{"task":"Use Claude BugHunter for an agent workflow","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"selected":{"rank":7,"match_score":293.5,"skill":{"slug":"simular-ai-agent-s","name":"Agent S","description":"Agent S: an open agentic framework that uses computers like a human","category":"agent-frameworks","repository":"https://github.com/simular-ai/Agent-S","github_repo":"simular-ai/Agent-S"},"recommendation_reasons":["Matches task terms: use, for, agent","Strong GitHub adoption: 11,843 stars","Install handoff is available","Repository freshness signal is available","Registry match score 294"],"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"12K","tone":"positive"},{"label":"Freshness","value":"1mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"score":100,"tier":"production","label":"Production candidate","summary":"Strong trust signals across adoption, maintenance, install readiness, and review status.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","checks":[{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"Install path","detail":"npx skills add simular-ai/Agent-S"},{"status":"pass","label":"Repository","detail":"https://github.com/simular-ai/Agent-S"},{"status":"pass","label":"License","detail":"Apache-2.0"},{"status":"pass","label":"Maintenance","detail":"1mo since push"},{"status":"pass","label":"AI review","detail":"Approved with no listed issues"},{"status":"pass","label":"Adoption","detail":"12K GitHub stars"},{"status":"pass","label":"Documentation","detail":"Usable description available"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"}],"strengths":["Manually verified listing","AI review approved","Recently maintained repository","Large GitHub adoption signal"],"warnings":[]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety":{"score":91,"level":"safe_to_install","label":"Safe to install with normal review","auto_install_allowed":true,"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":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add simular-ai/Agent-S","value":"Install the \"Agent S\" agent skill from https://github.com/simular-ai/Agent-S. 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: Agent S: an open agentic framework that uses computers like a human","kind":"agent-prompt","steps":["Review Agent S 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 skills add simular-ai/Agent-S","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Agent S\" agent skill from https://github.com/simular-ai/Agent-S. 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: Agent S: an open agentic framework that uses computers like a human","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 \"Agent S\" as a Claude Code skill from https://github.com/simular-ai/Agent-S. 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: Agent S: an open agentic framework that uses computers like a human","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 \"Agent S\" from https://github.com/simular-ai/Agent-S 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: Agent S: an open agentic framework that uses computers like a human","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"sports-analytics","title":"Sports analytics","url":"https://www.openagentskill.com/use-cases/sports-analytics"}],"urls":{"web":"https://www.openagentskill.com/skills/simular-ai-agent-s","api":"https://www.openagentskill.com/api/agent/skills/simular-ai-agent-s","install_api":"https://www.openagentskill.com/api/skills/simular-ai-agent-s/install","audit":"https://www.openagentskill.com/skills/simular-ai-agent-s/audit","badge":"https://www.openagentskill.com/api/badge/simular-ai-agent-s?metric=audit","repository":"https://github.com/simular-ai/Agent-S"}},"alternatives":[{"rank":1,"match_score":309.2,"skill":{"slug":"frankbria-ralph-claude-code","name":"Ralph Claude Code","description":"Autonomous AI development loop for Claude Code with intelligent exit detection","category":"agent-frameworks","repository":"https://github.com/frankbria/ralph-claude-code","github_repo":"frankbria/ralph-claude-code"},"recommendation_reasons":["Matches task terms: use, claude, for, agent","Useful GitHub adoption: 9,319 stars","Install handoff is available","Repository freshness signal is available","Registry match score 309"],"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"9.3K","tone":"positive"},{"label":"Freshness","value":"1d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"score":100,"tier":"production","label":"Production candidate","summary":"Strong trust signals across adoption, maintenance, install readiness, and review status.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","checks":[{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"Install path","detail":"npx skills add frankbria/ralph-claude-code"},{"status":"pass","label":"Repository","detail":"https://github.com/frankbria/ralph-claude-code"},{"status":"pass","label":"License","detail":"MIT"},{"status":"pass","label":"Maintenance","detail":"1d since push"},{"status":"pass","label":"AI review","detail":"Approved with no listed issues"},{"status":"pass","label":"Adoption","detail":"9.3K GitHub stars"},{"status":"pass","label":"Documentation","detail":"Usable description available"},{"status":"pass","label":"OpenAgentSkill usage","detail":"1 views, 0 install copies"}],"strengths":["Manually verified listing","AI review approved","Recently maintained repository","Large GitHub adoption signal"],"warnings":[]},"audit":{"audit_score":97,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety":{"score":69,"level":"review_before_install","label":"Review before install","auto_install_allowed":false,"audit_risk":"safe_to_try","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"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No major risk signals from current metadata"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add frankbria/ralph-claude-code","value":"Install the \"Ralph Claude Code\" agent skill from https://github.com/frankbria/ralph-claude-code. 