{"task":"Use Http Prompt","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"recommendation":{"task":"Use Http Prompt","agent":"codex","best_skill":{"slug":"dair-ai-prompt-engineering-guide","name":"Prompt Engineering Guide","description":"🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide","api_url":"https://www.openagentskill.com/api/agent/skills/dair-ai-prompt-engineering-guide","audit_url":"https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide/audit","repository":"https://github.com/dair-ai/Prompt-Engineering-Guide"},"install":{"command":"npx skills add dair-ai/Prompt-Engineering-Guide","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Prompt Engineering Guide\" agent skill from https://github.com/dair-ai/Prompt-Engineering-Guide. 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: 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.","install_api":"https://www.openagentskill.com/api/skills/dair-ai-prompt-engineering-guide/install","ready":true,"review_required":false,"auto_install_allowed":true,"policy":"allow"},"why_recommended":["Matches task terms: use, prompt","Strong GitHub adoption: 75,575 stars","Quality score 70/100","Install handoff is available","Repository freshness signal is available","Primary pick for Coding agents","94/100 OpenAgentSkill Trust Score v2","94/100 audit score"],"trust_score_v2":{"score":94,"tier":"production","label":"Production candidate","install_policy":"agent_install_candidate","evidence":{"stars":"76K GitHub stars","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/dair-ai/Prompt-Engineering-Guide","install":"npx skills add dair-ai/Prompt-Engineering-Guide","documentation":"Strong README/SKILL.md context"},"agent_compatibility":["MDX","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]}},"risk":{"level":"Safe to try","safety_tier":"Verified","safety":"90/100 Safe to install with normal review","trust":"94/100 Production candidate","notes":[]},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","90/100 agent safety score"]},"supply_asset":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"sports-analytics","title":"Sports analytics"}]},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":96,"lastPushedAt":"2026-03-11T20:09:13+00:00"},"github_quality":{"stars":75575,"starsLabel":"76K","forks":8210,"license":"MIT","qualityScore":100,"trustScore":94,"auditScore":94},"coverage_tags":["Coding","Coding agents","agent-frameworks","agents","ai-agents","agent","chatgpt","deep-learning"]},"alternatives":[{"slug":"piebald-ai-claude-code-system-prompts","name":"Claude Code System Prompts","url":"https://www.openagentskill.com/skills/piebald-ai-claude-code-system-prompts","install_command":"npx skills add Piebald-AI/claude-code-system-prompts","trust_score":95,"audit_score":97,"safety_score":73,"why_consider":"Matches task terms: use, prompt","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"73/100 Review before install","trust":"95/100 Production candidate","notes":["High-risk permission hints: Shell or command execution"]}},{"slug":"browser-use-browser-use","name":"Browser Use","url":"https://www.openagentskill.com/skills/browser-use-browser-use","install_command":"npx skills add browser-use/browser-use","trust_score":94,"audit_score":97,"safety_score":89,"why_consider":"Matches task terms: use","risk":{"level":"Safe to try","safety_tier":"Verified","safety":"89/100 Safe to install with normal review","trust":"94/100 Production candidate","notes":[]}},{"slug":"trycua-cua","name":"Cua","url":"https://www.openagentskill.com/skills/trycua-cua","install_command":"npx skills add trycua/cua","trust_score":98,"audit_score":98,"safety_score":90,"why_consider":"Matches task terms: use","risk":{"level":"Safe to try","safety_tier":"Verified","safety":"90/100 Safe to install with normal review","trust":"98/100 Production candidate","notes":[]}},{"slug":"web-infra-dev-midscene","name":"Midscene","url":"https://www.openagentskill.com/skills/web-infra-dev-midscene","install_command":"npx skills add web-infra-dev/midscene","trust_score":94,"audit_score":97,"safety_score":85,"why_consider":"Matches task terms: use","risk":{"level":"Safe to try","safety_tier":"Verified","safety":"85/100 Safe to install with normal review","trust":"94/100 Production candidate","notes":[]}}],"agent_instruction":"Use Prompt Engineering Guide for: Use Http Prompt\nReview audit: https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide/audit\nInstall in a sandbox first with: npx skills add dair-ai/Prompt-Engineering-Guide\nIf the audit or policy warnings are unacceptable, choose one of the alternatives."},"selected":{"rank":1,"match_score":113.6,"skill":{"slug":"dair-ai-prompt-engineering-guide","name":"Prompt Engineering Guide","description":"🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.","category":"agent-frameworks","repository":"https://github.com/dair-ai/Prompt-Engineering-Guide","github_repo":"dair-ai/Prompt-Engineering-Guide"},"recommendation_reasons":["Matches task terms: use, prompt","Strong GitHub adoption: 75,575 stars","Quality score 70/100","Install handoff is available","Repository freshness signal is available"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"sports-analytics","title":"Sports analytics"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add dair-ai/Prompt-Engineering-Guide","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":75575,"starsLabel":"76K","forks":8210,"license":"MIT","qualityScore":100,"trustScore":94,"auditScore":94},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":96,"lastPushedAt":"2026-03-11T20:09:13+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","Coding agents","agent-frameworks","agents","ai-agents","agent","chatgpt","deep-learning"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"76K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v2","score":94,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.16,"status":"pass","detail":"76K