{"eval":{"version":"openagentskill-skill-eval-v1","slug":"runmedev-vscode-runme","name":"Vscode Runme","generated_at":"2026-07-04T02:40:22.392Z","task_input":"Evaluate Vscode Runme before installing it in an AI agent workflow","status":"review","score":73,"risk_level":"medium","decision":{"recommendation":"manual_review","reason":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_allowed":false,"policy":"review","human_review_required":true},"task_fit":{"score":94,"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Read uploaded files","Extract structured fields"],"suited_agents":["TypeScript","Markdown","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"]},"install":{"command":"npx skills add runmedev/vscode-runme","ready":true,"policy":"review","safety_label":"Avoid automatic install","targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add runmedev/vscode-runme"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Vscode Runme\" agent skill from https://github.com/runmedev/vscode-runme. 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: DevOps Notebooks Built with Markdown - VS Code extension"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Vscode Runme\" as a Claude Code skill from https://github.com/runmedev/vscode-runme. 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: DevOps Notebooks Built with Markdown - VS Code extension"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Vscode Runme\" from https://github.com/runmedev/vscode-runme 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: DevOps Notebooks Built with Markdown - VS Code extension"}]},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","evidence":{"stars":"216 GitHub stars","repoActivity":"216 stars, 27 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/runmedev/vscode-runme","install":"npx skills add runmedev/vscode-runme","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"}},"audit":{"score":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 216 stars, 27 forks; issue activity unavailable in current metadata"]},"safety_gate":{"score":52,"tier":"experimental","label":"Experimental","auto_install_policy":"review","blocked":false,"permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"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":["High-risk permission hints: Shell or command execution","Quality score needs review"]},"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":94,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate Vscode Runme before installing it in an AI agent workflow","document-processing","Coding agents workflows; Claude Code teams; builders willing to evaluate younger projects"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add runmedev/vscode-runme"]},{"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 runmedev/vscode-runme"]},{"id":"trust_score","label":"Trust score","status":"warn","score":75,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","216 GitHub stars","Apache-2.0"]},{"id":"audit_score","label":"Audit score","status":"warn","score":80,"required_for_auto_install":true,"detail":"Needs review","evidence":["Quality score needs review"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":52,"required_for_auto_install":true,"detail":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","evidence":["Test manually in an isolated workspace and compare against safer alternatives.","High-risk permission hints: Shell or command execution"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"warn","score":74,"required_for_auto_install":false,"detail":"Public metadata needs stronger README/SKILL.md context","evidence":["Usable metadata, review docs"]},{"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":"2mo since push","evidence":["2mo since push"]},{"id":"permission_surface","label":"Permission surface","status":"warn","score":62,"required_for_auto_install":true,"detail":"shell or command execution, filesystem or document access","evidence":["Shell or command execution: high","Network access: medium","Filesystem access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"pass","score":82,"required_for_auto_install":false,"detail":"Alternative skills are available for comparison.","evidence":["microsoft-markitdown","paddlepaddle-paddleocr","stirling-tools-stirling-pdf","tesseract-ocr-tesseract"]}],"blockers":[],"warnings":["Trust score: Good trust signals with a few areas worth checking before rollout.","Audit score: Needs review","Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: shell or command execution, filesystem or document access","High-risk permission hints: Shell or command execution","Quality score needs review","Stars/forks activity: 216 stars, 27 forks; issue activity unavailable in current metadata"],"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","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Quality score needs review","Stars/forks activity: 216 stars, 27 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"alternatives":[{"slug":"microsoft-markitdown","name":"Markitdown","url":"https://www.openagentskill.com/skills/microsoft-markitdown","stars":156110,"install_command":"npx skills add microsoft/markitdown","trust_score":90,"audit_score":92},{"slug":"paddlepaddle-paddleocr","name":"PaddleOCR","url":"https://www.openagentskill.com/skills/paddlepaddle-paddleocr","stars":83080,"install_command":"npx skills add PaddlePaddle/PaddleOCR","trust_score":94,"audit_score":95},{"slug":"stirling-tools-stirling-pdf","name":"Stirling