{"task":"Use Llama Cpp Agent","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"feedback":{"event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","outcome_api":"https://www.openagentskill.com/api/agent/outcome","method":"POST","selected_skill_slug":"maximilian-winter-llama-cpp-agent","selected_skill_name":"Llama Cpp Agent","alternative_skill_slugs":["dicklesworthstone-swiss-army-llama","andrewkchan-deepseek-cpp","run-llama-llama-index","meta-llama-llama-cookbook"],"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_ec7c352a-8e16-482a-8aa7-256d0987ac2e","skill_slug":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e\" --skill \"maximilian-winter-llama-cpp-agent\" --task \"Use Llama Cpp Agent\" --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_ec7c352a-8e16-482a-8aa7-256d0987ac2e","selected_skill_slug":"maximilian-winter-llama-cpp-agent","selected_skill_name":"Llama Cpp Agent","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_ec7c352a-8e16-482a-8aa7-256d0987ac2e","skill_slug":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e\" --skill \"maximilian-winter-llama-cpp-agent\" --task \"Use Llama Cpp Agent\" --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-v1","receipt_id":"receipt_ec7c352a-8e16-482a-8aa7-256d0987ac2e","resolve_event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","generated_at":"2026-08-22T15:33:10.409Z","task":"Use Llama Cpp Agent","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"urls":{"web":"https://www.openagentskill.com/resolve?task=Use+Llama+Cpp+Agent&agent=codex&max_risk=medium","json":"https://www.openagentskill.com/api/agent/receipt?task=Use+Llama+Cpp+Agent&agent=codex&max_risk=medium","text":"https://www.openagentskill.com/api/agent/receipt?task=Use+Llama+Cpp+Agent&agent=codex&max_risk=medium&format=text","resolve_json":"https://www.openagentskill.com/api/agent/resolve?task=Use+Llama+Cpp+Agent&agent=codex&max_risk=medium","resolve_text":"https://www.openagentskill.com/api/agent/resolve?task=Use+Llama+Cpp+Agent&agent=codex&max_risk=medium&format=text"},"selected_skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","description":"The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","api_url":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","audit_url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","install_api_url":"https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent"},"install":{"command":"npx skills add Maximilian-Winter/llama-cpp-agent","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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":"Require human approval before installing into a real workspace.","why_selected":["Matches task terms: llama, cpp","Useful GitHub adoption: 647 stars","Install handoff is available","Repository freshness signal is available","Registry match score 42","Companion skill for GitHub automation","68/100 Trust Score","0/100 Agent Proven Score"],"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"]},"trust":{"score":68,"label":"Sandbox only","version":"trust-score-v5","base_score":76,"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":"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"]},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","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"],"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":"Needs review","safety_tier":"Reviewed with permission notes","safety_score":65,"audit_score":77,"notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown","65/100 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","Quality score needs review","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"dicklesworthstone-swiss-army-llama","name":"Swiss Army Llama","url":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama","audit_url":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama/audit","install_command":"npx skills add Dicklesworthstone/swiss_army_llama","trust_score":77,"audit_score":69,"safety_score":53,"reason":"Matches task terms: llama","policy":"review"},{"slug":"andrewkchan-deepseek-cpp","name":"Deepseek.Cpp","url":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp","audit_url":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp/audit","install_command":"npx skills add andrewkchan/deepseek.cpp","trust_score":70,"audit_score":68,"safety_score":56,"reason":"Matches task terms: llama, cpp","policy":"review"},{"slug":"run-llama-llama-index","name":"Llama Index","url":"https://www.openagentskill.com/skills/run-llama-llama-index","audit_url":"https://www.openagentskill.com/skills/run-llama-llama-index/audit","install_command":"npx skills add run-llama/llama_index","trust_score":87,"audit_score":91,"safety_score":75,"reason":"Matches task terms: llama","policy":"review"},{"slug":"meta-llama-llama-cookbook","name":"Llama Cookbook","url":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","audit_url":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook/audit","install_command":"npx skills add meta-llama/llama-cookbook","trust_score":89,"audit_score":91,"safety_score":79,"reason":"Matches task terms: llama","policy":"review"}],"outcome_feedback":{"event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","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_ec7c352a-8e16-482a-8aa7-256d0987ac2e","skill_slug":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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."},"dry_run_payload":{"event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","skill_slug":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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.","dry_run":true},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e\" --skill \"maximilian-winter-llama-cpp-agent\" --task \"Use Llama Cpp Agent\" --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/maximilian-winter-llama-cpp-agent/audit","Fetch the pre-install eval: https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","Do not auto-install yet. Ask for human review before running: npx skills add Maximilian-Winter/llama-cpp-agent","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_ec7c352a-8e16-482a-8aa7-256d0987ac2e."],"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 Llama Cpp Agent","agent":"codex","best_skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","description":"The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","api_url":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","audit_url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent"},"install":{"command":"npx skills add Maximilian-Winter/llama-cpp-agent","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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/maximilian-winter-llama-cpp-agent/install","ready":true,"review_required":true,"auto_install_allowed":false,"policy":"review"},"why_recommended":["Matches task terms: llama, cpp","Useful GitHub adoption: 647 stars","Install handoff is available","Repository freshness signal is available","Registry match score 42","Companion skill for GitHub automation","68/100 OpenAgentSkill Trust Score v5","77/100 audit score"],"trust_score_v5":{"score":68,"base_score":76,"outcome_confidence":0,"tier":"review","label":"Sandbox only","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":"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"]},"evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","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":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","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"],"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","function-calling","llamacpp","llm"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add Maximilian-Winter/llama-cpp-agent","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","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","function-calling","llamacpp","llm"],"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","Quality score needs review","Documentation summary is thin","License clarity: Unknown"],"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."}}},"trust_score_v4":{"score":76,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","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","function-calling","llamacpp","llm"],"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","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"trust_score_v3":{"score":76,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]}},"trust_score_v2":{"score":76,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]}},"risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"65/100 Review before install","trust":"76/100 Strong shortlist","notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":["License is unclear","65/100 agent safety score"]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","description":"The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","github_repo":"Maximilian-Winter/llama-cpp-agent"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Maximilian-Winter/llama-cpp-agent","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install maximilian-winter-llama-cpp-agent"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" as a Claude Code skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" from https://github.com/Maximilian-Winter/llama-cpp-agent 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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/maximilian-winter-llama-cpp-agent/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/maximilian-winter-llama-cpp-agent"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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","function-calling","llamacpp","llm"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"6mo since push","risk":"Needs review"},"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","Quality score needs review","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Llama Cpp Agent","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"maximilian-winter-llama-cpp-agent (Llama Cpp Agent)","install_command":"npx skills add Maximilian-Winter/llama-cpp-agent","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":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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/maximilian-winter-llama-cpp-agent","api":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","audit":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install","manifest":"https://www.openagentskill.com/api/registry/manifest/maximilian-winter-llama-cpp-agent"}},"agent_contract":{"version":"openagentskill-resolve-contract-v2","input_task":"Use Llama Cpp Agent","recommended_skill_slug":"maximilian-winter-llama-cpp-agent","recommended_skill_name":"Llama Cpp Agent","install_command":"npx skills add Maximilian-Winter/llama-cpp-agent","install_policy":"review","auto_install_allowed":false,"human_review_required":true,"audit_url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","skill_api_url":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","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","Quality score needs review","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"maximilian-winter-llama-cpp-agent (Llama Cpp Agent)","install_command":"npx skills add Maximilian-Winter/llama-cpp-agent","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."}},"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":"design-creative","title":"Design and creative"}]},"maintenance":{"status":"active","label":"6mo since push","daysSincePush":166,"lastPushedAt":"2026-03-09T05:57:48+00:00"},"github_quality":{"stars":647,"starsLabel":"647","forks":70,"license":"Unknown","qualityScore":70,"trustScore":76,"auditScore":77},"coverage_tags":["Coding","GitHub automation","agent-frameworks","llm-agent","agents","function-calling","llamacpp","llm"]},"alternatives":[{"slug":"dicklesworthstone-swiss-army-llama","name":"Swiss Army Llama","url":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama","install_command":"npx skills add Dicklesworthstone/swiss_army_llama","trust_score":77,"audit_score":69,"safety_score":53,"why_consider":"Matches task terms: llama","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"53/100 Avoid automatic install","trust":"77/100 Strong shortlist","notes":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin"]}},{"slug":"andrewkchan-deepseek-cpp","name":"Deepseek.Cpp","url":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp","install_command":"npx skills add andrewkchan/deepseek.cpp","trust_score":70,"audit_score":68,"safety_score":56,"why_consider":"Matches task terms: llama, cpp","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"56/100 Review before install","trust":"70/100 Manual review","notes":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown"]}},{"slug":"run-llama-llama-index","name":"Llama Index","url":"https://www.openagentskill.com/skills/run-llama-llama-index","install_command":"npx skills add run-llama/llama_index","trust_score":87,"audit_score":91,"safety_score":75,"why_consider":"Matches task terms: llama","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"75/100 Review before install","trust":"87/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"meta-llama-llama-cookbook","name":"Llama Cookbook","url":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","install_command":"npx skills add meta-llama/llama-cookbook","trust_score":89,"audit_score":91,"safety_score":79,"why_consider":"Matches task terms: llama","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"79/100 Review before install","trust":"89/100 Production candidate","notes":["Documentation summary is thin"]}}],"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use Llama Cpp Agent","agent":"codex","selected_skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","api_url":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","audit_url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Maximilian-Winter/llama-cpp-agent","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":68,"label":"Sandbox only","version":"trust-score-v5","base_score":76,"outcome_confidence":0,"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":76,"status":"info","detail":"647 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"status":"info","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"status":"info","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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":"Needs review","audit_label":"Needs review","safety":"65/100 Review before install","trust":"76/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["License is unclear","Quality score needs review","Documentation