GitHub stars"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.18,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.1,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.16,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency risk","score":90,"weight":0.14,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.14,"status":"pass","detail":"npx skills add dair-ai/Prompt-Engineering-Guide"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.06,"status":"pass","detail":"https://github.com/dair-ai/Prompt-Engineering-Guide"},{"id":"review_status","label":"Review status","score":88,"weight":0.06,"status":"pass","detail":"AI review data available"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"76K GitHub stars"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add dair-ai/Prompt-Engineering-Guide"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/dair-ai/Prompt-Engineering-Guide"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"5 views, 1 install copies"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","OpenAgentSkill usage activity detected"],"warnings":[],"evidence":{"stars":"76K GitHub stars","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/dair-ai/Prompt-Engineering-Guide","install":"npx skills add dair-ai/Prompt-Engineering-Guide","documentation":"Strong README/SKILL.md context"},"installReadiness":{"ready":true,"command":"npx skills add dair-ai/Prompt-Engineering-Guide","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","3mo since push"]},"agentCompatibility":["MDX","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]}},"audit":{"audit_score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety":{"score":90,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","90/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","90/100 agent safety score"]},"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 dair-ai/Prompt-Engineering-Guide","value":"Install the \"Prompt Engineering Guide\" agent skill from https://github.com/dair-ai/Prompt-Engineering-Guide. 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: 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.","kind":"agent-prompt","steps":["Review Prompt Engineering Guide 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 dair-ai/Prompt-Engineering-Guide","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 \"Prompt Engineering Guide\" agent skill from https://github.com/dair-ai/Prompt-Engineering-Guide. 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: 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.","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 \"Prompt Engineering Guide\" as a Claude Code skill from https://github.com/dair-ai/Prompt-Engineering-Guide. 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: 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.","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 \"Prompt Engineering Guide\" from https://github.com/dair-ai/Prompt-Engineering-Guide 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: 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.","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/dair-ai-prompt-engineering-guide","api":"https://www.openagentskill.com/api/agent/skills/dair-ai-prompt-engineering-guide","install_api":"https://www.openagentskill.com/api/skills/dair-ai-prompt-engineering-guide/install","audit":"https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide/audit","badge":"https://www.openagentskill.com/api/badge/dair-ai-prompt-engineering-guide?metric=audit","repository":"https://github.com/dair-ai/Prompt-Engineering-Guide"}},"alternatives":[{"rank":2,"match_score":112,"skill":{"slug":"piebald-ai-claude-code-system-prompts","name":"Claude Code System Prompts","description":"All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact,  statusline, magic docs, WebFetch, Bash cmd, security review, agent creation).  Updated for each Claude Code version.","category":"development","repository":"https://github.com/Piebald-AI/claude-code-system-prompts","github_repo":"Piebald-AI/claude-code-system-prompts"},"recommendation_reasons":["Matches task terms: use, prompt","Strong GitHub adoption: 10,835 stars","Quality score 71/100","Install handoff is available","Repository freshness signal is available"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","JavaScript"],"install":{"ready":true,"command":"npx skills add Piebald-AI/claude-code-system-prompts","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":10835,"starsLabel":"11K","forks":1890,"license":"MIT","qualityScore":100,"trustScore":95,"auditScore":97},"maintenance":{"status":"fresh","label":"9d since push","daysSincePush":9,"lastPushedAt":"2026-06-06T23:42:40+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","Coding agents","development","claude-code","developer-tools","claude-code-system-prompts","system-prompts","javascript"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"11K","tone":"positive"},{"label":"Freshness","value":"9d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v2","score":95,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.16,"status":"pass","detail":"11K GitHub stars"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.18,"status":"pass","detail":"9d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.1,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.16,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency risk","score":72,"weight":0.14,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.14,"status":"pass","detail":"npx skills add Piebald-AI/claude-code-system-prompts"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.06,"status":"pass","detail":"https://github.com/Piebald-AI/claude-code-system-prompts"},{"id":"review_status","label":"Review status","score":88,"weight":0.06,"status":"pass","detail":"AI review data available"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"11K GitHub