","audit_url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","install_api_url":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"install":{"command":"npx skills add jeinlee1991/chinese-llm-benchmark","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","ready":true,"policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"blocked":false},"decision":{"recommendation":"Review the audit page, then allow agent install in a sandboxed workflow.","why_selected":["Matches task terms: benchmark","Useful GitHub adoption: 6,163 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30","Primary pick for GitHub automation","76/100 Trust Score","0/100 Agent Proven Score"],"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"]},"trust":{"score":76,"label":"Review then install","version":"trust-score-v5","base_score":84,"outcome_confidence":0,"outcome_signal":"No agent outcome data yet","outcome_total":0,"outcome_success_rate":null,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["76/100 Trust Score v5","84/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]}},"agent_proven":{"score":0,"label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"installAttempts":0,"installSuccessRate":null,"riskBlocked":0,"setupRequired":0,"avgOutputQuality":null,"productionOutcomes":0}},"risk":{"level":"Safe to try","safety_tier":"Reviewed","safety_score":75,"audit_score":87,"notes":["License is unclear","License clarity: Unknown","Safe-to-try audit","75/100 agent safety score"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","audit_url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark/audit","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":80,"audit_score":71,"safety_score":55,"reason":"Matches task terms: benchmark","policy":"review"},{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","url":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","audit_url":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology/audit","install_command":"npx skills add affaan-m/ECC --skill benchmark-methodology","trust_score":76,"audit_score":85,"safety_score":73,"reason":"Matches task terms: benchmark","policy":"review"},{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","url":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","audit_url":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown/audit","install_command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","trust_score":85,"audit_score":90,"safety_score":78,"reason":"Matches task terms: breakdown","policy":"review"},{"slug":"embeddings-benchmark-mteb","name":"Mteb","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","audit_url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb/audit","install_command":"npx skills add embeddings-benchmark/mteb","trust_score":86,"audit_score":89,"safety_score":77,"reason":"Matches task terms: benchmark","policy":"review"}],"outcome_feedback":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"dry_run_payload":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"},"dry_run":true},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_f9145679-f463-426f-a518-2e2380ffcca5\" --skill \"jeinlee1991-chinese-llm-benchmark\" --task \"Use yyl-benchmark-breakdown\" --agent \"codex\" --outcome success","instruction":"After one narrow sandbox run, report success, failed, not_relevant, blocked_by_risk, or setup_required so Trust Score v5 and future agent rankings learn from real usage."},"next_steps":["Read the audit page: https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","Fetch the pre-install eval: https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","Do not auto-install yet. Ask for human review before running: npx skills add jeinlee1991/chinese-llm-benchmark","Run one narrow task with no production secrets or irreversible side effects.","Report the result to https://www.openagentskill.com/api/agent/outcome using event_id resolve_f9145679-f463-426f-a518-2e2380ffcca5."],"stable_fields":["receipt_id","selected_skill","install","trust","risk","alternatives","outcome_feedback","next_steps"],"freshness_policy":"Re-resolve before production use or after 24 hours to refresh trust, audit, and outcome signals."},"recommendation":{"task":"Use yyl-benchmark-breakdown","agent":"codex","best_skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","description":"非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","audit_url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"install":{"command":"npx skills add jeinlee1991/chinese-llm-benchmark","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","install_api":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","ready":true,"review_required":true,"auto_install_allowed":false,"policy":"review"},"why_recommended":["Matches task terms: benchmark","Useful GitHub adoption: 6,163 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30","Primary pick for GitHub automation","76/100 OpenAgentSkill Trust Score v5","87/100 audit score"],"trust_score_v5":{"score":76,"base_score":84,"outcome_confidence":0,"tier":"strong","label":"Review then install","version":"trust-score-v5","install_policy":"human_review_before_install","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["76/100 Trust Score v5","84/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"agent_compatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]},"outcomes":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","trust_score":76,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"best_for":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"do_not_use_for":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"known_risks":["License is unclear","License clarity: Unknown"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":84,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v4":{"score":84,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]},"outcomes":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"do_not_use_for":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"known_risks":["License is unclear","License clarity: Unknown"]},"trust_score_v3":{"score":84,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]}},"trust_score_v2":{"score":84,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]}},"risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"75/100 Review before install","trust":"84/100 Strong shortlist","notes":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","75/100 agent safety score"]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","description":"非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","github_repo":"jeinlee1991/chinese-llm-benchmark"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add jeinlee1991/chinese-llm-benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add jeinlee1991-chinese-llm-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Chinese Llm Benchmark\" as a Claude Code skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Chinese Llm Benchmark\" from https://github.com/jeinlee1991/chinese-llm-benchmark into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/jeinlee1991-chinese-llm-benchmark"},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"known_risks":["License is unclear","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":98,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"jeinlee1991-chinese-llm-benchmark (Chinese Llm Benchmark)","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","audit":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/jeinlee1991-chinese-llm-benchmark"}},"agent_contract":{"version":"openagentskill-resolve-contract-v2","input_task":"Use yyl-benchmark-breakdown","recommended_skill_slug":"jeinlee1991-chinese-llm-benchmark","recommended_skill_name":"Chinese Llm Benchmark","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","install_policy":"review","auto_install_allowed":false,"human_review_required":true,"audit_url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","skill_api_url":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"jeinlee1991-chinese-llm-benchmark (Chinese Llm Benchmark)","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"supply_asset":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"testing-qa","title":"Testing and QA"}]},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":93,"lastPushedAt":"2026-06-07T05:11:36+00:00"},"github_quality":{"stars":6163,"starsLabel":"6.2K","forks":250,"license":"Unknown","qualityScore":98,"trustScore":84,"auditScore":87},"coverage_tags":["Coding","GitHub automation","agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"]},"alternatives":[{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":80,"audit_score":71,"safety_score":55,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"55/100 Review before install","trust":"80/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]}},{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","url":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","install_command":"npx skills add affaan-m/ECC --skill benchmark-methodology","trust_score":76,"audit_score":85,"safety_score":73,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"73/100 Review before install","trust":"76/100 Strong shortlist","notes":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","url":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","install_command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","trust_score":85,"audit_score":90,"safety_score":78,"why_consider":"Matches task terms: breakdown","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"85/100 Strong shortlist","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"embeddings-benchmark-mteb","name":"Mteb","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","install_command":"npx skills add embeddings-benchmark/mteb","trust_score":86,"audit_score":89,"safety_score":77,"why_consider":"Matches task terms: benchmark","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"77/100 Review before install","trust":"86/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use yyl-benchmark-breakdown","agent":"codex","selected_skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","audit_url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add jeinlee1991/chinese-llm-benchmark","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":76,"label":"Review then install","version":"trust-score-v5","base_score":84,"outcome_confidence":0,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["76/100 Trust Score v5","84/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"status":"pass","detail":"6.