{"eval":{"version":"openagentskill-skill-eval-v1","slug":"pulumi-agent-skills","name":"Agent Skills","generated_at":"2026-08-11T04:40:20.978Z","task_input":"Evaluate Agent Skills before installing it in an AI agent workflow","status":"failed","score":71,"risk_level":"high","decision":{"recommendation":"do_not_auto_install","reason":"Permission surface: secrets or environment access, filesystem or document access","auto_install_allowed":false,"policy":"block","human_review_required":true},"task_fit":{"score":84,"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"]},"install":{"command":"npx skills add pulumi/agent-skills","ready":true,"policy":"review","safety_label":"Avoid automatic install","targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add pulumi/agent-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Agent Skills\" agent skill from https://github.com/pulumi/agent-skills. 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 collection of reusable agent skills for Pulumi workflows, including migrations from Terraform, CDK, and CloudFormation, packaged for AI coding assistants. 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\":\"pulumi-agent-skills\",\"task\":\"Install Agent Skills\",\"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 \"Agent Skills\" as a Claude Code skill from https://github.com/pulumi/agent-skills. 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 collection of reusable agent skills for Pulumi workflows, including migrations from Terraform, CDK, and CloudFormation, packaged for AI coding assistants. 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\":\"pulumi-agent-skills\",\"task\":\"Install Agent Skills\",\"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 \"Agent Skills\" from https://github.com/pulumi/agent-skills 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 collection of reusable agent skills for Pulumi workflows, including migrations from Terraform, CDK, and CloudFormation, packaged for AI coding assistants. 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\":\"pulumi-agent-skills\",\"task\":\"Install Agent Skills\",\"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":73,"label":"Strong shortlist","version":"trust-score-v4","evidence":{"stars":"63 GitHub stars","repoActivity":"63 stars, 5 forks","lastPushed":"4d since push","license":"Apache-2.0","repository":"https://github.com/pulumi/agent-skills","install":"npx skills add pulumi/agent-skills","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"}},"audit":{"score":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Dependency or permission surface needs review","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: secrets or environment access, filesystem or document access","GitHub adoption: 63 GitHub stars","Stars/forks activity: 63 stars, 5 forks; issue activity unavailable in current metadata","Dependency/runtime risk: credential or environment access, network or browser surface","Permission surface: secrets or environment access, filesystem or document access"]},"safety_gate":{"score":49,"tier":"experimental","label":"Experimental","auto_install_policy":"review","blocked":false,"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"},{"id":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"},{"id":"database","label":"Database access","reason":"Skill may inspect schemas, query databases, or work with persistent stores.","severity":"medium"}],"policy_warnings":["High-risk permission hints: 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 Agent Skills before installing it in an AI agent workflow","coding-agents","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 pulumi/agent-skills"]},{"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 pulumi/agent-skills"]},{"id":"trust_score","label":"Trust score","status":"warn","score":73,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","63 GitHub stars","Apache-2.0"]},{"id":"audit_score","label":"Audit score","status":"warn","score":81,"required_for_auto_install":true,"detail":"Needs review","evidence":["Dependency or permission surface needs review"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":49,"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: Secrets or environment access"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":90,"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":100,"required_for_auto_install":false,"detail":"4d since push","evidence":["4d since push"]},{"id":"permission_surface","label":"Permission surface","status":"fail","score":34,"required_for_auto_install":true,"detail":"secrets or environment access, filesystem or document access","evidence":["Network access: medium","Filesystem access: medium","Secrets or environment access: high"]},{"id":"alternatives","label":"Alternatives available","status":"pass","score":82,"required_for_auto_install":false,"detail":"Alternative skills are available for comparison.","evidence":["mattpocock-grill-with-docs","mattpocock-code-review","mattpocock-to-spec","mattpocock-to-tickets"]}],"blockers":["Permission surface: secrets or environment access, filesystem or document access"],"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.","High-risk permission hints: Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: secrets or environment access, filesystem or document access","GitHub adoption: 63 GitHub stars","Stars/forks activity: 63 stars, 5 forks; issue activity unavailable in current metadata","Dependency/runtime risk: credential or environment access, network or browser surface","Permission surface: secrets or environment access, filesystem or document 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","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: secrets or environment access, filesystem or document access"],"alternatives":[{"slug":"mattpocock-grill-with-docs","name":"Grill With Docs","url":"https://www.openagentskill.com/skills/mattpocock-grill-with-docs","stars":164748,"install_command":"npx skills add mattpocock/skills --skill grill-with-docs","trust_score":89,"audit_score":91},{"slug":"mattpocock-code-review","name":"Code Review","url":"https://www.openagentskill.com/skills/mattpocock-code-review","stars":168580,"install_command":"npx skills add mattpocock/skills --skill code-review","trust_score":94,"audit_score":95},{"slug":"mattpocock-to-spec","name":"To Spec","url":"https://www.openagentskill.com/skills/mattpocock-to-spec","stars":164748,"install_command":"npx skills add mattpocock/skills --skill to-spec","trust_score":90,"audit_score":92},{"slug":"mattpocock-to-tickets","name":"To Tickets","url":"https://www.openagentskill.com/skills/mattpocock-to-tickets","stars":176665,"install_command":"npx skills add mattpocock/skills --skill to-tickets","trust_score":91,"audit_score":93}],"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pulumi-agent-skills","name":"Agent Skills","description":"A collection of reusable agent skills for Pulumi workflows, including migrations from Terraform, CDK, and CloudFormation, packaged for AI coding assistants.","category":"coding-agents","url":"https://www.openagentskill.com/skills/pulumi-agent-skills","repository":"https://github.com/pulumi/agent-skills","github_repo":"pulumi/agent-skills"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add pulumi/agent-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add pulumi/agent-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Agent Skills\" agent skill from https://github.com/pulumi/agent-skills. 