stars"},{"status":"pass","label":"Recent maintenance","detail":"9d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add Piebald-AI/claude-code-system-prompts"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Piebald-AI/claude-code-system-prompts"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"6 views, 0 install copies"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal"],"warnings":[],"evidence":{"stars":"11K GitHub stars","lastPushed":"9d since push","license":"MIT","repository":"https://github.com/Piebald-AI/claude-code-system-prompts","install":"npx skills add Piebald-AI/claude-code-system-prompts","documentation":"Strong README/SKILL.md context"},"installReadiness":{"ready":true,"command":"npx skills add Piebald-AI/claude-code-system-prompts","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","9d since push"]},"agentCompatibility":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]}},"audit":{"audit_score":97,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety":{"score":73,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","73/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":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"}],"policy_warnings":["High-risk permission hints: Shell or command execution"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["High-risk permission hints: Shell or command execution","73/100 agent safety score"]},"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 Piebald-AI/claude-code-system-prompts","value":"Install the \"Claude Code System Prompts\" agent skill from https://github.com/Piebald-AI/claude-code-system-prompts. 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: All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.","kind":"agent-prompt","steps":["Review Claude Code System Prompts 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 Piebald-AI/claude-code-system-prompts","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 Code System Prompts\" agent skill from https://github.com/Piebald-AI/claude-code-system-prompts. 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: All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.","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 Code System Prompts\" as a Claude Code skill from https://github.com/Piebald-AI/claude-code-system-prompts. 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: All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.","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 Code System Prompts\" from https://github.com/Piebald-AI/claude-code-system-prompts 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: All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.","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":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/piebald-ai-claude-code-system-prompts","api":"https://www.openagentskill.com/api/agent/skills/piebald-ai-claude-code-system-prompts","install_api":"https://www.openagentskill.com/api/skills/piebald-ai-claude-code-system-prompts/install","audit":"https://www.openagentskill.com/skills/piebald-ai-claude-code-system-prompts/audit","badge":"https://www.openagentskill.com/api/badge/piebald-ai-claude-code-system-prompts?metric=audit","repository":"https://github.com/Piebald-AI/claude-code-system-prompts"}},{"rank":3,"match_score":107.5,"skill":{"slug":"browser-use-browser-use","name":"Browser Use","description":"🌐 Make websites accessible for AI agents. Automate tasks online with ease.","category":"agent-frameworks","repository":"https://github.com/browser-use/browser-use","github_repo":"browser-use/browser-use"},"recommendation_reasons":["Matches task terms: use","Strong GitHub adoption: 98,702 stars","Quality score 78/100","Install handoff is available","Repository freshness signal is available"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"web-scraping","title":"Web scraping"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Claude Code","Browser agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add browser-use/browser-use","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":98702,"starsLabel":"99K","forks":11011,"license":"MIT","qualityScore":100,"trustScore":94,"auditScore":97},"maintenance":{"status":"fresh","label":"2d since push","daysSincePush":2,"lastPushedAt":"2026-06-13T21:08:02+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","Coding agents","agent-frameworks","agents","ai-agents","ai-tools","browser-automation","browser-use"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"99K","tone":"positive"},{"label":"Freshness","value":"2d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v2","score":94,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.16,"status":"pass","detail":"99K GitHub stars"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.18,"status":"pass","detail":"2d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.1,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":74,"weight":0.16,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency risk","score":82,"weight":0.14,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.14,"status":"pass","detail":"npx skills add browser-use/browser-use"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.06,"status":"pass","detail":"https://github.com/browser-use/browser-use"},{"id":"review_status","label":"Review status","score":88,"weight":0.06,"status":"pass","detail":"AI review data available"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"99K GitHub stars"},{"status":"pass","label":"Recent maintenance","detail":"2d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add browser-use/browser-use"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/browser-use/browser-use"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"9 views, 6 install copies"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","OpenAgentSkill usage activity detected"],"warnings":[],"evidence":{"stars":"99K GitHub stars","lastPushed":"2d