summary is thin","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","Quality score needs review","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"dicklesworthstone-swiss-army-llama","name":"Swiss Army Llama","url":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama","install_command":"npx skills add Dicklesworthstone/swiss_army_llama","trust_score":77,"audit_score":69,"safety_score":53,"why_consider":"Matches task terms: llama","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"53/100 Avoid automatic install","trust":"77/100 Strong shortlist","notes":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin"]}},{"slug":"andrewkchan-deepseek-cpp","name":"Deepseek.Cpp","url":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp","install_command":"npx skills add andrewkchan/deepseek.cpp","trust_score":70,"audit_score":68,"safety_score":56,"why_consider":"Matches task terms: llama, cpp","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"56/100 Review before install","trust":"70/100 Manual review","notes":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown"]}},{"slug":"run-llama-llama-index","name":"Llama Index","url":"https://www.openagentskill.com/skills/run-llama-llama-index","install_command":"npx skills add run-llama/llama_index","trust_score":87,"audit_score":91,"safety_score":75,"why_consider":"Matches task terms: llama","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"75/100 Review before install","trust":"87/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"meta-llama-llama-cookbook","name":"Llama Cookbook","url":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","install_command":"npx skills add meta-llama/llama-cookbook","trust_score":89,"audit_score":91,"safety_score":79,"why_consider":"Matches task terms: llama","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"79/100 Review before install","trust":"89/100 Production candidate","notes":["Documentation summary is thin"]}}],"outcome_feedback":{"event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","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_ec7c352a-8e16-482a-8aa7-256d0987ac2e","skill_slug":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e\" --skill \"maximilian-winter-llama-cpp-agent\" --task \"Use Llama Cpp Agent\" --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 Llama Cpp Agent for: Use Llama Cpp Agent\nReview audit: https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit\nAsk for human approval before installing: npx skills add Maximilian-Winter/llama-cpp-agent\nIf the audit or policy warnings are unacceptable, choose one of the alternatives."},"recommendation_lanes":{"best_match":{"rank":1,"match_score":42,"raw_match_score":201.7,"semantic_relevance":42,"skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","description":"The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.","category":"agent-frameworks","github_stars":647,"created_at":"2026-05-23T07:49:08.044264+00:00","updated_at":"2026-03-09T05:57:48+00:00","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","github_repo":"Maximilian-Winter/llama-cpp-agent"},"recommendation_reasons":["Matches task terms: llama, cpp","Useful GitHub adoption: 647 stars","Install handoff is available","Repository freshness signal is available","Registry match score 42"],"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":"design-creative","title":"Design and creative"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Maximilian-Winter/llama-cpp-agent","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":647,"starsLabel":"647","forks":70,"license":"Unknown","qualityScore":70,"trustScore":76,"auditScore":77},"maintenance":{"status":"active","label":"6mo since push","daysSincePush":166,"lastPushedAt":"2026-03-09T05:57:48+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown","Needs review"]},"coverageTags":["Coding","GitHub automation","agent-frameworks","llm-agent","agents","function-calling","llamacpp","llm"]},"quality":{"score":70,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"647","tone":"positive"},{"label":"Freshness","value":"6mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"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":76,"weight":0.13,"status":"info","detail":"647 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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":"info","label":"GitHub adoption","detail":"647 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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 Maximilian-Winter/llama-cpp-agent","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","6mo since push"]},"agentCompatibility":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","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","function-calling","llamacpp","llm"],"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","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":76,"weight":0.13,"status":"info","detail":"647 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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":"info","label":"GitHub adoption","detail":"647 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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","Meaningful 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","Quality score needs review","Documentation summary is thin","License clarity: Unknown","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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 Maximilian-Winter/llama-cpp-agent","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","6mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","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":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","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"],"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","function-calling","llamacpp","llm"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add Maximilian-Winter/llama-cpp-agent","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","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","function-calling","llamacpp","llm"],"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","Quality score needs review","Documentation summary is thin","License clarity: Unknown"],"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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":65,"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":["License is unclear","65/100 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":["License is unclear"],"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":["License is unclear","65/100 agent safety score"]},"decision":{"readiness_score":81,"readiness_label":"Strong shortlist","headline":"Companion skill for GitHub automation","role":"Companion skill","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 Maximilian-Winter/llama-cpp-agent","value":"Install the \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 Llama Cpp Agent 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-v0.2.1/openagentskill-0.2.1.tgz install maximilian-winter-llama-cpp-agent","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 \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" as a Claude Code skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" from https://github.com/Maximilian-Winter/llama-cpp-agent 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","description":"The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","github_repo":"Maximilian-Winter/llama-cpp-agent"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Maximilian-Winter/llama-cpp-agent","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install maximilian-winter-llama-cpp-agent"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" as a Claude Code skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" from https://github.com/Maximilian-Winter/llama-cpp-agent 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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/maximilian-winter-llama-cpp-agent/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/maximilian-winter-llama-cpp-agent"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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","function-calling","llamacpp","llm"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"6mo since push","risk":"Needs review"},"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","Quality score needs review","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Llama Cpp Agent","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"maximilian-winter-llama-cpp-agent (Llama Cpp Agent)","install_command":"npx skills add Maximilian-Winter/llama-cpp-agent","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":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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/maximilian-winter-llama-cpp-agent","api":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","audit":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install","manifest":"https://www.openagentskill.com/api/registry/manifest/maximilian-winter-llama-cpp-agent"}},"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":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"}],"urls":{"web":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","api":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","install_api":"https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install","audit":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/maximilian-winter-llama-cpp-agent?metric=audit","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent"}},"safer_alternative":{"rank":5,"match_score":30,"raw_match_score":131.8,"semantic_relevance":30,"skill":{"slug":"meta-llama-llama-cookbook","name":"Llama Cookbook","description":"Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services  ","category":"ml-automation","github_stars":18356,"created_at":"2026-06-16T08:55:45.612917+00:00","updated_at":"2026-05-19T18:42:31+00:00","repository":"https://github.com/meta-llama/llama-cookbook","github_repo":"meta-llama/llama-cookbook"},"recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 18,356 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["LangChain","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add meta-llama/llama-cookbook","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":18356,"starsLabel":"18K","forks":2740,"license":"MIT","qualityScore":100,"trustScore":89,"auditScore":91},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":94,"lastPushedAt":"2026-05-19T18:42:31+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","ai","finetuning"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"18K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":89,"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":100,"weight":0.13,"status":"pass","detail":"18K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"18K stars, 2.7K 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":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 meta-llama/llama-cookbook"},{"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/meta-llama/llama-cookbook"},{"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":"18K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"18K stars, 2.7K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"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 meta-llama/llama-cookbook"},{"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/meta-llama/llama-cookbook"},{"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":["Documentation summary is thin"],"evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 2.7K forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/meta-llama/llama-cookbook","install":"npx skills add meta-llama/llama-cookbook","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 meta-llama/llama-cookbook","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":["Jupyter Notebook","Machine Learning","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":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"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":86,"base_score":89,"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":["86/100 Trust Score v5","89/100 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":100,"weight":0.13,"status":"pass","detail":"18K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"18K stars, 2.7K 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":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 meta-llama/llama-cookbook"},{"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/meta-llama/llama-cookbook"},{"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":"18K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"18K stars, 2.7K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"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 meta-llama/llama-cookbook"},{"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/meta-llama/llama-cookbook"},{"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":["Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 2.7K forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/meta-llama/llama-cookbook","install":"npx skills add meta-llama/llama-cookbook","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 meta-llama/llama-cookbook","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":["Jupyter Notebook","Machine Learning","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-v3","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"],"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":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add meta-llama/llama-cookbook","trust_score":86,"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":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"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":89,"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":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":79,"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","79/100 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","79/100 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","LangChain teams","teams that value GitHub adoption signals"],"risks":["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 meta-llama/llama-cookbook","value":"Install the \"Llama Cookbook\" agent skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 Llama Cookbook 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-v0.2.1/openagentskill-0.2.1.tgz install meta-llama-llama-cookbook","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 \"Llama Cookbook\" agent skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 \"Llama