PDF","url":"https://www.openagentskill.com/skills/stirling-tools-stirling-pdf","stars":81218,"install_command":"npx skills add Stirling-Tools/Stirling-PDF","trust_score":87,"audit_score":92},{"slug":"tesseract-ocr-tesseract","name":"Tesseract","url":"https://www.openagentskill.com/skills/tesseract-ocr-tesseract","stars":74690,"install_command":"npx skills add tesseract-ocr/tesseract","trust_score":92,"audit_score":95}],"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"runmedev-vscode-runme","name":"Vscode Runme","description":"DevOps Notebooks Built with Markdown - VS Code extension","category":"document-processing","url":"https://www.openagentskill.com/skills/runmedev-vscode-runme","repository":"https://github.com/runmedev/vscode-runme","github_repo":"runmedev/vscode-runme"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Read uploaded files","Extract structured fields"],"suited_agents":["TypeScript","Markdown","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add runmedev/vscode-runme","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add runmedev/vscode-runme"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Vscode Runme\" agent skill from https://github.com/runmedev/vscode-runme. 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: DevOps Notebooks Built with Markdown - VS Code extension"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Vscode Runme\" as a Claude Code skill from https://github.com/runmedev/vscode-runme. 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: DevOps Notebooks Built with Markdown - VS Code extension"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Vscode Runme\" from https://github.com/runmedev/vscode-runme 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: DevOps Notebooks Built with Markdown - VS Code extension"}],"handoff_url":"https://www.openagentskill.com/api/skills/runmedev-vscode-runme/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/runmedev-vscode-runme"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"216 GitHub stars","repoActivity":"216 stars, 27 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/runmedev/vscode-runme","install":"npx skills add runmedev/vscode-runme","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, 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":["document-processing","markdown","documents","bash","devops","notebook"],"known_risks":["Quality score needs review","Stars/forks activity: 216 stars, 27 forks; issue activity unavailable in current metadata"]},"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":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 216 stars, 27 forks; issue activity unavailable in current metadata"]},"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":75,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[{"slug":"microsoft-markitdown","name":"Markitdown","url":"https://www.openagentskill.com/skills/microsoft-markitdown","stars":156110,"install_command":"npx skills add microsoft/markitdown","trust_score":90,"audit_score":92},{"slug":"paddlepaddle-paddleocr","name":"PaddleOCR","url":"https://www.openagentskill.com/skills/paddlepaddle-paddleocr","stars":83080,"install_command":"npx skills add PaddlePaddle/PaddleOCR","trust_score":94,"audit_score":95},{"slug":"stirling-tools-stirling-pdf","name":"Stirling PDF","url":"https://www.openagentskill.com/skills/stirling-tools-stirling-pdf","stars":81218,"install_command":"npx skills add Stirling-Tools/Stirling-PDF","trust_score":87,"audit_score":92},{"slug":"tesseract-ocr-tesseract","name":"Tesseract","url":"https://www.openagentskill.com/skills/tesseract-ocr-tesseract","stars":74690,"install_command":"npx skills add tesseract-ocr/tesseract","trust_score":92,"audit_score":95}],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Quality score needs review","Stars/forks activity: 216 stars, 27 forks; issue activity unavailable in current metadata","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":"Evaluate Vscode Runme before installing it in an AI agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 80/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"runmedev-vscode-runme (Vscode Runme)","install_command":"npx skills add runmedev/vscode-runme","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":"runmedev-vscode-runme","task":"Evaluate Vscode Runme 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/runmedev-vscode-runme","api":"https://www.openagentskill.com/api/agent/skills/runmedev-vscode-runme","audit":"https://www.openagentskill.com/skills/runmedev-vscode-runme/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=runmedev-vscode-runme&task=Evaluate%20Vscode%20Runme%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Vscode%20Runme%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Evaluate%20Vscode%20Runme%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/runmedev-vscode-runme/install","manifest":"https://www.openagentskill.com/api/registry/manifest/runmedev-vscode-runme"}},"endpoints":{"web":"https://www.openagentskill.com/skills/runmedev-vscode-runme","api":"https://www.openagentskill.com/api/agent/skills/runmedev-vscode-runme","eval":"https://www.openagentskill.com/api/agent/evals?slug=runmedev-vscode-runme","audit":"https://www.openagentskill.com/skills/runmedev-vscode-runme/audit","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Vscode%20Runme%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":"2026-07-04T02:40:22.392Z"}}