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"status":"pass","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"id":"install_safety","label":"Install command safety","score":92,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"id":"review_status","label":"Review status","score":88,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"status":"info","detail":"No agent outcome data yet"}]},"risk":{"level":"Safe to try","audit_label":"Safe to try","safety":"75/100 Review before install","trust":"84/100 Strong shortlist","safety_tier":"Reviewed","notes":["License is unclear","License clarity: Unknown"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":80,"audit_score":71,"safety_score":55,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"55/100 Review before install","trust":"80/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]}},{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","url":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","install_command":"npx skills add affaan-m/ECC --skill benchmark-methodology","trust_score":76,"audit_score":85,"safety_score":73,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"73/100 Review before install","trust":"76/100 Strong shortlist","notes":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","url":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","install_command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","trust_score":85,"audit_score":90,"safety_score":78,"why_consider":"Matches task terms: breakdown","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"85/100 Strong shortlist","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"embeddings-benchmark-mteb","name":"Mteb","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","install_command":"npx skills add embeddings-benchmark/mteb","trust_score":86,"audit_score":89,"safety_score":77,"why_consider":"Matches task terms: benchmark","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"77/100 Review before install","trust":"86/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"outcome_feedback":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_f9145679-f463-426f-a518-2e2380ffcca5\" --skill \"jeinlee1991-chinese-llm-benchmark\" --task \"Use yyl-benchmark-breakdown\" --agent \"codex\" --outcome success"},"next_agent_action":"Ask for human approval or choose a safer alternative before installing.","stable_fields":["decision_packet.selected_skill","decision_packet.install","decision_packet.risk.do_not_use_when","decision_packet.alternatives","decision_packet.outcome_feedback","decision_packet.trust.decision"]},"agent_instruction":"Use Chinese Llm Benchmark for: Use yyl-benchmark-breakdown\nReview audit: https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit\nAsk for human approval before installing: npx skills add jeinlee1991/chinese-llm-benchmark\nIf the audit or policy warnings are unacceptable, choose one of the alternatives."},"recommendation_lanes":{"best_match":{"rank":1,"match_score":30,"raw_match_score":105.3,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","description":"非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。","category":"agent-frameworks","github_stars":6163,"created_at":"2026-05-23T07:49:07.381504+00:00","updated_at":"2026-06-07T05:11:36+00:00","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","github_repo":"jeinlee1991/chinese-llm-benchmark","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: benchmark","Useful GitHub adoption: 6,163 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"testing-qa","title":"Testing and QA"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add jeinlee1991/chinese-llm-benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":6163,"starsLabel":"6.2K","forks":250,"license":"Unknown","qualityScore":98,"trustScore":84,"auditScore":87},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":93,"lastPushedAt":"2026-06-07T05:11:36+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","License clarity: Unknown"]},"coverageTags":["Coding","GitHub automation","agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"]},"quality":{"score":98,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"6.2K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":84,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"6.2K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","License clarity: Unknown"],"evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add jeinlee1991/chinese-llm-benchmark","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","License clarity: Unknown"]},"trust_v5":{"version":"trust-score-v5","score":76,"base_score":84,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["76/100 Trust Score v5","84/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"6.2K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["License is unclear","License clarity: Unknown","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add jeinlee1991/chinese-llm-benchmark","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","3mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","trust_score":76,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","License clarity: Unknown"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":84,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety":{"score":75,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","75/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","75/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for GitHub automation","role":"Primary pick","best_for":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add jeinlee1991/chinese-llm-benchmark","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Chinese Llm Benchmark trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add jeinlee1991-chinese-llm-benchmark","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Chinese Llm Benchmark\" as a Claude Code skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Chinese Llm Benchmark\" from https://github.com/jeinlee1991/chinese-llm-benchmark into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","description":"非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","github_repo":"jeinlee1991/chinese-llm-benchmark"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add jeinlee1991/chinese-llm-benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add jeinlee1991-chinese-llm-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Chinese Llm Benchmark\" as a Claude Code skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Chinese Llm Benchmark\" from https://github.com/jeinlee1991/chinese-llm-benchmark into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/jeinlee1991-chinese-llm-benchmark"},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"known_risks":["License is unclear","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":98,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"jeinlee1991-chinese-llm-benchmark (Chinese Llm Benchmark)","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","audit":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/jeinlee1991-chinese-llm-benchmark"}},"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"urls":{"web":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","install_api":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","audit":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/jeinlee1991-chinese-llm-benchmark?metric=audit","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark"}},"safer_alternative":{"rank":10,"match_score":30,"raw_match_score":74.8,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"aquasecurity-kube-bench","name":"Kube Bench","description":"Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark","category":"devops","github_stars":8172,"created_at":"2026-06-12T19:00:37.541919+00:00","updated_at":"2026-08-24T19:32:49+00:00","repository":"https://github.com/aquasecurity/kube-bench","github_repo":"aquasecurity/kube-bench","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: benchmark","Useful GitHub adoption: 8,172 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"testing-qa","title":"Testing and QA"},{"slug":"security-compliance","title":"Security and compliance"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Go"],"install":{"ready":true,"command":"npx skills add aquasecurity/kube-bench","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":8172,"starsLabel":"8.2K","forks":1337,"license":"Apache-2.0","qualityScore":100,"trustScore":90,"auditScore":94},"maintenance":{"status":"fresh","label":"14d since push","daysSincePush":14,"lastPushedAt":"2026-08-24T19:32:49+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","GitHub automation","devops","kubernetes","cis-benchmark","cis-kubernetes-benchmark","cis-security","hacktoberfest"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"8.2K","tone":"positive"},{"label":"Freshness","value":"14d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"8.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":93,"weight":0.08,"status":"pass","detail":"8.2K stars, 1.3K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"14d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add aquasecurity/kube-bench"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/aquasecurity/kube-bench"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"8.2K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"8.2K stars, 1.3K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"14d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add aquasecurity/kube-bench"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/aquasecurity/kube-bench"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"8.2K GitHub stars","repoActivity":"8.2K stars, 1.3K forks","lastPushed":"14d since push","license":"Apache-2.0","repository":"https://github.com/aquasecurity/kube-bench","install":"npx skills add aquasecurity/kube-bench","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add aquasecurity/kube-bench","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","14d since push"]},"agentCompatibility":["Go","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["devops","kubernetes","cis-benchmark","cis-kubernetes-benchmark","cis-security","hacktoberfest"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"trust_v5":{"version":"trust-score-v5","score":87,"base_score":90,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"agent_install_candidate","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["87/100 Trust Score v5","90/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Low metadata risk"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"8.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":93,"weight":0.08,"status":"pass","detail":"8.2K stars, 1.3K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"14d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add aquasecurity/kube-bench"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/aquasecurity/kube-bench"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"8.2K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"8.2K stars, 1.3K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"14d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add aquasecurity/kube-bench"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/aquasecurity/kube-bench"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"8.2K GitHub stars","repoActivity":"8.2K stars, 1.3K forks","lastPushed":"14d since push","license":"Apache-2.0","repository":"https://github.com/aquasecurity/kube-bench","install":"npx skills add aquasecurity/kube-bench","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"agent_install_candidate"},"installReadiness":{"ready":true,"command":"npx skills add aquasecurity/kube-bench","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","14d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Go","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["devops","kubernetes","cis-benchmark","cis-kubernetes-benchmark","cis-security","hacktoberfest"],"suited_agents":["Go","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add aquasecurity/kube-bench","trust_score":87,"trust_version":"trust-score-v5","risk_level":"low","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["devops","kubernetes","cis-benchmark","cis-kubernetes-benchmark","cis-security","hacktoberfest"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":82,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","82/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","82/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for GitHub automation","role":"Primary pick","best_for":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add aquasecurity/kube-bench","value":"Install the \"Kube Bench\" agent skill from https://github.com/aquasecurity/kube-bench. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"aquasecurity-kube-bench\",\"task\":\"Install Kube Bench\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Kube Bench trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add aquasecurity-kube-bench","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Kube Bench\" agent skill from https://github.com/aquasecurity/kube-bench. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"aquasecurity-kube-bench\",\"task\":\"Install Kube Bench\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Kube Bench\" as a Claude Code skill from https://github.com/aquasecurity/kube-bench. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"aquasecurity-kube-bench\",\"task\":\"Install Kube Bench\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Kube Bench\" from https://github.com/aquasecurity/kube-bench into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"aquasecurity-kube-bench\",\"task\":\"Install Kube Bench\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"aquasecurity-kube-bench","name":"Kube Bench","description":"Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark","category":"devops","url":"https://www.openagentskill.com/skills/aquasecurity-kube-bench","repository":"https://github.com/aquasecurity/kube-bench","github_repo":"aquasecurity/kube-bench"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Run test suites","Capture failures"],"suited_agents":["Go","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add aquasecurity/kube-bench","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add aquasecurity-kube-bench"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Kube Bench\" agent skill from https://github.com/aquasecurity/kube-bench. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"aquasecurity-kube-bench\",\"task\":\"Install Kube Bench\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Kube Bench\" as a Claude Code skill from https://github.com/aquasecurity/kube-bench. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"aquasecurity-kube-bench\",\"task\":\"Install Kube Bench\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Kube Bench\" from https://github.com/aquasecurity/kube-bench into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"aquasecurity-kube-bench\",\"task\":\"Install Kube Bench\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/aquasecurity-kube-bench/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/aquasecurity-kube-bench"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"8.2K GitHub stars","repoActivity":"8.2K stars, 1.3K forks","lastPushed":"14d since push","license":"Apache-2.0","repository":"https://github.com/aquasecurity/kube-bench","install":"npx skills add aquasecurity/kube-bench","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["devops","kubernetes","cis-benchmark","cis-kubernetes-benchmark","cis-security","hacktoberfest"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"14d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 90/100 Production candidate","Audit: 94/100 Safe to try","Safety: 82/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"aquasecurity-kube-bench (Kube Bench)","install_command":"npx skills add aquasecurity/kube-bench","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"aquasecurity-kube-bench","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/aquasecurity-kube-bench","api":"https://www.openagentskill.com/api/agent/skills/aquasecurity-kube-bench","audit":"https://www.openagentskill.com/skills/aquasecurity-kube-bench/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=aquasecurity-kube-bench&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/aquasecurity-kube-bench/install","manifest":"https://www.openagentskill.com/api/registry/manifest/aquasecurity-kube-bench"}},"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"slug":"security-compliance","title":"Security and compliance","url":"https://www.openagentskill.com/use-cases/security-compliance"}],"urls":{"web":"https://www.openagentskill.com/skills/aquasecurity-kube-bench","api":"https://www.openagentskill.com/api/agent/skills/aquasecurity-kube-bench","install_api":"https://www.openagentskill.com/api/skills/aquasecurity-kube-bench/install","audit":"https://www.openagentskill.com/skills/aquasecurity-kube-bench/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=aquasecurity-kube-bench&task=Use%20yyl-benchmark-breakdown&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/aquasecurity-kube-bench?metric=audit","repository":"https://github.com/aquasecurity/kube-bench"}},"popular_alternative":{"rank":3,"match_score":30,"raw_match_score":100.5,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","description":">-","category":"automation","github_stars":252296,"created_at":"2026-09-07T12:06:15.251031+00:00","updated_at":"2026-09-07T11:17:03+00:00","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","github_repo":"affaan-m/ECC","source_version":{"version":"1.0.0","commit_sha":"e04ea0b9cc8248686edf5ac751cadff550e162b8","content_hash":"a4ac232387a4dec4df2e28dae9578ea7f73f848925096f0c335753ca257934ec","ref":"main","path":".agents/skills/benchmark-methodology/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: benchmark","Strong GitHub adoption: 252,296 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"local-desktop","title":"Local desktop"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add affaan-m/ECC --skill benchmark-methodology","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":252296,"starsLabel":"252K","forks":37869,"license":"MIT","qualityScore":89,"trustScore":76,"auditScore":85},"maintenance":{"status":"fresh","label":"Pushed today","daysSincePush":0,"lastPushedAt":"2026-09-07T11:17:03+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Coding","Coding agents","automation","agent-skill"]},"quality":{"score":89,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"252K","tone":"positive"},{"label":"Freshness","value":"Today","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure."]},"trust":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"252K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"252K stars, 38K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"Pushed today"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":36,"weight":0.14,"status":"fail","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add affaan-m/ECC --skill benchmark-methodology"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"252K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"252K stars, 38K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"Pushed today"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"fail","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add affaan-m/ECC --skill benchmark-methodology"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"252K GitHub stars","repoActivity":"252K stars, 38K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","install":"npx skills add affaan-m/ECC --skill benchmark-methodology","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Missing useful documentation signals","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add affaan-m/ECC --skill benchmark-methodology","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","Pushed today"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["automation","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":68,"base_score":76,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["68/100 Trust Score v5","76/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"252K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"252K stars, 38K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"Pushed today"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":36,"weight":0.14,"status":"fail","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add affaan-m/ECC --skill benchmark-methodology"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"252K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"252K stars, 38K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"Pushed today"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"fail","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add affaan-m/ECC --skill benchmark-methodology"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"252K GitHub stars","repoActivity":"252K stars, 38K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","install":"npx skills add affaan-m/ECC --skill benchmark-methodology","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Missing useful documentation signals","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add affaan-m/ECC --skill benchmark-methodology","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","Pushed today","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["automation","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add affaan-m/ECC --skill benchmark-methodology","trust_score":68,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["automation","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":85,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":73,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","73/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","73/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","best_for":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add affaan-m/ECC --skill benchmark-methodology","value":"Install the \"benchmark-methodology\" agent skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review benchmark-methodology trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add affaan-m-benchmark-methodology","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"benchmark-methodology\" agent skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"benchmark-methodology\" as a Claude Code skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"benchmark-methodology\" from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","description":">-","category":"automation","url":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","github_repo":"affaan-m/ECC"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add affaan-m/ECC --skill benchmark-methodology","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add affaan-m-benchmark-methodology"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"benchmark-methodology\" agent skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"benchmark-methodology\" as a Claude Code skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"benchmark-methodology\" from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/affaan-m-benchmark-methodology/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/affaan-m-benchmark-methodology"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"252K GitHub stars","repoActivity":"252K stars, 38K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","install":"npx skills add affaan-m/ECC --skill benchmark-methodology","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Missing useful documentation signals","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["automation","agent-skill"],"known_risks":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":85,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":89,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"Pushed today","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No OpenAgentSkill engagement data yet","Documentation summary is thin","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 85/100 Needs review","Safety: 73/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"affaan-m-benchmark-methodology (benchmark-methodology)","install_command":"npx skills add affaan-m/ECC --skill