Cookbook\" as a Claude Code skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 \"Llama Cookbook\" from https://github.com/meta-llama/llama-cookbook 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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":"meta-llama-llama-cookbook","name":"Llama Cookbook","description":"Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services  ","category":"ml-automation","url":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","repository":"https://github.com/meta-llama/llama-cookbook","github_repo":"meta-llama/llama-cookbook"},"suited_tasks":["Browser automation workflows","LangChain teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add meta-llama/llama-cookbook","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install meta-llama-llama-cookbook"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Cookbook\" agent skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 \"Llama Cookbook\" as a Claude Code skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 \"Llama Cookbook\" from https://github.com/meta-llama/llama-cookbook 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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/meta-llama-llama-cookbook/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/meta-llama-llama-cookbook"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 2.7K forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/meta-llama/llama-cookbook","install":"npx skills add meta-llama/llama-cookbook","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":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"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":91,"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":"Design and creative production","scenario":"Multimodal media","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","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 Llama Cpp Agent","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 89/100 Production candidate","Audit: 91/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"meta-llama-llama-cookbook (Llama Cookbook)","install_command":"npx skills add meta-llama/llama-cookbook","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":"meta-llama-llama-cookbook","task":"Use Llama Cpp Agent","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/meta-llama-llama-cookbook","api":"https://www.openagentskill.com/api/agent/skills/meta-llama-llama-cookbook","audit":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=meta-llama-llama-cookbook&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/meta-llama-llama-cookbook/install","manifest":"https://www.openagentskill.com/api/registry/manifest/meta-llama-llama-cookbook"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","api":"https://www.openagentskill.com/api/agent/skills/meta-llama-llama-cookbook","install_api":"https://www.openagentskill.com/api/skills/meta-llama-llama-cookbook/install","audit":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=meta-llama-llama-cookbook&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/meta-llama-llama-cookbook?metric=audit","repository":"https://github.com/meta-llama/llama-cookbook"}},"popular_alternative":{"rank":14,"match_score":30,"raw_match_score":110.3,"semantic_relevance":30,"skill":{"slug":"ggml-org-whisper-cpp","name":"Whisper.Cpp","description":"Port of OpenAI's Whisper model in C/C++","category":"media-automation","github_stars":50964,"created_at":"2026-06-21T00:55:59.040458+00:00","updated_at":"2026-06-22T10:06:51+00:00","repository":"https://github.com/ggml-org/whisper.cpp","github_repo":"ggml-org/whisper.cpp"},"recommendation_reasons":["Matches task terms: cpp","Strong GitHub adoption: 50,964 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add ggml-org/whisper.cpp","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":50964,"starsLabel":"51K","forks":5692,"license":"MIT","qualityScore":100,"trustScore":88,"auditScore":91},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":61,"lastPushedAt":"2026-06-22T10:06:51+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":["Design","Multimodal media","media-automation","speech-recognition","voice","ml-media","inference","openai"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"51K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"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":100,"weight":0.13,"status":"pass","detail":"51K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"51K stars, 5.7K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 ggml-org/whisper.cpp"},{"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/ggml-org/whisper.cpp"},{"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":"51K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"51K stars, 5.7K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo 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 ggml-org/whisper.cpp"},{"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/ggml-org/whisper.cpp"},{"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"51K GitHub stars","repoActivity":"51K stars, 5.7K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/ggml-org/whisper.cpp","install":"npx skills add ggml-org/whisper.cpp","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 ggml-org/whisper.cpp","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","2mo since push"]},"agentCompatibility":["C++","Speech","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":["media-automation","speech-recognition","voice","ml-media","inference","openai"],"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":82,"base_score":88,"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":["82/100 Trust Score v5","88/100 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":100,"weight":0.13,"status":"pass","detail":"51K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"51K stars, 5.7K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 ggml-org/whisper.cpp"},{"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/ggml-org/whisper.cpp"},{"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":"51K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"51K stars, 5.7K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo 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 ggml-org/whisper.cpp"},{"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/ggml-org/whisper.cpp"},{"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","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":"51K GitHub stars","repoActivity":"51K stars, 5.7K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/ggml-org/whisper.cpp","install":"npx skills add ggml-org/whisper.cpp","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 ggml-org/whisper.cpp","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","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["C++","Speech","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-v3","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"],"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":["media-automation","speech-recognition","voice","ml-media","inference","openai"],"suited_agents":["C++","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add ggml-org/whisper.cpp","trust_score":82,"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":["media-automation","speech-recognition","voice","ml-media","inference","openai"],"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":88,"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":91,"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":79,"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","79/100 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","79/100 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","OpenAI Agents teams","teams that value GitHub adoption signals"],"risks":["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 ggml-org/whisper.cpp","value":"Install the \"Whisper.Cpp\" agent skill from https://github.com/ggml-org/whisper.cpp. 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: Port of OpenAI's Whisper model in C/C++ 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\":\"ggml-org-whisper-cpp\",\"task\":\"Install Whisper.Cpp\",\"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 Whisper.Cpp 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-v0.2.1/openagentskill-0.2.1.tgz install ggml-org-whisper-cpp","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 \"Whisper.Cpp\" agent skill from https://github.com/ggml-org/whisper.cpp. 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: Port of OpenAI's Whisper model in C/C++ 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\":\"ggml-org-whisper-cpp\",\"task\":\"Install Whisper.Cpp\",\"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 \"Whisper.Cpp\" as a Claude Code skill from https://github.com/ggml-org/whisper.cpp. 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: Port of OpenAI's Whisper model in C/C++ 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\":\"ggml-org-whisper-cpp\",\"task\":\"Install Whisper.Cpp\",\"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 \"Whisper.Cpp\" from https://github.com/ggml-org/whisper.cpp 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: Port of OpenAI's Whisper model in C/C++ 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\":\"ggml-org-whisper-cpp\",\"task\":\"Install Whisper.Cpp\",\"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":"ggml-org-whisper-cpp","name":"Whisper.Cpp","description":"Port of OpenAI's Whisper model in C/C++","category":"media-automation","url":"https://www.openagentskill.com/skills/ggml-org-whisper-cpp","repository":"https://github.com/ggml-org/whisper.cpp","github_repo":"ggml-org/whisper.cpp"},"suited_tasks":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Inspect repository metadata","Compare code changes"],"suited_agents":["C++","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add ggml-org/whisper.cpp","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install ggml-org-whisper-cpp"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Whisper.Cpp\" agent skill from https://github.com/ggml-org/whisper.cpp. 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: Port of OpenAI's Whisper model in C/C++ 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\":\"ggml-org-whisper-cpp\",\"task\":\"Install Whisper.Cpp\",\"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 \"Whisper.Cpp\" as a Claude Code skill from https://github.com/ggml-org/whisper.cpp. 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: Port of OpenAI's Whisper model in C/C++ 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\":\"ggml-org-whisper-cpp\",\"task\":\"Install Whisper.Cpp\",\"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 \"Whisper.Cpp\" from https://github.com/ggml-org/whisper.cpp 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: Port of OpenAI's Whisper model in C/C++ 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\":\"ggml-org-whisper-cpp\",\"task\":\"Install Whisper.Cpp\",\"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/ggml-org-whisper-cpp/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ggml-org-whisper-cpp"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"51K GitHub stars","repoActivity":"51K stars, 5.7K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/ggml-org/whisper.cpp","install":"npx skills add ggml-org/whisper.cpp","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":["media-automation","speech-recognition","voice","ml-media","inference","openai"],"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":91,"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":100,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo 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 Llama Cpp Agent","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 91/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ggml-org-whisper-cpp (Whisper.Cpp)","install_command":"npx skills add ggml-org/whisper.cpp","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":"ggml-org-whisper-cpp","task":"Use Llama Cpp Agent","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/ggml-org-whisper-cpp","api":"https://www.openagentskill.com/api/agent/skills/ggml-org-whisper-cpp","audit":"https://www.openagentskill.com/skills/ggml-org-whisper-cpp/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ggml-org-whisper-cpp&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ggml-org-whisper-cpp/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ggml-org-whisper-cpp"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"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"}],"urls":{"web":"https://www.openagentskill.com/skills/ggml-org-whisper-cpp","api":"https://www.openagentskill.com/api/agent/skills/ggml-org-whisper-cpp","install_api":"https://www.openagentskill.com/api/skills/ggml-org-whisper-cpp/install","audit":"https://www.openagentskill.com/skills/ggml-org-whisper-cpp/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ggml-org-whisper-cpp&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/ggml-org-whisper-cpp?metric=audit","repository":"https://github.com/ggml-org/whisper.cpp"}},"new_contender":{"rank":8,"match_score":42,"raw_match_score":120,"semantic_relevance":42,"skill":{"slug":"mgonzs13-llama-ros","name":"Llama Ros","description":"llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2","category":"rag-knowledge","github_stars":260,"created_at":"2026-06-27T13:22:04.189948+00:00","updated_at":"2026-07-13T11:37:09+00:00","repository":"https://github.com/mgonzs13/llama_ros","github_repo":"mgonzs13/llama_ros"},"recommendation_reasons":["Matches task terms: llama, cpp","Install handoff is available","Repository freshness signal is available","Registry match score 42"],"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":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["OpenAI Agents","LangChain","CLI","Codex","Claude Code"],"install":{"ready":true,"command":"npx skills add mgonzs13/llama_ros","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":260,"starsLabel":"260","forks":47,"license":"MIT","qualityScore":69,"trustScore":76,"auditScore":79},"maintenance":{"status":"active","label":"1mo since push","daysSincePush":40,"lastPushedAt":"2026-07-13T11:37:09+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","reranking","search","knowledge","audio","cpp"]},"quality":{"score":69,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"260","tone":"neutral"},{"label":"Freshness","value":"1mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"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":62,"weight":0.13,"status":"info","detail":"260 