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: Autonomous AI development loop for Claude Code with intelligent exit detection","kind":"agent-prompt","steps":["Review Ralph Claude Code 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 skills add frankbria/ralph-claude-code","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Ralph Claude Code\" agent skill from https://github.com/frankbria/ralph-claude-code. 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: Autonomous AI development loop for Claude Code with intelligent exit detection","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 \"Ralph Claude Code\" as a Claude Code skill from https://github.com/frankbria/ralph-claude-code. 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: Autonomous AI development loop for Claude Code with intelligent exit detection","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 \"Ralph Claude Code\" from https://github.com/frankbria/ralph-claude-code 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: Autonomous AI development loop for Claude Code with intelligent exit detection","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/frankbria-ralph-claude-code","api":"https://www.openagentskill.com/api/agent/skills/frankbria-ralph-claude-code","install_api":"https://www.openagentskill.com/api/skills/frankbria-ralph-claude-code/install","audit":"https://www.openagentskill.com/skills/frankbria-ralph-claude-code/audit","badge":"https://www.openagentskill.com/api/badge/frankbria-ralph-claude-code?metric=audit","repository":"https://github.com/frankbria/ralph-claude-code"}},{"rank":2,"match_score":305,"skill":{"slug":"agentsmesh-agentsmesh","name":"AgentsMesh","description":"The AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.","category":"agent-frameworks","repository":"https://github.com/AgentsMesh/AgentsMesh","github_repo":"AgentsMesh/AgentsMesh"},"recommendation_reasons":["Matches task terms: use, claude, for, agent","Useful GitHub adoption: 2,212 stars","Install handoff is available","Repository freshness signal is available","Registry match score 305"],"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"2.2K","tone":"positive"},{"label":"Freshness","value":"Today","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"score":100,"tier":"production","label":"Production candidate","summary":"Strong trust signals across adoption, maintenance, install readiness, and review status.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","checks":[{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"Install path","detail":"npx skills add AgentsMesh/AgentsMesh"},{"status":"pass","label":"Repository","detail":"https://github.com/AgentsMesh/AgentsMesh"},{"status":"warn","label":"License","detail":"Unknown"},{"status":"pass","label":"Maintenance","detail":"Pushed today"},{"status":"pass","label":"AI review","detail":"Approved with no listed issues"},{"status":"pass","label":"Adoption","detail":"2.2K GitHub stars"},{"status":"pass","label":"Documentation","detail":"Usable description available"},{"status":"pass","label":"OpenAgentSkill usage","detail":"1 views, 0 install copies"}],"strengths":["Manually verified listing","AI review approved","Recently maintained repository","Meaningful GitHub adoption signal"],"warnings":["License is unclear"]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear"]},"safety":{"score":67,"level":"review_before_install","label":"Review before install","auto_install_allowed":false,"audit_risk":"safe_to_try","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","License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No major risk signals from current metadata"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add AgentsMesh/AgentsMesh","value":"Install the \"AgentsMesh\" agent skill from https://github.com/AgentsMesh/AgentsMesh. 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 AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.","kind":"agent-prompt","steps":["Review AgentsMesh 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 skills add AgentsMesh/AgentsMesh","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"AgentsMesh\" agent skill from https://github.com/AgentsMesh/AgentsMesh. 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 AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.","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 \"AgentsMesh\" as a Claude Code skill from https://github.com/AgentsMesh/AgentsMesh. 