benchmark-methodology","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"affaan-m-benchmark-methodology","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","api":"https://www.openagentskill.com/api/agent/skills/affaan-m-benchmark-methodology","audit":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=affaan-m-benchmark-methodology&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/affaan-m-benchmark-methodology/install","manifest":"https://www.openagentskill.com/api/registry/manifest/affaan-m-benchmark-methodology"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"urls":{"web":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","api":"https://www.openagentskill.com/api/agent/skills/affaan-m-benchmark-methodology","install_api":"https://www.openagentskill.com/api/skills/affaan-m-benchmark-methodology/install","audit":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=affaan-m-benchmark-methodology&task=Use%20yyl-benchmark-breakdown&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/affaan-m-benchmark-methodology?metric=audit","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"}},"new_contender":{"rank":4,"match_score":30,"raw_match_score":100.5,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","description":"Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.","category":"research","github_stars":91373,"created_at":"2026-09-01T14:40:54.691733+00:00","updated_at":"2026-08-28T23:31:50+00:00","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","github_repo":"addyosmani/agent-skills","source_version":{"version":"1.0.0","commit_sha":"d2c37ef6225dd8726cdd369a8030307f48592d26","content_hash":"ed0f90cc5951ddd4bcab7f871f64efec93a49af9279ef93bc470da77ad8da3f7","ref":"main","path":"skills/planning-and-task-breakdown/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: breakdown","Strong GitHub adoption: 91,373 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":91373,"starsLabel":"91K","forks":9758,"license":"MIT","qualityScore":89,"trustScore":85,"auditScore":90},"maintenance":{"status":"fresh","label":"10d since push","daysSincePush":10,"lastPushedAt":"2026-08-28T23:31:50+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":89,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"91K","tone":"positive"},{"label":"Freshness","value":"10d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"91K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"91K stars, 9.8K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"10d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"91K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"91K stars, 9.8K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"10d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"91K GitHub stars","repoActivity":"91K stars, 9.8K forks","lastPushed":"10d since push","license":"MIT","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","install":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","10d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":77,"base_score":85,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["77/100 Trust Score v5","85/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"91K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"91K stars, 9.8K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"10d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"91K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"91K stars, 9.8K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"10d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"91K GitHub stars","repoActivity":"91K stars, 9.8K forks","lastPushed":"10d since push","license":"MIT","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","install":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","10d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","trust_score":77,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","78/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Research agents","role":"Primary pick","best_for":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","value":"Install the \"planning-and-task-breakdown\" agent skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review planning-and-task-breakdown trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add addyosmani-planning-and-task-breakdown","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"planning-and-task-breakdown\" agent skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"planning-and-task-breakdown\" as a Claude Code skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"planning-and-task-breakdown\" from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","description":"Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.","category":"research","url":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","github_repo":"addyosmani/agent-skills"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add addyosmani-planning-and-task-breakdown"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"planning-and-task-breakdown\" agent skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"planning-and-task-breakdown\" as a Claude Code skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"planning-and-task-breakdown\" from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/addyosmani-planning-and-task-breakdown/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/addyosmani-planning-and-task-breakdown"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"91K GitHub stars","repoActivity":"91K stars, 9.8K forks","lastPushed":"10d since push","license":"MIT","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","install":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":89,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"10d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"addyosmani-planning-and-task-breakdown (planning-and-task-breakdown)","install_command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"addyosmani-planning-and-task-breakdown","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","api":"https://www.openagentskill.com/api/agent/skills/addyosmani-planning-and-task-breakdown","audit":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=addyosmani-planning-and-task-breakdown&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/addyosmani-planning-and-task-breakdown/install","manifest":"https://www.openagentskill.com/api/registry/manifest/addyosmani-planning-and-task-breakdown"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","api":"https://www.openagentskill.com/api/agent/skills/addyosmani-planning-and-task-breakdown","install_api":"https://www.openagentskill.com/api/skills/addyosmani-planning-and-task-breakdown/install","audit":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=addyosmani-planning-and-task-breakdown&task=Use%20yyl-benchmark-breakdown&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/addyosmani-planning-and-task-breakdown?metric=audit","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"}},"no_skill_option":{"recommended":true,"label":"Build without a third-party skill","reason":"Use a native agent workflow when the third-party permission or maintenance surface is not acceptable.","action":"Use the agent’s built-in tools for one narrow run, then reconsider a skill only if the workflow repeats."}},"selected":{"rank":1,"match_score":30,"raw_match_score":105.3,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","description":"非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。","category":"agent-frameworks","github_stars":6163,"created_at":"2026-05-23T07:49:07.381504+00:00","updated_at":"2026-06-07T05:11:36+00:00","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","github_repo":"jeinlee1991/chinese-llm-benchmark","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: benchmark","Useful GitHub adoption: 6,163 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"testing-qa","title":"Testing and QA"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add jeinlee1991/chinese-llm-benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":6163,"starsLabel":"6.2K","forks":250,"license":"Unknown","qualityScore":98,"trustScore":84,"auditScore":87},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":93,"lastPushedAt":"2026-06-07T05:11:36+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","License clarity: Unknown"]},"coverageTags":["Coding","GitHub automation","agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"]},"quality":{"score":98,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"6.2K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":84,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"6.2K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","License clarity: Unknown"],"evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add jeinlee1991/chinese-llm-benchmark","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","License clarity: Unknown"]},"trust_v5":{"version":"trust-score-v5","score":76,"base_score":84,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["76/100 Trust Score v5","84/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"6.2K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["License is unclear","License clarity: Unknown","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add jeinlee1991/chinese-llm-benchmark","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","3mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","trust_score":76,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","License clarity: Unknown"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":84,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety":{"score":75,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","75/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","75/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for GitHub automation","role":"Primary pick","best_for":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add jeinlee1991/chinese-llm-benchmark","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Chinese Llm Benchmark trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add jeinlee1991-chinese-llm-benchmark","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Chinese Llm Benchmark\" as a Claude Code skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Chinese Llm Benchmark\" from https://github.com/jeinlee1991/chinese-llm-benchmark into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","description":"非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","github_repo":"jeinlee1991/chinese-llm-benchmark"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add jeinlee1991/chinese-llm-benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add jeinlee1991-chinese-llm-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Chinese Llm Benchmark\" as a Claude Code skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Chinese Llm Benchmark\" from https://github.com/jeinlee1991/chinese-llm-benchmark into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/jeinlee1991-chinese-llm-benchmark"},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"known_risks":["License is unclear","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":98,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"jeinlee1991-chinese-llm-benchmark (Chinese Llm Benchmark)","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","audit":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/jeinlee1991-chinese-llm-benchmark"}},"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"urls":{"web":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","install_api":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","audit":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/jeinlee1991-chinese-llm-benchmark?metric=audit","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark"}},"alternatives":[{"rank":2,"match_score":30,"raw_match_score":100.9,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","description":"Text recognition (optical character recognition) with deep learning methods, ICCV 