since push","license":"MIT","repository":"https://github.com/browser-use/browser-use","install":"npx skills add browser-use/browser-use","documentation":"Usable metadata, review docs"},"installReadiness":{"ready":true,"command":"npx skills add browser-use/browser-use","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","2d since push"]},"agentCompatibility":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]}},"audit":{"audit_score":97,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety":{"score":89,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","89/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"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"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","89/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","best_for":["Browser automation workflows","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 Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add browser-use/browser-use","value":"Install the \"Browser Use\" agent skill from https://github.com/browser-use/browser-use. 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: 🌐 Make websites accessible for AI agents. Automate tasks online with ease.","kind":"agent-prompt","steps":["Review Browser Use 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 browser-use/browser-use","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 \"Browser Use\" agent skill from https://github.com/browser-use/browser-use. 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: 🌐 Make websites accessible for AI agents. Automate tasks online with ease.","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 \"Browser Use\" as a Claude Code skill from https://github.com/browser-use/browser-use. 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: 🌐 Make websites accessible for AI agents. Automate tasks online with ease.","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 \"Browser Use\" from https://github.com/browser-use/browser-use 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: 🌐 Make websites accessible for AI agents. Automate tasks online with ease.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"urls":{"web":"https://www.openagentskill.com/skills/browser-use-browser-use","api":"https://www.openagentskill.com/api/agent/skills/browser-use-browser-use","install_api":"https://www.openagentskill.com/api/skills/browser-use-browser-use/install","audit":"https://www.openagentskill.com/skills/browser-use-browser-use/audit","badge":"https://www.openagentskill.com/api/badge/browser-use-browser-use?metric=audit","repository":"https://github.com/browser-use/browser-use"}},{"rank":4,"match_score":97.5,"skill":{"slug":"trycua-cua","name":"Cua","description":"Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).","category":"automation","repository":"https://github.com/trycua/cua","github_repo":"trycua/cua"},"recommendation_reasons":["Matches task terms: use","Strong GitHub adoption: 17,942 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"local-desktop","title":"Local desktop"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","HTML"],"install":{"ready":true,"command":"npx skills add trycua/cua","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":17942,"starsLabel":"18K","forks":1161,"license":"MIT","qualityScore":100,"trustScore":98,"auditScore":98},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-06-13T03:10:17+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","Coding agents","automation","computer-use","desktop-agent","agent","ai-agent","apple"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"18K","tone":"positive"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v2","score":98,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.16,"status":"pass","detail":"18K GitHub stars"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.18,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.1,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.16,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency risk","score":90,"weight":0.14,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.14,"status":"pass","detail":"npx skills add trycua/cua"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.06,"status":"pass","detail":"https://github.com/trycua/cua"},{"id":"review_status","label":"Review status","score":88,"weight":0.06,"status":"pass","detail":"AI review data available"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"18K GitHub stars"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add trycua/cua"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/trycua/cua"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"3 views, 0 install copies"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal"],"warnings":[],"evidence":{"stars":"18K GitHub stars","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/trycua/cua","install":"npx skills add trycua/cua","documentation":"Strong README/SKILL.md context"},"installReadiness":{"ready":true,"command":"npx skills add trycua/cua","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","3d since push"]},"agentCompatibility":["HTML","Computer Use","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]}},"audit":{"audit_score":98,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety":{"score":90,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","90/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","90/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Local desktop","role":"Primary pick","best_for":["Local desktop 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 Local desktop 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 trycua/cua","value":"Install the \"Cua\" agent skill from https://github.com/trycua/cua. 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: Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).","kind":"agent-prompt","steps":["Review Cua 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 trycua/cua","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 \"Cua\" agent skill from https://github.com/trycua/cua. 