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"260 stars, 47 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 mgonzs13/llama_ros"},{"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/mgonzs13/llama_ros"},{"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":"info","label":"GitHub adoption","detail":"260 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"260 stars, 47 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo 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 mgonzs13/llama_ros"},{"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/mgonzs13/llama_ros"},{"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","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"260 GitHub stars","repoActivity":"260 stars, 47 forks","lastPushed":"1mo since push","license":"MIT","repository":"https://github.com/mgonzs13/llama_ros","install":"npx skills add mgonzs13/llama_ros","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 mgonzs13/llama_ros","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","1mo since push"]},"agentCompatibility":["C++","Reranking","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","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":["rag-knowledge","reranking","search","knowledge","audio","cpp"],"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":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","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":62,"weight":0.13,"status":"info","detail":"260 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"260 stars, 47 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 mgonzs13/llama_ros"},{"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/mgonzs13/llama_ros"},{"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":"info","label":"GitHub adoption","detail":"260 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"260 stars, 47 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo 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 mgonzs13/llama_ros"},{"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/mgonzs13/llama_ros"},{"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","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","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":"260 GitHub stars","repoActivity":"260 stars, 47 forks","lastPushed":"1mo since push","license":"MIT","repository":"https://github.com/mgonzs13/llama_ros","install":"npx skills add mgonzs13/llama_ros","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 mgonzs13/llama_ros","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","1mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["C++","Reranking","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","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-v3","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"],"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","reranking","search","knowledge","audio","cpp"],"suited_agents":["C++","Reranking","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add mgonzs13/llama_ros","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":["rag-knowledge","reranking","search","knowledge","audio","cpp"],"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":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","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":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":67,"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","67/100 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","67/100 agent safety score"]},"decision":{"readiness_score":68,"readiness_label":"Prototype first","headline":"Fallback candidate for RAG and knowledge","role":"Fallback candidate","best_for":["RAG and knowledge workflows","OpenAI Agents teams","builders willing to evaluate younger projects"],"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 mgonzs13/llama_ros","value":"Install the \"Llama Ros\" agent skill from https://github.com/mgonzs13/llama_ros. 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: llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2 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\":\"mgonzs13-llama-ros\",\"task\":\"Install Llama Ros\",\"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 Llama Ros 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-v0.2.1/openagentskill-0.2.1.tgz install mgonzs13-llama-ros","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 \"Llama Ros\" agent skill from https://github.com/mgonzs13/llama_ros. 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: llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2 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\":\"mgonzs13-llama-ros\",\"task\":\"Install Llama Ros\",\"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 \"Llama Ros\" as a Claude Code skill from https://github.com/mgonzs13/llama_ros. 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: llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2 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\":\"mgonzs13-llama-ros\",\"task\":\"Install Llama Ros\",\"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 \"Llama Ros\" from https://github.com/mgonzs13/llama_ros 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: llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2 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\":\"mgonzs13-llama-ros\",\"task\":\"Install Llama Ros\",\"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":"mgonzs13-llama-ros","name":"Llama Ros","description":"llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/mgonzs13-llama-ros","repository":"https://github.com/mgonzs13/llama_ros","github_repo":"mgonzs13/llama_ros"},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["C++","Reranking","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add mgonzs13/llama_ros","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install mgonzs13-llama-ros"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Ros\" agent skill from https://github.com/mgonzs13/llama_ros. 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: llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2 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\":\"mgonzs13-llama-ros\",\"task\":\"Install Llama Ros\",\"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 \"Llama Ros\" as a Claude Code skill from https://github.com/mgonzs13/llama_ros. 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: llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2 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\":\"mgonzs13-llama-ros\",\"task\":\"Install Llama Ros\",\"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 \"Llama Ros\" from https://github.com/mgonzs13/llama_ros 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: llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2 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\":\"mgonzs13-llama-ros\",\"task\":\"Install Llama Ros\",\"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/mgonzs13-llama-ros/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/mgonzs13-llama-ros"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"260 GitHub stars","repoActivity":"260 stars, 47 forks","lastPushed":"1mo since push","license":"MIT","repository":"https://github.com/mgonzs13/llama_ros","install":"npx skills add mgonzs13/llama_ros","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":["rag-knowledge","reranking","search","knowledge","audio","cpp"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","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":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","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":69,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1mo since push","risk":"Needs review"},"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","Quality score needs review","Stars/forks activity: 260 stars, 47 forks; issue activity unavailable in current metadata","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 Llama Cpp Agent","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 79/100 Needs review","Safety: 67/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"mgonzs13-llama-ros (Llama Ros)","install_command":"npx skills add mgonzs13/llama_ros","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":"mgonzs13-llama-ros","task":"Use Llama Cpp Agent","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/mgonzs13-llama-ros","api":"https://www.openagentskill.com/api/agent/skills/mgonzs13-llama-ros","audit":"https://www.openagentskill.com/skills/mgonzs13-llama-ros/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=mgonzs13-llama-ros&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/mgonzs13-llama-ros/install","manifest":"https://www.openagentskill.com/api/registry/manifest/mgonzs13-llama-ros"}},"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":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"}],"urls":{"web":"https://www.openagentskill.com/skills/mgonzs13-llama-ros","api":"https://www.openagentskill.com/api/agent/skills/mgonzs13-llama-ros","install_api":"https://www.openagentskill.com/api/skills/mgonzs13-llama-ros/install","audit":"https://www.openagentskill.com/skills/mgonzs13-llama-ros/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=mgonzs13-llama-ros&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/mgonzs13-llama-ros?metric=audit","repository":"https://github.com/mgonzs13/llama_ros"}},"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":42,"raw_match_score":201.7,"semantic_relevance":42,"skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","description":"The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.","category":"agent-frameworks","github_stars":647,"created_at":"2026-05-23T07:49:08.044264+00:00","updated_at":"2026-03-09T05:57:48+00:00","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","github_repo":"Maximilian-Winter/llama-cpp-agent"},"recommendation_reasons":["Matches task terms: llama, cpp","Useful GitHub adoption: 647 stars","Install handoff is available","Repository freshness signal is available","Registry match score 42"],"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":"design-creative","title":"Design and creative"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Maximilian-Winter/llama-cpp-agent","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":647,"starsLabel":"647","forks":70,"license":"Unknown","qualityScore":70,"trustScore":76,"auditScore":77},"maintenance":{"status":"active","label":"6mo since push","daysSincePush":166,"lastPushedAt":"2026-03-09T05:57:48+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown","Needs review"]},"coverageTags":["Coding","GitHub automation","agent-frameworks","llm-agent","agents","function-calling","llamacpp","llm"]},"quality":{"score":70,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"647","tone":"positive"},{"label":"Freshness","value":"6mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"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":76,"weight":0.13,"status":"info","detail":"647 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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":"info","label":"GitHub adoption","detail":"647 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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 Maximilian-Winter/llama-cpp-agent","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","6mo since push"]},"agentCompatibility":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","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","function-calling","llamacpp","llm"],"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","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":76,"weight":0.13,"status":"info","detail":"647 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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":"info","label":"GitHub adoption","detail":"647 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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","Meaningful 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","Quality score needs review","Documentation summary is thin","License clarity: Unknown","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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 Maximilian-Winter/llama-cpp-agent","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","6mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","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":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","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"],"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","function-calling","llamacpp","llm"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add Maximilian-Winter/llama-cpp-agent","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","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","function-calling","llamacpp","llm"],"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","Quality score needs review","Documentation summary is thin","License clarity: Unknown"],"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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":65,"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":["License is unclear","65/100 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":["License is unclear"],"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":["License is unclear","65/100 agent safety score"]},"decision":{"readiness_score":81,"readiness_label":"Strong shortlist","headline":"Companion skill for GitHub automation","role":"Companion skill","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 Maximilian-Winter/llama-cpp-agent","value":"Install the \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 Llama Cpp Agent 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-v0.2.1/openagentskill-0.2.1.tgz install maximilian-winter-llama-cpp-agent","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 \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" as a Claude Code skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" from https://github.com/Maximilian-Winter/llama-cpp-agent 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","description":"The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","github_repo":"Maximilian-Winter/llama-cpp-agent"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Maximilian-Winter/llama-cpp-agent","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install maximilian-winter-llama-cpp-agent"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" as a Claude Code skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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 \"Llama Cpp Agent\" from https://github.com/Maximilian-Winter/llama-cpp-agent 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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/maximilian-winter-llama-cpp-agent/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/maximilian-winter-llama-cpp-agent"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"647 GitHub stars","repoActivity":"647 stars, 70 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","install":"npx skills add Maximilian-Winter/llama-cpp-agent","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","function-calling","llamacpp","llm"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"6mo since push","risk":"Needs review"},"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","Quality score needs review","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Llama Cpp Agent","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"maximilian-winter-llama-cpp-agent (Llama Cpp Agent)","install_command":"npx skills add Maximilian-Winter/llama-cpp-agent","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":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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/maximilian-winter-llama-cpp-agent","api":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","audit":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install","manifest":"https://www.openagentskill.com/api/registry/manifest/maximilian-winter-llama-cpp-agent"}},"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":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"}],"urls":{"web":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","api":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","install_api":"https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install","audit":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/maximilian-winter-llama-cpp-agent?metric=audit","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent"}},"alternatives":[{"rank":2,"match_score":30,"raw_match_score":153.1,"semantic_relevance":30,"skill":{"slug":"dicklesworthstone-swiss-army-llama","name":"Swiss Army Llama","description":"A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.","category":"rag-knowledge","github_stars":1053,"created_at":"2026-06-05T06:01:50.296095+00:00","updated_at":"2025-02-27T11:19:55+00:00","repository":"https://github.com/Dicklesworthstone/swiss_army_llama","github_repo":"Dicklesworthstone/swiss_army_llama"},"recommendation_reasons":["Matches task terms: llama","Useful GitHub adoption: 1,053 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":"github-automation","title":"GitHub automation"},{"slug":"customer-support","title":"Customer support"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Dicklesworthstone/swiss_army_llama","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1053,"starsLabel":"1.1K","forks":66,"license":"Unknown","qualityScore":60,"trustScore":77,"auditScore":69},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":541,"lastPushedAt":"2025-02-27T11:19:55+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","semantic-search","retrieval","knowledge","embedding-similarity","embedding-vectors"]},"quality":{"score":60,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"1.1K","tone":"positive"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":77,"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":"1.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.1K stars, 66 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y 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 Dicklesworthstone/swiss_army_llama"},{"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":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Dicklesworthstone/swiss_army_llama"},{"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":"1.1K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.1K stars, 66 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y 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 Dicklesworthstone/swiss_army_llama"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Dicklesworthstone/swiss_army_llama"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","License clarity: Unknown"],"evidence":{"stars":"1.1K GitHub stars","repoActivity":"1.1K stars, 66 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/Dicklesworthstone/swiss_army_llama","install":"npx skills add Dicklesworthstone/swiss_army_llama","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add Dicklesworthstone/swiss_army_llama","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","1y since push"]},"agentCompatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y 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":["rag-knowledge","semantic-search","retrieval","knowledge","embedding-similarity","embedding-vectors"],"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","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","License clarity: Unknown"]},"trust_v5":{"version":"trust-score-v5","score":69,"base_score":77,"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":["69/100 Trust Score v5","77/100 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":"1.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.1K stars, 66 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y 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 Dicklesworthstone/swiss_army_llama"},{"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":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Dicklesworthstone/swiss_army_llama"},{"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":"1.1K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.1K stars, 66 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y 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 Dicklesworthstone/swiss_army_llama"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Dicklesworthstone/swiss_army_llama"},{"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","Meaningful 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","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","License clarity: Unknown","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"1.1K GitHub stars","repoActivity":"1.1K stars, 66 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/Dicklesworthstone/swiss_army_llama","install":"npx skills add Dicklesworthstone/swiss_army_llama","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","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 Dicklesworthstone/swiss_army_llama","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","1y 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":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y 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-v3","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"],"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","embedding-similarity","embedding-vectors"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add Dicklesworthstone/swiss_army_llama","trust_score":69,"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":["rag-knowledge","semantic-search","retrieval","knowledge","embedding-similarity","embedding-vectors"],"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","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","License clarity: Unknown"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":77,"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":69,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin"]},"safety":{"score":53,"level":"avoid_auto_install","label":"Avoid automatic 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":["License is unclear","53/100 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":["License is unclear"],"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":["License is unclear","53/100 agent safety score"]},"decision":{"readiness_score":62,"readiness_label":"Prototype first","headline":"Fallback candidate for RAG and knowledge","role":"Fallback candidate","best_for":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","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 Dicklesworthstone/swiss_army_llama","value":"Install the \"Swiss Army Llama\" agent skill from https://github.com/Dicklesworthstone/swiss_army_llama. 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: A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract. 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\":\"dicklesworthstone-swiss-army-llama\",\"task\":\"Install Swiss Army Llama\",\"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 Swiss Army Llama 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-v0.2.1/openagentskill-0.2.1.tgz install dicklesworthstone-swiss-army-llama","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 \"Swiss Army Llama\" agent skill from https://github.com/Dicklesworthstone/swiss_army_llama. 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: A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract. 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\":\"dicklesworthstone-swiss-army-llama\",\"task\":\"Install Swiss Army Llama\",\"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 \"Swiss Army Llama\" as a Claude Code skill from https://github.com/Dicklesworthstone/swiss_army_llama. 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: A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract. 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\":\"dicklesworthstone-swiss-army-llama\",\"task\":\"Install Swiss Army Llama\",\"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 \"Swiss Army Llama\" from https://github.com/Dicklesworthstone/swiss_army_llama 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: A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract. 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\":\"dicklesworthstone-swiss-army-llama\",\"task\":\"Install Swiss Army Llama\",\"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":"dicklesworthstone-swiss-army-llama","name":"Swiss Army Llama","description":"A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama","repository":"https://github.com/Dicklesworthstone/swiss_army_llama","github_repo":"Dicklesworthstone/swiss_army_llama"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Dicklesworthstone/swiss_army_llama","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install dicklesworthstone-swiss-army-llama"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Swiss Army Llama\" agent skill from https://github.com/Dicklesworthstone/swiss_army_llama. 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: A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract. 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\":\"dicklesworthstone-swiss-army-llama\",\"task\":\"Install Swiss Army Llama\",\"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 \"Swiss Army Llama\" as a Claude Code skill from https://github.com/Dicklesworthstone/swiss_army_llama. 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: A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract. 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\":\"dicklesworthstone-swiss-army-llama\",\"task\":\"Install Swiss Army Llama\",\"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 \"Swiss Army Llama\" from https://github.com/Dicklesworthstone/swiss_army_llama 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: A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract. 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\":\"dicklesworthstone-swiss-army-llama\",\"task\":\"Install Swiss Army Llama\",\"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/dicklesworthstone-swiss-army-llama/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/dicklesworthstone-swiss-army-llama"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.1K GitHub stars","repoActivity":"1.1K stars, 66 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/Dicklesworthstone/swiss_army_llama","install":"npx skills add Dicklesworthstone/swiss_army_llama","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","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":["rag-knowledge","semantic-search","retrieval","knowledge","embedding-similarity","embedding-vectors"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","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":69,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","License clarity: Unknown"]},"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":60,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1y 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","No OpenAgentSkill engagement data yet","License is unclear","Repository appears stale","Quality score needs review","Documentation summary is thin"],"agent_contract":{"task_input":"Use Llama Cpp Agent","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 77/100 Strong shortlist","Audit: 69/100 Needs review","Safety: 53/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"dicklesworthstone-swiss-army-llama (Swiss Army Llama)","install_command":"npx skills add Dicklesworthstone/swiss_army_llama","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":"dicklesworthstone-swiss-army-llama","task":"Use Llama Cpp Agent","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/dicklesworthstone-swiss-army-llama","api":"https://www.openagentskill.com/api/agent/skills/dicklesworthstone-swiss-army-llama","audit":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=dicklesworthstone-swiss-army-llama&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/dicklesworthstone-swiss-army-llama/install","manifest":"https://www.openagentskill.com/api/registry/manifest/dicklesworthstone-swiss-army-llama"}},"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"customer-support","title":"Customer support","url":"https://www.openagentskill.com/use-cases/customer-support"}],"urls":{"web":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama","api":"https://www.openagentskill.com/api/agent/skills/dicklesworthstone-swiss-army-llama","install_api":"https://www.openagentskill.com/api/skills/dicklesworthstone-swiss-army-llama/install","audit":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=dicklesworthstone-swiss-army-llama&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/dicklesworthstone-swiss-army-llama?metric=audit","repository":"https://github.com/Dicklesworthstone/swiss_army_llama"}},{"rank":3,"match_score":42,"raw_match_score":142.6,"semantic_relevance":42,"skill":{"slug":"andrewkchan-deepseek-cpp","name":"Deepseek.Cpp","description":"CPU inference for the DeepSeek family of large language models in