2019","category":"document-processing","github_stars":3937,"created_at":"2026-06-05T13:01:08.962553+00:00","updated_at":"2024-03-04T10:24:54+00:00","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","github_repo":"clovaai/deep-text-recognition-benchmark","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: benchmark","Useful GitHub adoption: 3,937 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Document processing","description":"I need my agent to read PDFs, extract tables, and turn documents into structured data.","useCases":[{"slug":"document-processing","title":"Document processing"},{"slug":"web-scraping","title":"Web scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Jupyter Notebook"],"install":{"ready":true,"command":"npx skills add clovaai/deep-text-recognition-benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":3937,"starsLabel":"3.9K","forks":1133,"license":"Apache-2.0","qualityScore":70,"trustScore":80,"auditScore":71},"maintenance":{"status":"stale","label":"3y since push","daysSincePush":917,"lastPushedAt":"2024-03-04T10:24:54+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"coverageTags":["Research","Document processing","document-processing","ocr","documents","extraction","crnn","deep-learning"]},"quality":{"score":70,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"3.9K","tone":"positive"},{"label":"Freshness","value":"3y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.9K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"3.9K stars, 1.1K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add clovaai/deep-text-recognition-benchmark"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/clovaai/deep-text-recognition-benchmark"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"3.9K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.9K stars, 1.1K forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add clovaai/deep-text-recognition-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/clovaai/deep-text-recognition-benchmark"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"4 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"],"evidence":{"stars":"3.9K GitHub stars","repoActivity":"3.9K stars, 1.1K forks","lastPushed":"3y since push","license":"Apache-2.0","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","install":"npx skills add clovaai/deep-text-recognition-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add clovaai/deep-text-recognition-benchmark","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3y since push"]},"agentCompatibility":["Jupyter Notebook","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["document-processing","ocr","documents","extraction","crnn","deep-learning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"trust_v5":{"version":"trust-score-v5","score":72,"base_score":80,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["72/100 Trust Score v5","80/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.9K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"3.9K stars, 1.1K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add clovaai/deep-text-recognition-benchmark"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/clovaai/deep-text-recognition-benchmark"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"3.9K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.9K stars, 1.1K forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add clovaai/deep-text-recognition-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/clovaai/deep-text-recognition-benchmark"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"4 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"3.9K GitHub stars","repoActivity":"3.9K stars, 1.1K forks","lastPushed":"3y since push","license":"Apache-2.0","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","install":"npx skills add clovaai/deep-text-recognition-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add clovaai/deep-text-recognition-benchmark","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3y since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Jupyter Notebook","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["document-processing","ocr","documents","extraction","crnn","deep-learning"],"suited_agents":["Jupyter Notebook","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":72,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["document-processing","ocr","documents","extraction","crnn","deep-learning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"safety":{"score":55,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Documentation summary is thin","55/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["Documentation summary is thin","55/100 agent safety score"]},"decision":{"readiness_score":75,"readiness_label":"Strong shortlist","headline":"Companion skill for Document processing","role":"Companion skill","best_for":["Document processing workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale"],"next_steps":["Install it in a sandbox agent and run one Document processing task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add clovaai/deep-text-recognition-benchmark","value":"Install the \"Deep Text Recognition Benchmark\" agent skill from https://github.com/clovaai/deep-text-recognition-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Deep Text Recognition Benchmark trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add clovaai-deep-text-recognition-benchmark","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Deep Text Recognition Benchmark\" agent skill from https://github.com/clovaai/deep-text-recognition-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Deep Text Recognition Benchmark\" as a Claude Code skill from https://github.com/clovaai/deep-text-recognition-benchmark. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition Benchmark\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Deep Text Recognition Benchmark\" from https://github.com/clovaai/deep-text-recognition-benchmark into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition Benchmark\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","description":"Text recognition (optical character recognition) with deep learning methods, ICCV 2019","category":"document-processing","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","github_repo":"clovaai/deep-text-recognition-benchmark"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Crawl target URLs","Extract tables and metadata"],"suited_agents":["Jupyter Notebook","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add clovaai/deep-text-recognition-benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add clovaai-deep-text-recognition-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Deep Text Recognition Benchmark\" agent skill from https://github.com/clovaai/deep-text-recognition-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Deep Text Recognition Benchmark\" as a Claude Code skill from https://github.com/clovaai/deep-text-recognition-benchmark. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition Benchmark\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Deep Text Recognition Benchmark\" from https://github.com/clovaai/deep-text-recognition-benchmark into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition Benchmark\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/clovaai-deep-text-recognition-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/clovaai-deep-text-recognition-benchmark"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"3.9K GitHub stars","repoActivity":"3.9K stars, 1.1K forks","lastPushed":"3y since push","license":"Apache-2.0","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","install":"npx skills add clovaai/deep-text-recognition-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["document-processing","ocr","documents","extraction","crnn","deep-learning"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":70,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 3y since push","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 80/100 Strong shortlist","Audit: 71/100 Needs review","Safety: 55/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"clovaai-deep-text-recognition-benchmark (Deep Text Recognition Benchmark)","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"clovaai-deep-text-recognition-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","api":"https://www.openagentskill.com/api/agent/skills/clovaai-deep-text-recognition-benchmark","audit":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=clovaai-deep-text-recognition-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/clovaai-deep-text-recognition-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/clovaai-deep-text-recognition-benchmark"}},"use_cases":[{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","api":"https://www.openagentskill.com/api/agent/skills/clovaai-deep-text-recognition-benchmark","install_api":"https://www.openagentskill.com/api/skills/clovaai-deep-text-recognition-benchmark/install","audit":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=clovaai-deep-text-recognition-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/clovaai-deep-text-recognition-benchmark?metric=audit","repository":"https://github.com/clovaai/deep-text-recognition-benchmark"}},{"rank":3,"match_score":30,"raw_match_score":100.5,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","description":">-","category":"automation","github_stars":252296,"created_at":"2026-09-07T12:06:15.251031+00:00","updated_at":"2026-09-07T11:17:03+00:00","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","github_repo":"affaan-m/ECC","source_version":{"version":"1.0.0","commit_sha":"e04ea0b9cc8248686edf5ac751cadff550e162b8","content_hash":"a4ac232387a4dec4df2e28dae9578ea7f73f848925096f0c335753ca257934ec","ref":"main","path":".agents/skills/benchmark-methodology/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: benchmark","Strong GitHub adoption: 252,296 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"local-desktop","title":"Local desktop"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add affaan-m/ECC --skill benchmark-methodology","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":252296,"starsLabel":"252K","forks":37869,"license":"MIT","qualityScore":89,"trustScore":76,"auditScore":85},"maintenance":{"status":"fresh","label":"Pushed today","daysSincePush":0,"lastPushedAt":"2026-09-07T11:17:03+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Coding","Coding agents","automation","agent-skill"]},"quality":{"score":89,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"252K","tone":"positive"},{"label":"Freshness","value":"Today","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure."]