{"eval":{"version":"openagentskill-skill-eval-v1","slug":"agentscope-ai-paper-review","name":"paper-review","generated_at":"2026-09-06T07:40:12.816Z","task_input":"Evaluate paper-review before installing it in an AI agent workflow","status":"failed","score":63,"risk_level":"high","decision":{"recommendation":"do_not_auto_install","reason":"Agent safety gate: This skill should not be selected by an agent without explicit human security review.","auto_install_allowed":false,"policy":"block","human_review_required":true},"task_fit":{"score":84,"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Navigate pages","Click and type safely"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"]},"install":{"command":"npx skills add agentscope-ai/OpenJudge --skill paper-review","ready":true,"policy":"block","safety_label":"Avoid automatic install","targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add agentscope-ai-paper-review"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"paper-review\" agent skill from https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review. 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: Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file. 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\":\"agentscope-ai-paper-review\",\"task\":\"Install paper-review\",\"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 \"paper-review\" as a Claude Code skill from https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review. 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: Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file. 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\":\"agentscope-ai-paper-review\",\"task\":\"Install paper-review\",\"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 \"paper-review\" from https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review 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: Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file. 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\":\"agentscope-ai-paper-review\",\"task\":\"Install paper-review\",\"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."}]},"trust":{"score":66,"label":"Manual review","version":"trust-score-v4","evidence":{"stars":"816 GitHub stars","repoActivity":"816 stars, 65 forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review","install":"npx skills add agentscope-ai/OpenJudge --skill paper-review","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"}},"audit":{"score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Dependency or permission surface needs review","Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Inconsistency between SKILL.md and reference.md regarding vision mode default: SKILL.md says --vision is on by default, while reference.md lists use_vision_for_pdf default as False. This could confuse users about whether pypdfium2 is required by default.","The skill requires API keys and external API calls (LiteLLM, CrossRef, arXiv, DBLP), which may raise privacy or cost concerns, but these are standard for such tools and clearly documented.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution"]},"safety_gate":{"score":30,"tier":"blocked","label":"Blocked for auto-install","auto_install_policy":"block","blocked":true,"permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"browser","label":"Browser automation","reason":"Skill may drive a browser or interact with web pages.","severity":"medium"},{"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"},{"id":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"}],"policy_warnings":["High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review"]},"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":84,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate paper-review before installing it in an AI agent workflow","research","Research agents workflows; Claude Code teams; teams that value GitHub adoption signals"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add agentscope-ai/OpenJudge --skill paper-review"]},{"id":"install_safety","label":"Install command safety","status":"pass","score":92,"required_for_auto_install":true,"detail":"standard package or runtime install path","evidence":["npx skills add agentscope-ai/OpenJudge --skill paper-review"]},{"id":"trust_score","label":"Trust score","status":"warn","score":66,"required_for_auto_install":true,"detail":"Potentially useful, but at least one trust signal needs human inspection.","evidence":["Manual review","816 GitHub stars","Apache-2.0"]},{"id":"audit_score","label":"Audit score","status":"warn","score":74,"required_for_auto_install":true,"detail":"Needs review","evidence":["Dependency or permission surface needs review"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"fail","score":30,"required_for_auto_install":true,"detail":"This skill should not be selected by an agent without explicit human security review.","evidence":["Do not auto-install. Inspect the source, dependencies, and permission surface first.","Metadata combines secrets access with shell or command execution"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":86,"required_for_auto_install":false,"detail":"Metadata includes enough usage and workflow context","evidence":["Strong README/SKILL.md context"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"Apache-2.0","evidence":["Apache-2.0"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":88,"required_for_auto_install":false,"detail":"1mo since push","evidence":["1mo since push"]},{"id":"permission_surface","label":"Permission surface","status":"fail","score":22,"required_for_auto_install":true,"detail":"secrets or environment access, shell or command execution","evidence":["Shell or command execution: high","Browser automation: medium","Network access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"pass","score":82,"required_for_auto_install":false,"detail":"Alternative skills are available for comparison.","evidence":["yanliudesign-mono-color-skill","mvanhorn-last30days-skill","imbad0202-academic-research-skills","assafelovic-gpt-researcher"]}],"blockers":["Agent safety gate: This skill should not be selected by an agent without explicit human security review.","Permission surface: secrets or environment access, shell or command execution"],"warnings":["Trust score: Potentially useful, but at least one trust signal needs human inspection.","Audit score: Needs review","High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Inconsistency between SKILL.md and reference.md regarding vision mode default: SKILL.md says --vision is on by default, while reference.md lists use_vision_for_pdf default as False. This could confuse users about whether pypdfium2 is required by default.","The skill requires API keys and external API calls (LiteLLM, CrossRef, arXiv, DBLP), which may raise privacy or cost concerns, but these are standard for such tools and clearly documented.