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 AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.","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 \"AgentsMesh\" from https://github.com/AgentsMesh/AgentsMesh 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 AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"sports-analytics","title":"Sports analytics","url":"https://www.openagentskill.com/use-cases/sports-analytics"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/agentsmesh-agentsmesh","api":"https://www.openagentskill.com/api/agent/skills/agentsmesh-agentsmesh","install_api":"https://www.openagentskill.com/api/skills/agentsmesh-agentsmesh/install","audit":"https://www.openagentskill.com/skills/agentsmesh-agentsmesh/audit","badge":"https://www.openagentskill.com/api/badge/agentsmesh-agentsmesh?metric=audit","repository":"https://github.com/AgentsMesh/AgentsMesh"}},{"rank":3,"match_score":301.1,"skill":{"slug":"addyosmani-web-quality-skills","name":"Web Quality Skills","description":"Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.","category":"agent-skills","repository":"https://github.com/addyosmani/web-quality-skills","github_repo":"addyosmani/web-quality-skills"},"recommendation_reasons":["Matches task terms: use, claude, for, agent","Useful GitHub adoption: 2,324 stars","Install handoff is available","Repository freshness signal is available","Registry match score 301"],"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"2.3K","tone":"positive"},{"label":"Freshness","value":"Today","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"score":100,"tier":"production","label":"Production candidate","summary":"Strong trust signals across adoption, maintenance, install readiness, and review status.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","checks":[{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"Install path","detail":"npx skills add addyosmani/web-quality-skills"},{"status":"pass","label":"Repository","detail":"https://github.com/addyosmani/web-quality-skills"},{"status":"pass","label":"License","detail":"MIT"},{"status":"pass","label":"Maintenance","detail":"Pushed today"},{"status":"pass","label":"AI review","detail":"Approved with no listed issues"},{"status":"pass","label":"Adoption","detail":"2.3K GitHub stars"},{"status":"pass","label":"Documentation","detail":"Usable description available"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"}],"strengths":["Manually verified listing","AI review approved","Recently maintained repository","Meaningful GitHub adoption signal"],"warnings":[]},"audit":{"audit_score":97,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety":{"score":69,"level":"review_before_install","label":"Review before install","auto_install_allowed":false,"audit_risk":"safe_to_try","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"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add addyosmani/web-quality-skills","value":"Install the \"Web Quality Skills\" agent skill from https://github.com/addyosmani/web-quality-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: Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.","kind":"agent-prompt","steps":["Review Web Quality Skills 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 skills add addyosmani/web-quality-skills","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Web Quality Skills\" agent skill from https://github.com/addyosmani/web-quality-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: Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.","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 \"Web Quality Skills\" as a Claude Code skill from https://github.com/addyosmani/web-quality-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: Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.","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 \"Web Quality Skills\" from https://github.com/addyosmani/web-quality-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: Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/addyosmani-web-quality-skills","api":"https://www.openagentskill.com/api/agent/skills/addyosmani-web-quality-skills","install_api":"https://www.openagentskill.com/api/skills/addyosmani-web-quality-skills/install","audit":"https://www.openagentskill.com/skills/addyosmani-web-quality-skills/audit","badge":"https://www.openagentskill.com/api/badge/addyosmani-web-quality-skills?metric=audit","repository":"https://github.com/addyosmani/web-quality-skills"}},{"rank":4,"match_score":301,"skill":{"slug":"elementalsouls-claude-bughunter","name":"Claude BugHunter","description":"A Claude Code skill bundle for bug hunting and external red-team work — 71 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.","category":"development","repository":"https://github.com/elementalsouls/Claude-BugHunter","github_repo":"elementalsouls/Claude-BugHunter"},"recommendation_reasons":["Matches task terms: use, claude, bughunter, for","Useful GitHub adoption: 2,243 stars","Install handoff is available","Repository freshness signal is available","Registry match score 301"],"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"2.2K","tone":"positive"},{"label":"Freshness","value":"5d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"score":100,"tier":"production","label":"Production candidate","summary":"Strong trust signals across adoption, maintenance, install readiness, and review status.