},"trust":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"252K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"252K stars, 38K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"Pushed today"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":36,"weight":0.14,"status":"fail","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add affaan-m/ECC --skill benchmark-methodology"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"252K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"252K stars, 38K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"Pushed today"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"fail","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add affaan-m/ECC --skill benchmark-methodology"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"252K GitHub stars","repoActivity":"252K stars, 38K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","install":"npx skills add affaan-m/ECC --skill benchmark-methodology","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Missing useful documentation signals","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add affaan-m/ECC --skill benchmark-methodology","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","Pushed today"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["automation","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":68,"base_score":76,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["68/100 Trust Score v5","76/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"252K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"252K stars, 38K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"Pushed today"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":36,"weight":0.14,"status":"fail","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add affaan-m/ECC --skill benchmark-methodology"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"252K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"252K stars, 38K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"Pushed today"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"fail","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add affaan-m/ECC --skill benchmark-methodology"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"252K GitHub stars","repoActivity":"252K stars, 38K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","install":"npx skills add affaan-m/ECC --skill benchmark-methodology","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Missing useful documentation signals","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add affaan-m/ECC --skill benchmark-methodology","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","Pushed today","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["automation","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add affaan-m/ECC --skill benchmark-methodology","trust_score":68,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["automation","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":85,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":73,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","73/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","73/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","best_for":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add affaan-m/ECC --skill benchmark-methodology","value":"Install the \"benchmark-methodology\" agent skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review benchmark-methodology trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add affaan-m-benchmark-methodology","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"benchmark-methodology\" agent skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"benchmark-methodology\" as a Claude Code skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"benchmark-methodology\" from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","description":">-","category":"automation","url":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","github_repo":"affaan-m/ECC"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add affaan-m/ECC --skill benchmark-methodology","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add affaan-m-benchmark-methodology"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"benchmark-methodology\" agent skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"benchmark-methodology\" as a Claude Code skill from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"benchmark-methodology\" from https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"affaan-m-benchmark-methodology\",\"task\":\"Install benchmark-methodology\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/affaan-m-benchmark-methodology/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/affaan-m-benchmark-methodology"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"252K GitHub stars","repoActivity":"252K stars, 38K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology","install":"npx skills add affaan-m/ECC --skill benchmark-methodology","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Missing useful documentation signals","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["automation","agent-skill"],"known_risks":["The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":85,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":89,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"Pushed today","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No OpenAgentSkill engagement data yet","Documentation summary is thin","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 85/100 Needs review","Safety: 73/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"affaan-m-benchmark-methodology (benchmark-methodology)","install_command":"npx skills add affaan-m/ECC --skill benchmark-methodology","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"affaan-m-benchmark-methodology","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","api":"https://www.openagentskill.com/api/agent/skills/affaan-m-benchmark-methodology","audit":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=affaan-m-benchmark-methodology&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/affaan-m-benchmark-methodology/install","manifest":"https://www.openagentskill.com/api/registry/manifest/affaan-m-benchmark-methodology"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"urls":{"web":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","api":"https://www.openagentskill.com/api/agent/skills/affaan-m-benchmark-methodology","install_api":"https://www.openagentskill.com/api/skills/affaan-m-benchmark-methodology/install","audit":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=affaan-m-benchmark-methodology&task=Use%20yyl-benchmark-breakdown&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/affaan-m-benchmark-methodology?metric=audit","repository":"https://github.com/affaan-m/ECC/tree/main/.agents/skills/benchmark-methodology"}},{"rank":4,"match_score":30,"raw_match_score":100.5,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","description":"Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.","category":"research","github_stars":91373,"created_at":"2026-09-01T14:40:54.691733+00:00","updated_at":"2026-08-28T23:31:50+00:00","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","github_repo":"addyosmani/agent-skills","source_version":{"version":"1.0.0","commit_sha":"d2c37ef6225dd8726cdd369a8030307f48592d26","content_hash":"ed0f90cc5951ddd4bcab7f871f64efec93a49af9279ef93bc470da77ad8da3f7","ref":"main","path":"skills/planning-and-task-breakdown/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: breakdown","Strong GitHub adoption: 91,373 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":91373,"starsLabel":"91K","forks":9758,"license":"MIT","qualityScore":89,"trustScore":85,"auditScore":90},"maintenance":{"status":"fresh","label":"10d since push","daysSincePush":10,"lastPushedAt":"2026-08-28T23:31:50+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":89,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"91K","tone":"positive"},{"label":"Freshness","value":"10d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"91K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"91K stars, 9.8K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"10d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"91K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"91K stars, 9.8K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"10d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"91K GitHub stars","repoActivity":"91K stars, 9.8K forks","lastPushed":"10d since push","license":"MIT","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","install":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","10d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":77,"base_score":85,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["77/100 Trust Score v5","85/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"91K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"91K stars, 9.8K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"10d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"91K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"91K stars, 9.8K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"10d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"91K GitHub stars","repoActivity":"91K stars, 9.8K forks","lastPushed":"10d since push","license":"MIT","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","install":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","10d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","trust_score":77,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","78/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Research agents","role":"Primary pick","best_for":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","value":"Install the \"planning-and-task-breakdown\" agent skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review planning-and-task-breakdown trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add addyosmani-planning-and-task-breakdown","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"planning-and-task-breakdown\" agent skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"planning-and-task-breakdown\" as a Claude Code skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"planning-and-task-breakdown\" from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","description":"Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.","category":"research","url":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","github_repo":"addyosmani/agent-skills"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add addyosmani-planning-and-task-breakdown"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"planning-and-task-breakdown\" agent skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"planning-and-task-breakdown\" as a Claude Code skill from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"planning-and-task-breakdown\" from https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"addyosmani-planning-and-task-breakdown\",\"task\":\"Install planning-and-task-breakdown\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/addyosmani-planning-and-task-breakdown/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/addyosmani-planning-and-task-breakdown"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"91K GitHub stars","repoActivity":"91K stars, 9.8K forks","lastPushed":"10d since push","license":"MIT","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","install":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":89,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"10d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"addyosmani-planning-and-task-breakdown (planning-and-task-breakdown)","install_command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"addyosmani-planning-and-task-breakdown","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","api":"https://www.openagentskill.com/api/agent/skills/addyosmani-planning-and-task-breakdown","audit":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=addyosmani-planning-and-task-breakdown&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/addyosmani-planning-and-task-breakdown/install","manifest":"https://www.openagentskill.com/api/registry/manifest/addyosmani-planning-and-task-breakdown"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","api":"https://www.openagentskill.com/api/agent/skills/addyosmani-planning-and-task-breakdown","install_api":"https://www.openagentskill.com/api/skills/addyosmani-planning-and-task-breakdown/install","audit":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=addyosmani-planning-and-task-breakdown&task=Use%20yyl-benchmark-breakdown&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/addyosmani-planning-and-task-breakdown?metric=audit","repository":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"}},{"rank":5,"match_score":30,"raw_match_score":97.4,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"embeddings-benchmark-mteb","name":"Mteb","description":"MTEB: Massive Text Embedding Benchmark","category":"rag-knowledge","github_stars":3309,"created_at":"2026-06-05T06:01:49.882433+00:00","updated_at":"2026-06-19T21:00:15+00:00","repository":"https://github.com/embeddings-benchmark/mteb","github_repo":"embeddings-benchmark/mteb","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: benchmark","Useful GitHub adoption: 3,309 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"research-agents","title":"Research agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add embeddings-benchmark/mteb","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":3309,"starsLabel":"3.3K","forks":627,"license":"Apache-2.0","qualityScore":95,"trustScore":86,"auditScore":89},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":80,"lastPushedAt":"2026-06-19T21:00:15+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"]},"quality":{"score":95,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"3.3K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":86,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"3.3K stars, 627 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add embeddings-benchmark/mteb"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/embeddings-benchmark/mteb"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"3.3K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.3K stars, 627 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add embeddings-benchmark/mteb"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/embeddings-benchmark/mteb"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"3.3K GitHub stars","repoActivity":"3.3K stars, 627 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/embeddings-benchmark/mteb","install":"npx skills add embeddings-benchmark/mteb","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add embeddings-benchmark/mteb","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":80,"base_score":86,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"agent_install_candidate","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["80/100 Trust Score v5","86/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"3.3K stars, 627 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add embeddings-benchmark/mteb"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/embeddings-benchmark/mteb"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"3.3K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.3K stars, 627 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add embeddings-benchmark/mteb"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/embeddings-benchmark/mteb"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"3.3K GitHub stars","repoActivity":"3.3K stars, 627 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/embeddings-benchmark/mteb","install":"npx skills add embeddings-benchmark/mteb","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"agent_install_candidate"},"installReadiness":{"ready":true,"command":"npx skills add embeddings-benchmark/mteb","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add embeddings-benchmark/mteb","trust_score":80,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":86,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":77,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","77/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","77/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","best_for":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add embeddings-benchmark/mteb","value":"Install the \"Mteb\" agent skill from https://github.com/embeddings-benchmark/mteb. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: MTEB: Massive Text Embedding Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Mteb trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add embeddings-benchmark-mteb","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Mteb\" agent skill from https://github.com/embeddings-benchmark/mteb. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: MTEB: Massive Text Embedding Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Mteb\" as a Claude Code skill from https://github.com/embeddings-benchmark/mteb. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: MTEB: Massive Text Embedding Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Mteb\" from https://github.com/embeddings-benchmark/mteb into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: MTEB: Massive Text Embedding Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"embeddings-benchmark-mteb","name":"Mteb","description":"MTEB: Massive Text Embedding Benchmark","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","repository":"https://github.com/embeddings-benchmark/mteb","github_repo":"embeddings-benchmark/mteb"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add embeddings-benchmark/mteb","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add embeddings-benchmark-mteb"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mteb\" agent skill from https://github.com/embeddings-benchmark/mteb. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: MTEB: Massive Text Embedding Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mteb\" as a Claude Code skill from https://github.com/embeddings-benchmark/mteb. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: MTEB: Massive Text Embedding Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mteb\" from https://github.com/embeddings-benchmark/mteb into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: MTEB: Massive Text Embedding Benchmark After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/embeddings-benchmark-mteb/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/embeddings-benchmark-mteb"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"3.3K GitHub stars","repoActivity":"3.3K stars, 627 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/embeddings-benchmark/mteb","install":"npx skills add embeddings-benchmark/mteb","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use yyl-benchmark-breakdown","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 89/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"embeddings-benchmark-mteb (Mteb)","install_command":"npx skills add embeddings-benchmark/mteb","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"embeddings-benchmark-mteb","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","api":"https://www.openagentskill.com/api/agent/skills/embeddings-benchmark-mteb","audit":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=embeddings-benchmark-mteb&task=Use%20yyl-benchmark-breakdown&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/embeddings-benchmark-mteb/install","manifest":"https://www.openagentskill.com/api/registry/manifest/embeddings-benchmark-mteb"}},"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","api":"https://www.openagentskill.com/api/agent/skills/embeddings-benchmark-mteb","install_api":"https://www.openagentskill.com/api/skills/embeddings-benchmark-mteb/install","audit":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=embeddings-benchmark-mteb&task=Use%20yyl-benchmark-breakdown&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/embeddings-benchmark-mteb?metric=audit","repository":"https://github.com/embeddings-benchmark/mteb"}}],"blocked_candidates":[],"agent_workflow":{"mode":"resolve_review_install","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","selected_skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark"},"install":{"target":"codex","label":"Codex install prompt","kind":"agent-prompt","command":"npx skills add jeinlee1991/chinese-llm-benchmark","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","api":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install"},"copy_paste_prompt":"Task: Use yyl-benchmark-breakdown\nUse Chinese Llm Benchmark from https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark.\nReview the audit first: https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit\nReview the eval first: https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install\nInstall command: npx skills add jeinlee1991/chinese-llm-benchmark\nIf audit or policy warnings look unsafe for this workspace, use one of the alternatives instead.","api_sequence":[{"step":1,"label":"Resolve task","method":"GET","url":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}}}],"review_checklist":["Safety tier: Reviewed","Safety score: 75/100 Review before install","Audit score: 87/100 Safe to try","Trust score: 76/100 Review then install","Readiness: 100/100 Production-ready","License is unclear","License is unclear","License clarity: Unknown"],"fallback_strategy":[{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","reason":"Matches task terms: benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_api":"https://www.openagentskill.com/api/skills/clovaai-deep-text-recognition-benchmark/install"},{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","reason":"Matches task terms: benchmark","url":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","install_api":"https://www.openagentskill.com/api/skills/affaan-m-benchmark-methodology/install"},{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","reason":"Matches task terms: breakdown","url":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","install_api":"https://www.openagentskill.com/api/skills/addyosmani-planning-and-task-breakdown/install"}],"expected_agent_output":{"selected_skill":"slug and name","install_command":"command or agent prompt used","risk_summary":"audit, trust, and policy notes","next_step":"what the agent will do after install","outcome_event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5"}},"agent_handoff":{"version":"openagentskill-agent-handoff-v1","mode":"resolve_compare_review_install","task":"Use yyl-benchmark-breakdown","agent":"codex","selected_skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","audit_url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark"},"install_plan":{"command":"npx skills add jeinlee1991/chinese-llm-benchmark","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","install_api":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","auto_install_allowed":false,"human_review_required":true,"policy":"review"},"api_sequence":[{"step":1,"label":"Resolve task","method":"GET","url":"https://www.openagentskill.com/api/agent/resolve?task=Use%20yyl-benchmark-breakdown&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}}}],"platform_templates":[{"id":"codex","name":"Codex","surface":"Coding agent / local workspace","copy_prompt":"Task: Use yyl-benchmark-breakdown\nSelected skill: Chinese Llm Benchmark (jeinlee1991-chinese-llm-benchmark)\nSkill URL: https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark\nAudit URL: https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install\nInstall command: npx skills add jeinlee1991/chinese-llm-benchmark\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- Deep Text Recognition Benchmark (clovaai-deep-text-recognition-benchmark): https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark\n- benchmark-methodology (affaan-m-benchmark-methodology): https://www.openagentskill.com/skills/affaan-m-benchmark-methodology\n- planning-and-task-breakdown (addyosmani-planning-and-task-breakdown): https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown\n\nExpected Codex output:\n- selected_skill\n- install_command\n- risk_summary\n- outcome_event_id\n- alternatives\n- files_or_commands_to_touch\n- next_action"},{"id":"claude-code","name":"Claude Code","surface":"Claude Code skill workflow","copy_prompt":"Task: Use yyl-benchmark-breakdown\nSelected skill: Chinese