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","Inconsistency between SKILL.md and reference.md regarding vision mode default: SKILL.md says --vision is on by default, while reference.md lists use_vision_for_pdf default as False. This could confuse users about whether pypdfium2 is required by default.","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision"],"alternatives":[{"slug":"yanliudesign-mono-color-skill","name":"mono-color","url":"https://www.openagentskill.com/skills/yanliudesign-mono-color-skill","stars":1919,"install_command":"npx skills add yanliudesign/mono-color-skill --skill mono-color","trust_score":85,"audit_score":93},{"slug":"mvanhorn-last30days-skill","name":"Last30days Skill","url":"https://www.openagentskill.com/skills/mvanhorn-last30days-skill","stars":60956,"install_command":"npx skills add mvanhorn/last30days-skill -g","trust_score":94,"audit_score":95},{"slug":"imbad0202-academic-research-skills","name":"Academic Research Skills","url":"https://www.openagentskill.com/skills/imbad0202-academic-research-skills","stars":38374,"install_command":"npx skills add Imbad0202/academic-research-skills","trust_score":89,"audit_score":91},{"slug":"assafelovic-gpt-researcher","name":"GPT Researcher","url":"https://www.openagentskill.com/skills/assafelovic-gpt-researcher","stars":27966,"install_command":"npx skills add assafelovic/gpt-researcher","trust_score":85,"audit_score":90}],"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"agentscope-ai-paper-review","name":"paper-review","description":"Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.","category":"research","url":"https://www.openagentskill.com/skills/agentscope-ai-paper-review","repository":"https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review","github_repo":"agentscope-ai/OpenJudge"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Navigate pages","Click and type safely"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add agentscope-ai/OpenJudge --skill paper-review","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add agentscope-ai-paper-review"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"paper-review\" agent skill from https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review. 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: Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file. 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\":\"agentscope-ai-paper-review\",\"task\":\"Install paper-review\",\"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 \"paper-review\" as a Claude Code skill from https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review. 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: Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file. 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\":\"agentscope-ai-paper-review\",\"task\":\"Install paper-review\",\"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 \"paper-review\" from https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review 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: Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file. 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\":\"agentscope-ai-paper-review\",\"task\":\"Install paper-review\",\"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/agentscope-ai-paper-review/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/agentscope-ai-paper-review"},"trust":{"score":66,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"816 GitHub stars","repoActivity":"816 stars, 65 forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review","install":"npx skills add agentscope-ai/OpenJudge --skill paper-review","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Inconsistency between SKILL.md and reference.md regarding vision mode default: SKILL.md says --vision is on by default, while reference.md lists use_vision_for_pdf default as False. This could confuse users about whether pypdfium2 is required by default.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"]},"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":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Dependency or permission surface needs review","Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Inconsistency between SKILL.md and reference.md regarding vision mode default: SKILL.md says --vision is on by default, while reference.md lists use_vision_for_pdf default as False. This could confuse users about whether pypdfium2 is required by default.","The skill requires API keys and external API calls (LiteLLM, CrossRef, arXiv, DBLP), which may raise privacy or cost concerns, but these are standard for such tools and clearly documented.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution"]},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","auto_install_policy":"block","auto_install_allowed":false,"human_review_required":true,"blocked":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first."},"quality":{"score":70,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"1mo since push","risk":"Needs review"},"alternative_skills":[{"slug":"yanliudesign-mono-color-skill","name":"mono-color","url":"https://www.openagentskill.com/skills/yanliudesign-mono-color-skill","stars":1919,"install_command":"npx skills add yanliudesign/mono-color-skill --skill mono-color","trust_score":85,"audit_score":93},{"slug":"mvanhorn-last30days-skill","name":"Last30days Skill","url":"https://www.openagentskill.com/skills/mvanhorn-last30days-skill","stars":60956,"install_command":"npx skills add mvanhorn/last30days-skill -g","trust_score":94,"audit_score":95},{"slug":"imbad0202-academic-research-skills","name":"Academic Research Skills","url":"https://www.openagentskill.com/skills/imbad0202-academic-research-skills","stars":38374,"install_command":"npx skills add Imbad0202/academic-research-skills","trust_score":89,"audit_score":91},{"slug":"assafelovic-gpt-researcher","name":"GPT Researcher","url":"https://www.openagentskill.com/skills/assafelovic-gpt-researcher","stars":27966,"install_command":"npx skills add assafelovic/gpt-researcher","trust_score":85,"audit_score":90}],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","Inconsistency between SKILL.md and reference.md regarding vision mode default: SKILL.md says --vision is on by default, while reference.md lists use_vision_for_pdf default as False. This could confuse users about whether pypdfium2 is required by default.","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision"],"agent_contract":{"task_input":"Evaluate paper-review before installing it in an AI agent workflow","recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","install_policy":"block","minimum_review_before_use":["Trust: 66/100 Manual review","Audit: 74/100 Needs review","Safety: 30/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"agentscope-ai-paper-review (paper-review)","install_command":"npx skills add agentscope-ai/OpenJudge --skill paper-review","risk_summary":"Needs review; Blocked for auto-install; 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":"agentscope-ai-paper-review","task":"Evaluate paper-review before installing it in an AI agent workflow","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/agentscope-ai-paper-review","api":"https://www.openagentskill.com/api/agent/skills/agentscope-ai-paper-review","audit":"https://www.openagentskill.com/skills/agentscope-ai-paper-review/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=agentscope-ai-paper-review&task=Evaluate%20paper-review%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20paper-review%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Evaluate%20paper-review%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/agentscope-ai-paper-review/install","manifest":"https://www.openagentskill.com/api/registry/manifest/agentscope-ai-paper-review"}},"endpoints":{"web":"https://www.openagentskill.com/skills/agentscope-ai-paper-review","api":"https://www.openagentskill.com/api/agent/skills/agentscope-ai-paper-review","eval":"https://www.openagentskill.com/api/agent/evals?slug=agentscope-ai-paper-review","audit":"https://www.openagentskill.com/skills/agentscope-ai-paper-review/audit","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20paper-review%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium"}},"meta":{"endpoint":"/api/agent/evals","mode":"skill_eval","purpose":"Pre-install eval contract for a single skill. Agents should read this before installing a reusable skill.","generated_at":"2026-09-06T07:40:12.816Z"}}