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","checks":[{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"Install path","detail":"npx skills add elementalsouls/Claude-BugHunter"},{"status":"pass","label":"Repository","detail":"https://github.com/elementalsouls/Claude-BugHunter"},{"status":"warn","label":"License","detail":"Unknown"},{"status":"pass","label":"Maintenance","detail":"5d since push"},{"status":"pass","label":"AI review","detail":"Approved with no listed issues"},{"status":"pass","label":"Adoption","detail":"2.2K GitHub stars"},{"status":"pass","label":"Documentation","detail":"Usable description available"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"}],"strengths":["Manually verified listing","AI review approved","Recently maintained repository","Meaningful GitHub adoption signal"],"warnings":["License is unclear"]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear"]},"safety":{"score":79,"level":"review_before_install","label":"Review before install","auto_install_allowed":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":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add elementalsouls/Claude-BugHunter","value":"Install the \"Claude BugHunter\" agent skill from https://github.com/elementalsouls/Claude-BugHunter. 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 Claude Code skill bundle for bug hunting and external red-team work — 71 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.","kind":"agent-prompt","steps":["Review Claude BugHunter 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 skills add elementalsouls/Claude-BugHunter","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Claude BugHunter\" agent skill from https://github.com/elementalsouls/Claude-BugHunter. 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 Claude Code skill bundle for bug hunting and external red-team work — 71 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.","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 \"Claude BugHunter\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter. 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 Claude Code skill bundle for bug hunting and external red-team work — 71 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.","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 \"Claude BugHunter\" from https://github.com/elementalsouls/Claude-BugHunter 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 Claude Code skill bundle for bug hunting and external red-team work — 71 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"sports-analytics","title":"Sports analytics","url":"https://www.openagentskill.com/use-cases/sports-analytics"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/elementalsouls-claude-bughunter","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-claude-bughunter","install_api":"https://www.openagentskill.com/api/skills/elementalsouls-claude-bughunter/install","audit":"https://www.openagentskill.com/skills/elementalsouls-claude-bughunter/audit","badge":"https://www.openagentskill.com/api/badge/elementalsouls-claude-bughunter?metric=audit","repository":"https://github.com/elementalsouls/Claude-BugHunter"}}],"agent_workflow":{"mode":"resolve_review_install","recommended_action":"Install after normal workspace review.","selected_skill":{"slug":"simular-ai-agent-s","name":"Agent S","url":"https://www.openagentskill.com/skills/simular-ai-agent-s","repository":"https://github.com/simular-ai/Agent-S"},"install":{"target":"codex","label":"Codex install prompt","kind":"agent-prompt","command":"npx skills add simular-ai/Agent-S","value":"Install the \"Agent S\" agent skill from https://github.com/simular-ai/Agent-S. 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: Agent S: an open agentic framework that uses computers like a human","api":"https://www.openagentskill.com/api/skills/simular-ai-agent-s/install"},"copy_paste_prompt":"Task: Use Claude BugHunter for an agent workflow\nUse Agent S from https://www.openagentskill.com/skills/simular-ai-agent-s.\nReview the audit first: https://www.openagentskill.com/skills/simular-ai-agent-s/audit\nInstall handoff: https://www.openagentskill.com/api/skills/simular-ai-agent-s/install\nInstall command: npx skills add simular-ai/Agent-S\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%20Claude%20BugHunter%20for%20an%20agent%20workflow&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/simular-ai-agent-s"},{"step":3,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/simular-ai-agent-s/install"},{"step":4,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/simular-ai-agent-s/audit"}],"review_checklist":["Safety score: 91/100 Safe to install with normal review","Audit score: 95/100 Safe to try","Trust score: 100/100 Production candidate","Readiness: 100/100 Production-ready"],"fallback_strategy":[{"slug":"frankbria-ralph-claude-code","name":"Ralph Claude Code","reason":"Matches task terms: use, claude, for, agent","url":"https://www.openagentskill.com/skills/frankbria-ralph-claude-code","install_api":"https://www.openagentskill.com/api/skills/frankbria-ralph-claude-code/install"},{"slug":"agentsmesh-agentsmesh","name":"AgentsMesh","reason":"Matches task terms: use, claude, for, agent","url":"https://www.openagentskill.com/skills/agentsmesh-agentsmesh","install_api":"https://www.openagentskill.com/api/skills/agentsmesh-agentsmesh/install"},{"slug":"addyosmani-web-quality-skills","name":"Web Quality Skills","reason":"Matches task terms: use, claude, for, agent","url":"https://www.openagentskill.com/skills/addyosmani-web-quality-skills","install_api":"https://www.openagentskill.com/api/skills/addyosmani-web-quality-skills/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"}},"policy_decision":{"status":"approved_for_agent_install","summary":"Policy allows an agent to install this skill after normal workspace review."},"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":"1.0","generated_at":"2026-06-14T17:46:28.268Z","total_skills_searched":980,"total_candidates":15}}