Llm Benchmark (jeinlee1991-chinese-llm-benchmark)\nSkill URL: https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark\nAudit URL: https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install\nInstall command: npx skills add jeinlee1991/chinese-llm-benchmark\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- Deep Text Recognition Benchmark (clovaai-deep-text-recognition-benchmark): https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark\n- benchmark-methodology (affaan-m-benchmark-methodology): https://www.openagentskill.com/skills/affaan-m-benchmark-methodology\n- planning-and-task-breakdown (addyosmani-planning-and-task-breakdown): https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown\n\nExpected Claude Code output:\n- selected_skill\n- skill_files_or_instructions\n- install_prompt\n- risk_summary\n- outcome_event_id\n- activation_steps\n- fallback_skill"},{"id":"cursor","name":"Cursor","surface":"Cursor rules / agent instructions","copy_prompt":"Task: Use yyl-benchmark-breakdown\nSelected skill: Chinese Llm Benchmark (jeinlee1991-chinese-llm-benchmark)\nSkill URL: https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark\nAudit URL: https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20yyl-benchmark-breakdown&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install\nInstall command: npx skills add jeinlee1991/chinese-llm-benchmark\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- Deep Text Recognition Benchmark (clovaai-deep-text-recognition-benchmark): https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark\n- benchmark-methodology (affaan-m-benchmark-methodology): https://www.openagentskill.com/skills/affaan-m-benchmark-methodology\n- planning-and-task-breakdown (addyosmani-planning-and-task-breakdown): https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown\n\nExpected Cursor output:\n- selected_skill\n- cursor_rule_or_prompt\n- install_command\n- risk_summary\n- outcome_event_id\n- when_to_use\n- when_not_to_use"}],"review_checklist":["Safety tier: Reviewed","Safety score: 75/100 Review before install","Audit score: 87/100 Safe to try","Trust score: 76/100 Review then install","Readiness: 100/100 Production-ready","License is unclear","License is unclear","License clarity: Unknown"],"expected_output":{"selected_skill":"slug and name","install_command":"command or agent prompt used","risk_summary":"audit, trust, and policy notes","next_step":"what the agent will do after install","outcome_event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5"},"feedback":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_f9145679-f463-426f-a518-2e2380ffcca5\" --skill \"jeinlee1991-chinese-llm-benchmark\" --task \"Use yyl-benchmark-breakdown\" --agent \"codex\" --outcome success","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"]},"blocked_actions":["Do not install when safety_gate.blocked is true.","Do not install when the audit or eval reports unacceptable workspace risk.","Do not execute shell commands, access secrets, or call external services without user approval.","Do not keep the skill as an always-on instruction if it only fits a narrow task."]},"policy_decision":{"status":"human_review_required","summary":"Review the audit page, then allow agent install in a sandboxed workflow."},"agent_decision":{"input_task":"Use yyl-benchmark-breakdown","recommended_skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","audit_url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","safety_tier":"Reviewed","auto_install_policy":"review"},"alternative_skills":[{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"55/100 Review before install","trust":"80/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]}},{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","url":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","install_command":"npx skills add affaan-m/ECC --skill benchmark-methodology","why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"73/100 Review before install","trust":"76/100 Strong shortlist","notes":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","url":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","install_command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","why_consider":"Matches task terms: breakdown","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"85/100 Strong shortlist","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","install_target":"Codex install prompt","why_recommended":["Matches task terms: benchmark","Useful GitHub adoption: 6,163 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30","Primary pick for GitHub automation"],"risk_summary":{"level":"Safe to try","safety_tier":"Reviewed","safety":"75/100 Review before install","trust":"84/100 Strong shortlist","notes":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","action":"Review the audit page, then allow agent install in a sandboxed workflow."},"feedback":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_f9145679-f463-426f-a518-2e2380ffcca5\" --skill \"jeinlee1991-chinese-llm-benchmark\" --task \"Use yyl-benchmark-breakdown\" --agent \"codex\" --outcome success","contract":{"version":"openagentskill-agent-feedback-loop-v3","status":"active","purpose":"Report the result of one resolved skill run so Trust Score v5 and future Resolve rankings learn from real use.","event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","selected_skill_slug":"jeinlee1991-chinese-llm-benchmark","selected_skill_name":"Chinese Llm Benchmark","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","idempotency":"Retrying the same event_id updates the previous outcome.","dry_run":{"supported":true,"instruction":"Set dry_run=true to validate a payload before wiring a new agent integration."},"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"error_types":["install_failed","runtime_error","not_relevant","permission_blocked","risk_blocked","setup_required","low_quality_output","missing_dependency","timeout","other"],"workspaces":["sandbox","local","ci","production","unknown"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url"],"payload_template":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_f9145679-f463-426f-a518-2e2380ffcca5\" --skill \"jeinlee1991-chinese-llm-benchmark\" --task \"Use yyl-benchmark-breakdown\" --agent \"codex\" --outcome success","ranking_inputs_updated":["Trust Score v5 outcome confidence","Resolve ranking outcome evidence","Skill detail outcome signal block","Outcome leaderboard"]}},"agent_next_steps":["Read the audit URL before installing.","Ask for human approval before installing.","Use install command: npx skills add jeinlee1991/chinese-llm-benchmark","After one narrow task, report the outcome with: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_f9145679-f463-426f-a518-2e2380ffcca5\" --skill \"jeinlee1991-chinese-llm-benchmark\" --task \"Use yyl-benchmark-breakdown\" --agent \"codex\" --outcome success","Summarize output, warnings, files touched, and whether setup or human review was required."]},"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use yyl-benchmark-breakdown","agent":"codex","selected_skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","audit_url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add jeinlee1991/chinese-llm-benchmark","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":76,"label":"Review then install","version":"trust-score-v5","base_score":84,"outcome_confidence":0,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["76/100 Trust Score v5","84/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"status":"pass","detail":"6.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"status":"pass","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add jeinlee1991/chinese-llm-benchmark"},{"id":"install_safety","label":"Install command safety","score":92,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/jeinlee1991/chinese-llm-benchmark"},{"id":"review_status","label":"Review status","score":88,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"status":"info","detail":"No agent outcome data yet"}]},"risk":{"level":"Safe to try","audit_label":"Safe to try","safety":"75/100 Review before install","trust":"84/100 Strong shortlist","safety_tier":"Reviewed","notes":["License is unclear","License clarity: Unknown"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":80,"audit_score":71,"safety_score":55,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"55/100 Review before install","trust":"80/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]}},{"slug":"affaan-m-benchmark-methodology","name":"benchmark-methodology","url":"https://www.openagentskill.com/skills/affaan-m-benchmark-methodology","install_command":"npx skills add affaan-m/ECC --skill benchmark-methodology","trust_score":76,"audit_score":85,"safety_score":73,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"73/100 Review before install","trust":"76/100 Strong shortlist","notes":["Documentation summary is thin","The SKILL.md excerpt provided is truncated, but the available content is sufficient to assess the skill's purpose and structure.","No explicit limitations or edge cases are documented, though the methodology is well-scoped.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"addyosmani-planning-and-task-breakdown","name":"planning-and-task-breakdown","url":"https://www.openagentskill.com/skills/addyosmani-planning-and-task-breakdown","install_command":"npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown","trust_score":85,"audit_score":90,"safety_score":78,"why_consider":"Matches task terms: breakdown","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"85/100 Strong shortlist","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"embeddings-benchmark-mteb","name":"Mteb","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","install_command":"npx skills add embeddings-benchmark/mteb","trust_score":86,"audit_score":89,"safety_score":77,"why_consider":"Matches task terms: benchmark","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"77/100 Review before install","trust":"86/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"outcome_feedback":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_f9145679-f463-426f-a518-2e2380ffcca5","skill_slug":"jeinlee1991-chinese-llm-benchmark","task":"Use yyl-benchmark-breakdown","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_f9145679-f463-426f-a518-2e2380ffcca5\" --skill \"jeinlee1991-chinese-llm-benchmark\" --task \"Use yyl-benchmark-breakdown\" --agent \"codex\" --outcome success"},"next_agent_action":"Ask for human approval or choose a safer alternative before installing.","stable_fields":["decision_packet.selected_skill","decision_packet.install","decision_packet.risk.do_not_use_when","decision_packet.alternatives","decision_packet.outcome_feedback","decision_packet.trust.decision"]},"benchmark":{"endpoint":"https://www.openagentskill.com/api/agent/evals","note":"Use the evals endpoint to regression-test recommendation quality before changing ranking logic."},"meta":{"endpoint":"/api/agent/resolve","api_version":"2.0","generated_at":"2026-09-08T09:01:33.805Z","total_skills_searched":910,"total_candidates":15,"candidate_pool":{"sort":"quality","size":910,"note":"Resolver searches the highest-quality candidate pool for low-latency agent use. Browse /skills for the full public index."},"contract":{"best_skill":"recommendation.best_skill","install":"recommendation.install","why":"recommendation.why_recommended","risk":"recommendation.risk","alternatives":"recommendation.alternatives","agent_handoff":"agent_handoff.platform_templates + agent_handoff.review_checklist","decision_packet":"decision_packet","install_receipt":"install_receipt","recommendation_lanes":"recommendation_lanes"}}}