C++","category":"ml-automation","github_stars":317,"created_at":"2026-06-21T03:57:13.473453+00:00","updated_at":"2025-10-02T23:33:05+00:00","repository":"https://github.com/andrewkchan/deepseek.cpp","github_repo":"andrewkchan/deepseek.cpp"},"recommendation_reasons":["Matches task terms: llama, cpp","Install handoff is available","Repository freshness signal is available","Registry match score 42"],"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","C++"],"install":{"ready":true,"command":"npx skills add andrewkchan/deepseek.cpp","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":317,"starsLabel":"317","forks":33,"license":"Unknown","qualityScore":53,"trustScore":70,"auditScore":68},"maintenance":{"status":"stable","label":"11mo since push","daysSincePush":323,"lastPushedAt":"2025-10-02T23:33:05+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","cpp","deepseek"]},"quality":{"score":53,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"317","tone":"neutral"},{"label":"Freshness","value":"11mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":70,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"317 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"317 stars, 33 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"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 andrewkchan/deepseek.cpp"},{"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/andrewkchan/deepseek.cpp"},{"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":"info","label":"GitHub adoption","detail":"317 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"317 stars, 33 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"11mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"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 andrewkchan/deepseek.cpp"},{"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/andrewkchan/deepseek.cpp"},{"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","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"317 GitHub stars","repoActivity":"317 stars, 33 forks","lastPushed":"11mo since push","license":"Unknown","repository":"https://github.com/andrewkchan/deepseek.cpp","install":"npx skills add andrewkchan/deepseek.cpp","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 andrewkchan/deepseek.cpp","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","11mo since push"]},"agentCompatibility":["C++","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","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":["ml-automation","machine-learning","automation","ml-media","cpp","deepseek"],"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","Quality score needs review","Documentation summary is thin","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":62,"base_score":70,"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":["62/100 Trust Score v5","70/100 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":62,"weight":0.13,"status":"info","detail":"317 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"317 stars, 33 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"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 andrewkchan/deepseek.cpp"},{"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/andrewkchan/deepseek.cpp"},{"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":"info","label":"GitHub adoption","detail":"317 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"317 stars, 33 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"11mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"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 andrewkchan/deepseek.cpp"},{"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/andrewkchan/deepseek.cpp"},{"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","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown","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":"317 GitHub stars","repoActivity":"317 stars, 33 forks","lastPushed":"11mo since push","license":"Unknown","repository":"https://github.com/andrewkchan/deepseek.cpp","install":"npx skills add andrewkchan/deepseek.cpp","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 andrewkchan/deepseek.cpp","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","11mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["C++","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","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":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","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"],"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":["ml-automation","machine-learning","automation","ml-media","cpp","deepseek"],"suited_agents":["C++","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add andrewkchan/deepseek.cpp","trust_score":62,"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":["ml-automation","machine-learning","automation","ml-media","cpp","deepseek"],"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","Quality score needs review","Documentation summary is thin","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":70,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"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":68,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"safety":{"score":56,"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":["License is unclear","56/100 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":["License is unclear"],"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":["License is unclear","56/100 agent safety score"]},"decision":{"readiness_score":43,"readiness_label":"Needs manual review","headline":"Needs validation for Browser automation","role":"Needs validation","best_for":["Browser automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["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 andrewkchan/deepseek.cpp","value":"Install the \"Deepseek.Cpp\" agent skill from https://github.com/andrewkchan/deepseek.cpp. 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: CPU inference for the DeepSeek family of large language models in C++ 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\":\"andrewkchan-deepseek-cpp\",\"task\":\"Install Deepseek.Cpp\",\"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 Deepseek.Cpp 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-v0.2.1/openagentskill-0.2.1.tgz install andrewkchan-deepseek-cpp","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 \"Deepseek.Cpp\" agent skill from https://github.com/andrewkchan/deepseek.cpp. 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: CPU inference for the DeepSeek family of large language models in C++ 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\":\"andrewkchan-deepseek-cpp\",\"task\":\"Install Deepseek.Cpp\",\"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 \"Deepseek.Cpp\" as a Claude Code skill from https://github.com/andrewkchan/deepseek.cpp. 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: CPU inference for the DeepSeek family of large language models in C++ 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\":\"andrewkchan-deepseek-cpp\",\"task\":\"Install Deepseek.Cpp\",\"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 \"Deepseek.Cpp\" from https://github.com/andrewkchan/deepseek.cpp 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: CPU inference for the DeepSeek family of large language models in C++ 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\":\"andrewkchan-deepseek-cpp\",\"task\":\"Install Deepseek.Cpp\",\"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":"andrewkchan-deepseek-cpp","name":"Deepseek.Cpp","description":"CPU inference for the DeepSeek family of large language models in C++","category":"ml-automation","url":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp","repository":"https://github.com/andrewkchan/deepseek.cpp","github_repo":"andrewkchan/deepseek.cpp"},"suited_tasks":["Browser automation workflows","general agent builders","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["C++","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add andrewkchan/deepseek.cpp","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install andrewkchan-deepseek-cpp"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Deepseek.Cpp\" agent skill from https://github.com/andrewkchan/deepseek.cpp. 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: CPU inference for the DeepSeek family of large language models in C++ 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\":\"andrewkchan-deepseek-cpp\",\"task\":\"Install Deepseek.Cpp\",\"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 \"Deepseek.Cpp\" as a Claude Code skill from https://github.com/andrewkchan/deepseek.cpp. 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: CPU inference for the DeepSeek family of large language models in C++ 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\":\"andrewkchan-deepseek-cpp\",\"task\":\"Install Deepseek.Cpp\",\"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 \"Deepseek.Cpp\" from https://github.com/andrewkchan/deepseek.cpp 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: CPU inference for the DeepSeek family of large language models in C++ 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\":\"andrewkchan-deepseek-cpp\",\"task\":\"Install Deepseek.Cpp\",\"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/andrewkchan-deepseek-cpp/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/andrewkchan-deepseek-cpp"},"trust":{"score":70,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"317 GitHub stars","repoActivity":"317 stars, 33 forks","lastPushed":"11mo since push","license":"Unknown","repository":"https://github.com/andrewkchan/deepseek.cpp","install":"npx skills add andrewkchan/deepseek.cpp","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":["ml-automation","machine-learning","automation","ml-media","cpp","deepseek"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown","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":68,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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":53,"label":"Needs review"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"11mo since push","risk":"Needs review"},"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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"agent_contract":{"task_input":"Use Llama Cpp Agent","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 70/100 Manual review","Audit: 68/100 Needs review","Safety: 56/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"andrewkchan-deepseek-cpp (Deepseek.Cpp)","install_command":"npx skills add andrewkchan/deepseek.cpp","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":"andrewkchan-deepseek-cpp","task":"Use Llama Cpp Agent","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/andrewkchan-deepseek-cpp","api":"https://www.openagentskill.com/api/agent/skills/andrewkchan-deepseek-cpp","audit":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=andrewkchan-deepseek-cpp&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/andrewkchan-deepseek-cpp/install","manifest":"https://www.openagentskill.com/api/registry/manifest/andrewkchan-deepseek-cpp"}},"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":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"}],"urls":{"web":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp","api":"https://www.openagentskill.com/api/agent/skills/andrewkchan-deepseek-cpp","install_api":"https://www.openagentskill.com/api/skills/andrewkchan-deepseek-cpp/install","audit":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=andrewkchan-deepseek-cpp&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/andrewkchan-deepseek-cpp?metric=audit","repository":"https://github.com/andrewkchan/deepseek.cpp"}},{"rank":4,"match_score":30,"raw_match_score":134.3,"semantic_relevance":30,"skill":{"slug":"run-llama-llama-index","name":"Llama Index","description":"LlamaIndex is the leading document agent and OCR platform","category":"data","github_stars":50200,"created_at":"2026-05-21T15:36:32.432376+00:00","updated_at":"2026-06-17T19:25:43+00:00","repository":"https://github.com/run-llama/llama_index","github_repo":"run-llama/llama_index"},"recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 50,200 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"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":"document-processing","title":"Document processing"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["LlamaIndex","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add run-llama/llama_index","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":50200,"starsLabel":"50K","forks":7581,"license":"MIT","qualityScore":100,"trustScore":87,"auditScore":91},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":65,"lastPushedAt":"2026-06-17T19:25:43+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","data","rag","retrieval","agents","application","fine-tuning"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"50K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":87,"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":100,"weight":0.13,"status":"pass","detail":"50K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"50K stars, 7.6K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 run-llama/llama_index"},{"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":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/run-llama/llama_index"},{"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":"50K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"50K stars, 7.6K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo 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 run-llama/llama_index"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/run-llama/llama_index"},{"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"50K GitHub stars","repoActivity":"50K stars, 7.6K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/run-llama/llama_index","install":"npx skills add run-llama/llama_index","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add run-llama/llama_index","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","2mo since push"]},"agentCompatibility":["Python","RAG","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":["data","rag","retrieval","agents","application","fine-tuning"],"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":81,"base_score":87,"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":["81/100 Trust Score v5","87/100 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":100,"weight":0.13,"status":"pass","detail":"50K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"50K stars, 7.6K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 