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 collection of reusable agent skills for Pulumi workflows, including migrations from Terraform, CDK, and CloudFormation, packaged for AI coding assistants. 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\":\"pulumi-agent-skills\",\"task\":\"Install Agent Skills\",\"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 \"Agent Skills\" as a Claude Code skill from https://github.com/pulumi/agent-skills. 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 collection of reusable agent skills for Pulumi workflows, including migrations from Terraform, CDK, and CloudFormation, packaged for AI coding assistants. 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\":\"pulumi-agent-skills\",\"task\":\"Install Agent Skills\",\"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 \"Agent Skills\" from https://github.com/pulumi/agent-skills 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 collection of reusable agent skills for Pulumi workflows, including migrations from Terraform, CDK, and CloudFormation, packaged for AI coding assistants. 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\":\"pulumi-agent-skills\",\"task\":\"Install Agent Skills\",\"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/pulumi-agent-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pulumi-agent-skills"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"63 GitHub stars","repoActivity":"63 stars, 5 forks","lastPushed":"4d since push","license":"Apache-2.0","repository":"https://github.com/pulumi/agent-skills","install":"npx skills add pulumi/agent-skills","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, filesystem or document access","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":["coding-agents","pulumi","infrastructure-as-code","migration","iac","agent-skills"],"known_risks":["Quality score needs review","Permission surface needs review: secrets or environment access, filesystem or document access","GitHub adoption: 63 GitHub stars","Stars/forks activity: 63 stars, 5 forks; issue activity unavailable in current metadata","Dependency/runtime risk: credential or environment access, network or browser surface","Permission surface: secrets or environment access, filesystem or document access"]},"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":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Dependency or permission surface needs review","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: secrets or environment access, filesystem or document access","GitHub adoption: 63 GitHub stars","Stars/forks activity: 63 stars, 5 forks; issue activity unavailable in current metadata","Dependency/runtime risk: credential or environment access, network or browser surface","Permission surface: secrets or environment access, filesystem or document access"]},"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":76,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"4d since push","risk":"Needs review"},"alternative_skills":[{"slug":"mattpocock-grill-with-docs","name":"Grill With Docs","url":"https://www.openagentskill.com/skills/mattpocock-grill-with-docs","stars":164748,"install_command":"npx skills add mattpocock/skills --skill grill-with-docs","trust_score":89,"audit_score":91},{"slug":"mattpocock-code-review","name":"Code Review","url":"https://www.openagentskill.com/skills/mattpocock-code-review","stars":168580,"install_command":"npx skills add mattpocock/skills --skill code-review","trust_score":94,"audit_score":95},{"slug":"mattpocock-to-spec","name":"To Spec","url":"https://www.openagentskill.com/skills/mattpocock-to-spec","stars":164748,"install_command":"npx skills add mattpocock/skills --skill to-spec","trust_score":90,"audit_score":92},{"slug":"mattpocock-to-tickets","name":"To Tickets","url":"https://www.openagentskill.com/skills/mattpocock-to-tickets","stars":176665,"install_command":"npx skills add mattpocock/skills --skill to-tickets","trust_score":91,"audit_score":93}],"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: Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: secrets or environment access, filesystem or document access"],"agent_contract":{"task_input":"Evaluate Agent Skills 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: 73/100 Strong shortlist","Audit: 81/100 Needs review","Safety: 49/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pulumi-agent-skills (Agent Skills)","install_command":"npx skills add pulumi/agent-skills","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":"pulumi-agent-skills","task":"Evaluate Agent Skills 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/pulumi-agent-skills","api":"https://www.openagentskill.com/api/agent/skills/pulumi-agent-skills","audit":"https://www.openagentskill.com/skills/pulumi-agent-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pulumi-agent-skills&task=Evaluate%20Agent%20Skills%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Agent%20Skills%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Evaluate%20Agent%20Skills%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pulumi-agent-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pulumi-agent-skills"}},"endpoints":{"web":"https://www.openagentskill.com/skills/pulumi-agent-skills","api":"https://www.openagentskill.com/api/agent/skills/pulumi-agent-skills","eval":"https://www.openagentskill.com/api/agent/evals?slug=pulumi-agent-skills","audit":"https://www.openagentskill.com/skills/pulumi-agent-skills/audit","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Agent%20Skills%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":"2026-08-11T04:40:20.978Z"}}