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: Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).","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 \"Cua\" as a Claude Code skill from https://github.com/trycua/cua. 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: Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).","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 \"Cua\" from https://github.com/trycua/cua 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: Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"use_cases":[{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"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"}],"urls":{"web":"https://www.openagentskill.com/skills/trycua-cua","api":"https://www.openagentskill.com/api/agent/skills/trycua-cua","install_api":"https://www.openagentskill.com/api/skills/trycua-cua/install","audit":"https://www.openagentskill.com/skills/trycua-cua/audit","badge":"https://www.openagentskill.com/api/badge/trycua-cua?metric=audit","repository":"https://github.com/trycua/cua"}},{"rank":5,"match_score":96.7,"skill":{"slug":"web-infra-dev-midscene","name":"Midscene","description":"AI-powered, vision-driven UI automation for every platform.","category":"automation","repository":"https://github.com/web-infra-dev/midscene","github_repo":"web-infra-dev/midscene"},"recommendation_reasons":["Matches task terms: use","Strong GitHub adoption: 13,695 stars","Quality score 72/100","Install handoff is available","Repository freshness signal is available"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Claude Code","OpenAI Agents","Browser agents","CLI","Codex"],"install":{"ready":true,"command":"npx skills add web-infra-dev/midscene","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":13695,"starsLabel":"14K","forks":1038,"license":"MIT","qualityScore":100,"trustScore":94,"auditScore":97},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-06-13T03:45:46+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","Coding agents","automation","computer-use","desktop-agent","ai","ai-test","browser-use"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"14K","tone":"positive"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v2","score":94,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.16,"status":"pass","detail":"14K GitHub stars"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.18,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.1,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":74,"weight":0.16,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency risk","score":82,"weight":0.14,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.14,"status":"pass","detail":"npx skills add web-infra-dev/midscene"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.06,"status":"pass","detail":"https://github.com/web-infra-dev/midscene"},{"id":"review_status","label":"Review status","score":88,"weight":0.06,"status":"pass","detail":"AI review data available"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"14K GitHub stars"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add web-infra-dev/midscene"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/web-infra-dev/midscene"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal"],"warnings":[],"evidence":{"stars":"14K GitHub stars","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/web-infra-dev/midscene","install":"npx skills add web-infra-dev/midscene","documentation":"Usable metadata, review docs"},"installReadiness":{"ready":true,"command":"npx skills add web-infra-dev/midscene","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","3d since push"]},"agentCompatibility":["TypeScript","Computer Use","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]}},"audit":{"audit_score":97,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety":{"score":85,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","85/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"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"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","85/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","best_for":["Browser automation workflows","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 Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add web-infra-dev/midscene","value":"Install the \"Midscene\" agent skill from https://github.com/web-infra-dev/midscene. 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: AI-powered, vision-driven UI automation for every platform.","kind":"agent-prompt","steps":["Review Midscene 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 web-infra-dev/midscene","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 \"Midscene\" agent skill from https://github.com/web-infra-dev/midscene. 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: AI-powered, vision-driven UI automation for every platform.","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 \"Midscene\" as a Claude Code skill from https://github.com/web-infra-dev/midscene. 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: AI-powered, vision-driven UI automation for every platform.","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 \"Midscene\" from https://github.com/web-infra-dev/midscene 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: AI-powered, vision-driven UI automation for every platform.