run-llama/llama_index"},{"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":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/run-llama/llama_index"},{"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":"50K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"50K stars, 7.6K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo 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 run-llama/llama_index"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/run-llama/llama_index"},{"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","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":"50K GitHub stars","repoActivity":"50K stars, 7.6K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/run-llama/llama_index","install":"npx skills add run-llama/llama_index","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","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 run-llama/llama_index","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","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","RAG","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-v3","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"],"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":["data","rag","retrieval","agents","application","fine-tuning"],"suited_agents":["Python","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add run-llama/llama_index","trust_score":81,"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":["data","rag","retrieval","agents","application","fine-tuning"],"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":87,"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":91,"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":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"},{"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":"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 RAG and knowledge","role":"Primary pick","best_for":["RAG and knowledge workflows","LlamaIndex teams","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 run-llama/llama_index","value":"Install the \"Llama Index\" agent skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform 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\":\"run-llama-llama-index\",\"task\":\"Install Llama Index\",\"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 Llama Index 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-v0.2.1/openagentskill-0.2.1.tgz install run-llama-llama-index","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 \"Llama Index\" agent skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform 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\":\"run-llama-llama-index\",\"task\":\"Install Llama Index\",\"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 \"Llama Index\" as a Claude Code skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform 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\":\"run-llama-llama-index\",\"task\":\"Install Llama Index\",\"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 \"Llama Index\" from https://github.com/run-llama/llama_index 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: LlamaIndex is the leading document agent and OCR platform 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\":\"run-llama-llama-index\",\"task\":\"Install Llama Index\",\"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":"run-llama-llama-index","name":"Llama Index","description":"LlamaIndex is the leading document agent and OCR platform","category":"data","url":"https://www.openagentskill.com/skills/run-llama-llama-index","repository":"https://github.com/run-llama/llama_index","github_repo":"run-llama/llama_index"},"suited_tasks":["RAG and knowledge workflows","LlamaIndex teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Read uploaded files","Extract structured fields"],"suited_agents":["Python","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LlamaIndex","CLI"],"install":{"command":"npx skills add run-llama/llama_index","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install run-llama-llama-index"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Index\" agent skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform 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\":\"run-llama-llama-index\",\"task\":\"Install Llama Index\",\"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 \"Llama Index\" as a Claude Code skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform 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\":\"run-llama-llama-index\",\"task\":\"Install Llama Index\",\"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 \"Llama Index\" from https://github.com/run-llama/llama_index 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: LlamaIndex is the leading document agent and OCR platform 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\":\"run-llama-llama-index\",\"task\":\"Install Llama Index\",\"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/run-llama-llama-index/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/run-llama-llama-index"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"50K GitHub stars","repoActivity":"50K stars, 7.6K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/run-llama/llama_index","install":"npx skills add run-llama/llama_index","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","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":["data","rag","retrieval","agents","application","fine-tuning"],"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":91,"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":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"2mo 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 Llama Cpp Agent","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 87/100 Production candidate","Audit: 91/100 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":"run-llama-llama-index (Llama Index)","install_command":"npx skills add run-llama/llama_index","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":"run-llama-llama-index","task":"Use Llama Cpp Agent","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/run-llama-llama-index","api":"https://www.openagentskill.com/api/agent/skills/run-llama-llama-index","audit":"https://www.openagentskill.com/skills/run-llama-llama-index/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=run-llama-llama-index&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/run-llama-llama-index/install","manifest":"https://www.openagentskill.com/api/registry/manifest/run-llama-llama-index"}},"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/run-llama-llama-index","api":"https://www.openagentskill.com/api/agent/skills/run-llama-llama-index","install_api":"https://www.openagentskill.com/api/skills/run-llama-llama-index/install","audit":"https://www.openagentskill.com/skills/run-llama-llama-index/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=run-llama-llama-index&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/run-llama-llama-index?metric=audit","repository":"https://github.com/run-llama/llama_index"}},{"rank":5,"match_score":30,"raw_match_score":131.8,"semantic_relevance":30,"skill":{"slug":"meta-llama-llama-cookbook","name":"Llama Cookbook","description":"Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services  ","category":"ml-automation","github_stars":18356,"created_at":"2026-06-16T08:55:45.612917+00:00","updated_at":"2026-05-19T18:42:31+00:00","repository":"https://github.com/meta-llama/llama-cookbook","github_repo":"meta-llama/llama-cookbook"},"recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 18,356 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["LangChain","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add meta-llama/llama-cookbook","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":18356,"starsLabel":"18K","forks":2740,"license":"MIT","qualityScore":100,"trustScore":89,"auditScore":91},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":94,"lastPushedAt":"2026-05-19T18:42:31+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","ai","finetuning"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"18K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":89,"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":100,"weight":0.13,"status":"pass","detail":"18K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"18K stars, 2.7K 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":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 meta-llama/llama-cookbook"},{"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/meta-llama/llama-cookbook"},{"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":"18K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"18K stars, 2.7K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"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 meta-llama/llama-cookbook"},{"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/meta-llama/llama-cookbook"},{"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":["Documentation summary is thin"],"evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 2.7K forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/meta-llama/llama-cookbook","install":"npx skills add meta-llama/llama-cookbook","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 meta-llama/llama-cookbook","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":["Jupyter Notebook","Machine Learning","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":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"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":86,"base_score":89,"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":["86/100 Trust Score v5","89/100 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":100,"weight":0.13,"status":"pass","detail":"18K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"18K stars, 2.7K 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":86,"weight":0.09,"status":"pass","detail":"MIT"},{"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 meta-llama/llama-cookbook"},{"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/meta-llama/llama-cookbook"},{"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":"18K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"18K stars, 2.7K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"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 meta-llama/llama-cookbook"},{"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/meta-llama/llama-cookbook"},{"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":["Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 2.7K forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/meta-llama/llama-cookbook","install":"npx skills add meta-llama/llama-cookbook","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 meta-llama/llama-cookbook","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":["Jupyter Notebook","Machine Learning","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-v3","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"],"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":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add meta-llama/llama-cookbook","trust_score":86,"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":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"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":89,"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":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":79,"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","79/100 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","79/100 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","LangChain teams","teams that value GitHub adoption signals"],"risks":["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 meta-llama/llama-cookbook","value":"Install the \"Llama Cookbook\" agent skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 Llama Cookbook 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-v0.2.1/openagentskill-0.2.1.tgz install meta-llama-llama-cookbook","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 \"Llama Cookbook\" agent skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 \"Llama Cookbook\" as a Claude Code skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 \"Llama Cookbook\" from https://github.com/meta-llama/llama-cookbook 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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":"meta-llama-llama-cookbook","name":"Llama Cookbook","description":"Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services  ","category":"ml-automation","url":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","repository":"https://github.com/meta-llama/llama-cookbook","github_repo":"meta-llama/llama-cookbook"},"suited_tasks":["Browser automation workflows","LangChain teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add meta-llama/llama-cookbook","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install meta-llama-llama-cookbook"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Cookbook\" agent skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 \"Llama Cookbook\" as a Claude Code skill from https://github.com/meta-llama/llama-cookbook. 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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 \"Llama Cookbook\" from https://github.com/meta-llama/llama-cookbook 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: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services 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\":\"meta-llama-llama-cookbook\",\"task\":\"Install Llama Cookbook\",\"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/meta-llama-llama-cookbook/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/meta-llama-llama-cookbook"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 2.7K forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/meta-llama/llama-cookbook","install":"npx skills add meta-llama/llama-cookbook","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":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"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":91,"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":"Design and creative production","scenario":"Multimodal media","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","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 Llama Cpp Agent","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 89/100 Production candidate","Audit: 91/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"meta-llama-llama-cookbook (Llama Cookbook)","install_command":"npx skills add meta-llama/llama-cookbook","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":"meta-llama-llama-cookbook","task":"Use Llama Cpp Agent","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/meta-llama-llama-cookbook","api":"https://www.openagentskill.com/api/agent/skills/meta-llama-llama-cookbook","audit":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=meta-llama-llama-cookbook&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/meta-llama-llama-cookbook/install","manifest":"https://www.openagentskill.com/api/registry/manifest/meta-llama-llama-cookbook"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","api":"https://www.openagentskill.com/api/agent/skills/meta-llama-llama-cookbook","install_api":"https://www.openagentskill.com/api/skills/meta-llama-llama-cookbook/install","audit":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=meta-llama-llama-cookbook&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/meta-llama-llama-cookbook?metric=audit","repository":"https://github.com/meta-llama/llama-cookbook"}}],"blocked_candidates":[],"agent_workflow":{"mode":"resolve_review_install","recommended_action":"Require human approval before installing into a real workspace.","selected_skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent"},"install":{"target":"codex","label":"Codex install prompt","kind":"agent-prompt","command":"npx skills add Maximilian-Winter/llama-cpp-agent","value":"Install the \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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/maximilian-winter-llama-cpp-agent/install"},"copy_paste_prompt":"Task: Use Llama Cpp Agent\nUse Llama Cpp Agent from https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent.\nReview the audit first: https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit\nReview the eval first: https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install\nInstall command: npx skills add Maximilian-Winter/llama-cpp-agent\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%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","skill_slug":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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."}}],"review_checklist":["Safety tier: Reviewed with permission notes","Safety score: 65/100 Review before install","Audit score: 77/100 Needs review","Trust score: 68/100 Sandbox only","Readiness: 81/100 Strong shortlist","License is unclear","License is unclear","Quality score needs review","Documentation summary is thin"],"fallback_strategy":[{"slug":"dicklesworthstone-swiss-army-llama","name":"Swiss Army Llama","reason":"Matches task terms: llama","url":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama","install_api":"https://www.openagentskill.com/api/skills/dicklesworthstone-swiss-army-llama/install"},{"slug":"andrewkchan-deepseek-cpp","name":"Deepseek.Cpp","reason":"Matches task terms: llama, cpp","url":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp","install_api":"https://www.openagentskill.com/api/skills/andrewkchan-deepseek-cpp/install"},{"slug":"run-llama-llama-index","name":"Llama Index","reason":"Matches task terms: llama","url":"https://www.openagentskill.com/skills/run-llama-llama-index","install_api":"https://www.openagentskill.com/api/skills/run-llama-llama-index/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_ec7c352a-8e16-482a-8aa7-256d0987ac2e"}},"agent_handoff":{"version":"openagentskill-agent-handoff-v1","mode":"resolve_compare_review_install","task":"Use Llama Cpp Agent","agent":"codex","selected_skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","api_url":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","audit_url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent"},"install_plan":{"command":"npx skills add Maximilian-Winter/llama-cpp-agent","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Llama Cpp Agent\" agent skill from https://github.com/Maximilian-Winter/llama-cpp-agent. 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: The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls. 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\":\"maximilian-winter-llama-cpp-agent\",\"task\":\"Install Llama Cpp Agent\",\"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/maximilian-winter-llama-cpp-agent/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%20Llama%20Cpp%20Agent&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","skill_slug":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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."}}],"platform_templates":[{"id":"codex","name":"Codex","surface":"Coding agent / local workspace","copy_prompt":"Task: Use Llama Cpp Agent\nSelected skill: Llama Cpp Agent (maximilian-winter-llama-cpp-agent)\nSkill URL: https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent\nAudit URL: https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install\nInstall command: npx skills add Maximilian-Winter/llama-cpp-agent\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- Swiss Army Llama (dicklesworthstone-swiss-army-llama): https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama\n- Deepseek.Cpp (andrewkchan-deepseek-cpp): https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp\n- Llama Index (run-llama-llama-index): https://www.openagentskill.com/skills/run-llama-llama-index\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 Llama Cpp Agent\nSelected skill: Llama Cpp Agent (maximilian-winter-llama-cpp-agent)\nSkill URL: https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent\nAudit URL: https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install\nInstall command: npx skills add Maximilian-Winter/llama-cpp-agent\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- Swiss Army Llama (dicklesworthstone-swiss-army-llama): https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama\n- Deepseek.Cpp (andrewkchan-deepseek-cpp): https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp\n- Llama Index (run-llama-llama-index): https://www.openagentskill.com/skills/run-llama-llama-index\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 Llama Cpp Agent\nSelected skill: Llama Cpp Agent (maximilian-winter-llama-cpp-agent)\nSkill URL: https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent\nAudit URL: https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=maximilian-winter-llama-cpp-agent&task=Use%20Llama%20Cpp%20Agent&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/maximilian-winter-llama-cpp-agent/install\nInstall command: npx skills add Maximilian-Winter/llama-cpp-agent\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- Swiss Army Llama (dicklesworthstone-swiss-army-llama): https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama\n- Deepseek.Cpp (andrewkchan-deepseek-cpp): https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp\n- Llama Index (run-llama-llama-index): https://www.openagentskill.com/skills/run-llama-llama-index\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 with permission notes","Safety score: 65/100 Review before install","Audit score: 77/100 Needs review","Trust score: 68/100 Sandbox only","Readiness: 81/100 Strong shortlist","License is unclear","License is unclear","Quality score needs review","Documentation summary is thin"],"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_ec7c352a-8e16-482a-8aa7-256d0987ac2e"},"feedback":{"event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e\" --skill \"maximilian-winter-llama-cpp-agent\" --task \"Use Llama Cpp Agent\" --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":"Require human approval before installing into a real workspace."},"agent_decision":{"input_task":"Use Llama Cpp Agent","recommended_skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","audit_url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent","safety_tier":"Reviewed with permission notes","auto_install_policy":"review"},"alternative_skills":[{"slug":"dicklesworthstone-swiss-army-llama","name":"Swiss Army Llama","url":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama","install_command":"npx skills add Dicklesworthstone/swiss_army_llama","why_consider":"Matches task terms: llama","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"53/100 Avoid automatic install","trust":"77/100 Strong shortlist","notes":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin"]}},{"slug":"andrewkchan-deepseek-cpp","name":"Deepseek.Cpp","url":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp","install_command":"npx skills add andrewkchan/deepseek.cpp","why_consider":"Matches task terms: llama, cpp","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"56/100 Review before install","trust":"70/100 Manual review","notes":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown"]}},{"slug":"run-llama-llama-index","name":"Llama Index","url":"https://www.openagentskill.com/skills/run-llama-llama-index","install_command":"npx skills add run-llama/llama_index","why_consider":"Matches task terms: llama","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"75/100 Review before install","trust":"87/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"install_command":"npx skills add Maximilian-Winter/llama-cpp-agent","install_target":"Codex install prompt","why_recommended":["Matches task terms: llama, cpp","Useful GitHub adoption: 647 stars","Install handoff is available","Repository freshness signal is available","Registry match score 42","Companion skill for GitHub automation"],"risk_summary":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"65/100 Review before install","trust":"76/100 Strong shortlist","notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","action":"Require human approval before installing into a real workspace."},"feedback":{"event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e\" --skill \"maximilian-winter-llama-cpp-agent\" --task \"Use Llama Cpp Agent\" --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_ec7c352a-8e16-482a-8aa7-256d0987ac2e","selected_skill_slug":"maximilian-winter-llama-cpp-agent","selected_skill_name":"Llama Cpp Agent","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_ec7c352a-8e16-482a-8aa7-256d0987ac2e","skill_slug":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e\" --skill \"maximilian-winter-llama-cpp-agent\" --task \"Use Llama Cpp Agent\" --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 Maximilian-Winter/llama-cpp-agent","After one narrow task, report the outcome with: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e\" --skill \"maximilian-winter-llama-cpp-agent\" --task \"Use Llama Cpp Agent\" --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 Llama Cpp Agent","agent":"codex","selected_skill":{"slug":"maximilian-winter-llama-cpp-agent","name":"Llama Cpp Agent","url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent","api_url":"https://www.openagentskill.com/api/agent/skills/maximilian-winter-llama-cpp-agent","audit_url":"https://www.openagentskill.com/skills/maximilian-winter-llama-cpp-agent/audit","repository":"https://github.com/Maximilian-Winter/llama-cpp-agent"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Maximilian-Winter/llama-cpp-agent","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":68,"label":"Sandbox only","version":"trust-score-v5","base_score":76,"outcome_confidence":0,"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":76,"status":"info","detail":"647 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"status":"info","detail":"647 stars, 70 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"status":"info","detail":"6mo 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 Maximilian-Winter/llama-cpp-agent"},{"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/Maximilian-Winter/llama-cpp-agent"},{"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":"Needs review","audit_label":"Needs review","safety":"65/100 Review before install","trust":"76/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["License is unclear","Quality score needs review","Documentation summary is thin","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","Quality score needs review","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"dicklesworthstone-swiss-army-llama","name":"Swiss Army Llama","url":"https://www.openagentskill.com/skills/dicklesworthstone-swiss-army-llama","install_command":"npx skills add Dicklesworthstone/swiss_army_llama","trust_score":77,"audit_score":69,"safety_score":53,"why_consider":"Matches task terms: llama","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"53/100 Avoid automatic install","trust":"77/100 Strong shortlist","notes":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin"]}},{"slug":"andrewkchan-deepseek-cpp","name":"Deepseek.Cpp","url":"https://www.openagentskill.com/skills/andrewkchan-deepseek-cpp","install_command":"npx skills add andrewkchan/deepseek.cpp","trust_score":70,"audit_score":68,"safety_score":56,"why_consider":"Matches task terms: llama, cpp","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"56/100 Review before install","trust":"70/100 Manual review","notes":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 317 stars, 33 forks; issue activity unavailable in current metadata","License clarity: Unknown"]}},{"slug":"run-llama-llama-index","name":"Llama Index","url":"https://www.openagentskill.com/skills/run-llama-llama-index","install_command":"npx skills add run-llama/llama_index","trust_score":87,"audit_score":91,"safety_score":75,"why_consider":"Matches task terms: llama","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"75/100 Review before install","trust":"87/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"meta-llama-llama-cookbook","name":"Llama Cookbook","url":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","install_command":"npx skills add meta-llama/llama-cookbook","trust_score":89,"audit_score":91,"safety_score":79,"why_consider":"Matches task terms: llama","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"79/100 Review before install","trust":"89/100 Production candidate","notes":["Documentation summary is thin"]}}],"outcome_feedback":{"event_id":"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e","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_ec7c352a-8e16-482a-8aa7-256d0987ac2e","skill_slug":"maximilian-winter-llama-cpp-agent","task":"Use Llama Cpp Agent","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_ec7c352a-8e16-482a-8aa7-256d0987ac2e\" --skill \"maximilian-winter-llama-cpp-agent\" --task \"Use Llama Cpp Agent\" --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":"2026-08-22T15:33:10.409Z","total_skills_searched":851,"total_candidates":15,"candidate_pool":{"sort":"quality","size":851,"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"}}}