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"urls":{"web":"https://www.openagentskill.com/skills/web-infra-dev-midscene","api":"https://www.openagentskill.com/api/agent/skills/web-infra-dev-midscene","install_api":"https://www.openagentskill.com/api/skills/web-infra-dev-midscene/install","audit":"https://www.openagentskill.com/skills/web-infra-dev-midscene/audit","badge":"https://www.openagentskill.com/api/badge/web-infra-dev-midscene?metric=audit","repository":"https://github.com/web-infra-dev/midscene"}}],"blocked_candidates":[],"agent_workflow":{"mode":"resolve_review_install","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","selected_skill":{"slug":"dair-ai-prompt-engineering-guide","name":"Prompt Engineering Guide","url":"https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide","repository":"https://github.com/dair-ai/Prompt-Engineering-Guide"},"install":{"target":"codex","label":"Codex install prompt","kind":"agent-prompt","command":"npx skills add dair-ai/Prompt-Engineering-Guide","value":"Install the \"Prompt Engineering Guide\" agent skill from https://github.com/dair-ai/Prompt-Engineering-Guide. 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: 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.","api":"https://www.openagentskill.com/api/skills/dair-ai-prompt-engineering-guide/install"},"copy_paste_prompt":"Task: Use Http Prompt\nUse Prompt Engineering Guide from https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide.\nReview the audit first: https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide/audit\nInstall handoff: https://www.openagentskill.com/api/skills/dair-ai-prompt-engineering-guide/install\nInstall command: npx skills add dair-ai/Prompt-Engineering-Guide\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%20Http%20Prompt&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/dair-ai-prompt-engineering-guide"},{"step":3,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/dair-ai-prompt-engineering-guide/install"},{"step":4,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide/audit"}],"review_checklist":["Safety tier: Verified","Safety score: 90/100 Safe to install with normal review","Audit score: 94/100 Safe to try","Trust score: 94/100 Production candidate","Readiness: 100/100 Production-ready"],"fallback_strategy":[{"slug":"piebald-ai-claude-code-system-prompts","name":"Claude Code System Prompts","reason":"Matches task terms: use, prompt","url":"https://www.openagentskill.com/skills/piebald-ai-claude-code-system-prompts","install_api":"https://www.openagentskill.com/api/skills/piebald-ai-claude-code-system-prompts/install"},{"slug":"browser-use-browser-use","name":"Browser Use","reason":"Matches task terms: use","url":"https://www.openagentskill.com/skills/browser-use-browser-use","install_api":"https://www.openagentskill.com/api/skills/browser-use-browser-use/install"},{"slug":"trycua-cua","name":"Cua","reason":"Matches task terms: use","url":"https://www.openagentskill.com/skills/trycua-cua","install_api":"https://www.openagentskill.com/api/skills/trycua-cua/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":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"agent_decision":{"input_task":"Use Http Prompt","recommended_skill":{"slug":"dair-ai-prompt-engineering-guide","name":"Prompt Engineering Guide","url":"https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide","audit_url":"https://www.openagentskill.com/skills/dair-ai-prompt-engineering-guide/audit","repository":"https://github.com/dair-ai/Prompt-Engineering-Guide","safety_tier":"Verified","auto_install_policy":"allow"},"alternative_skills":[{"slug":"piebald-ai-claude-code-system-prompts","name":"Claude Code System Prompts","url":"https://www.openagentskill.com/skills/piebald-ai-claude-code-system-prompts","install_command":"npx skills add Piebald-AI/claude-code-system-prompts","why_consider":"Matches task terms: use, prompt","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"73/100 Review before install","trust":"95/100 Production candidate","notes":["High-risk permission hints: Shell or command execution"]}},{"slug":"browser-use-browser-use","name":"Browser Use","url":"https://www.openagentskill.com/skills/browser-use-browser-use","install_command":"npx skills add browser-use/browser-use","why_consider":"Matches task terms: use","risk":{"level":"Safe to try","safety_tier":"Verified","safety":"89/100 Safe to install with normal review","trust":"94/100 Production candidate","notes":[]}},{"slug":"trycua-cua","name":"Cua","url":"https://www.openagentskill.com/skills/trycua-cua","install_command":"npx skills add trycua/cua","why_consider":"Matches task terms: use","risk":{"level":"Safe to try","safety_tier":"Verified","safety":"90/100 Safe to install with normal review","trust":"98/100 Production candidate","notes":[]}}],"install_command":"npx skills add dair-ai/Prompt-Engineering-Guide","install_target":"Codex install prompt","why_recommended":["Matches task terms: use, prompt","Strong GitHub adoption: 75,575 stars","Quality score 70/100","Install handoff is available","Repository freshness signal is available","Primary pick for Coding agents"],"risk_summary":{"level":"Safe to try","safety_tier":"Verified","safety":"90/100 Safe to install with normal review","trust":"94/100 Production candidate","notes":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"agent_next_steps":["Read the audit URL before installing.","Install in a sandbox or low-risk workspace first.","Use install command: npx skills add dair-ai/Prompt-Engineering-Guide","After installation, run one narrow task and report output, warnings, and files touched."]},"benchmark":{"endpoint":"https://www.openagentskill.com/api/agent/evals","note":"Use the evals endpoint to regression-test recommendation quality before changing ranking logic."},"meta":{"endpoint":"/api/agent/resolve","api_version":"2.0","generated_at":"2026-06-16T13:35:03.484Z","total_skills_searched":735,"total_candidates":15,"candidate_pool":{"sort":"quality","size":735,"note":"Resolver searches the highest-quality candidate pool for low-latency agent use. Browse /skills for the full public index."},"contract":{"best_skill":"recommendation.best_skill","install":"recommendation.install","why":"recommendation.why_recommended","risk":"recommendation.risk","alternatives":"recommendation.alternatives"}}}