{"eval":{"version":"openagentskill-skill-eval-v1","slug":"browser-use","name":"Browser Use","generated_at":"2026-06-20T17:47:59.562Z","task_input":"Evaluate Browser Use before installing it in an AI agent workflow","status":"review","score":88,"risk_level":"medium","decision":{"recommendation":"manual_review","reason":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_allowed":false,"policy":"review","human_review_required":true},"task_fit":{"score":70,"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Crawl target URLs","Extract tables and metadata"],"suited_agents":["Claude","GPT-4","LangChain","OpenClaw","Codex","Claude Code","OpenAI Agents","Browser agents"]},"install":{"command":"npx skills add browser-use/browser-use","ready":true,"policy":"review","safety_label":"Review before install","targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add browser-use/browser-use"},{"id":"codex","label":"Codex","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 AI agents interact with websites using natural language"},{"id":"claude-code","label":"Claude Code","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 AI agents interact with websites using natural language"},{"id":"cursor","label":"Cursor","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 AI agents interact with websites using natural language"}]},"trust":{"score":92,"label":"Production candidate","version":"trust-score-v3","evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 11K forks","lastPushed":"18d since push","license":"MIT","repository":"https://github.com/browser-use/browser-use","install":"npx skills add browser-use/browser-use","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata"}},"audit":{"score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"score":78,"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","blocked":false,"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":["Documentation summary is thin"]},"checks":[{"id":"task_fit","label":"Task fit","status":"warn","score":70,"required_for_auto_install":true,"detail":"Task fit is weak; compare alternatives before selecting.","evidence":["Evaluate Browser Use before installing it in an AI agent workflow","web-automation","Browser automation workflows; Claude Code teams; teams that value GitHub adoption signals"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add browser-use/browser-use"]},{"id":"install_safety","label":"Install command safety","status":"pass","score":92,"required_for_auto_install":true,"detail":"standard package or runtime install path","evidence":["npx skills add browser-use/browser-use"]},{"id":"trust_score","label":"Trust score","status":"pass","score":92,"required_for_auto_install":true,"detail":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","evidence":["Production candidate","97K GitHub stars","MIT"]},{"id":"audit_score","label":"Audit score","status":"pass","score":94,"required_for_auto_install":true,"detail":"Safe to try","evidence":["Documentation summary is thin"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":78,"required_for_auto_install":true,"detail":"Good audit and safety signals with no high-risk permission hints in public metadata.","evidence":["Review the audit page, then allow agent install in a sandboxed workflow.","Safe-to-try audit"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"fail","score":50,"required_for_auto_install":false,"detail":"Public metadata needs stronger README/SKILL.md context","evidence":["Thin public metadata"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"MIT","evidence":["MIT"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":100,"required_for_auto_install":false,"detail":"18d since push","evidence":["18d since push"]},{"id":"permission_surface","label":"Permission surface","status":"pass","score":86,"required_for_auto_install":true,"detail":"network or browser access","evidence":["Browser automation: medium","Network access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"pass","score":82,"required_for_auto_install":false,"detail":"Alternative skills are available for comparison.","evidence":["crawl4ai","scrapy-scrapy","d4vinci-scrapling","naibowang-easyspider"]}],"blockers":[],"warnings":["Task fit: Task fit is weak; compare alternatives before selecting.","Agent safety gate: Good audit and safety signals with no high-risk permission hints in public metadata.","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No major risk signals from current metadata","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"alternatives":[{"slug":"crawl4ai","name":"Crawl4AI","url":"https://www.openagentskill.com/skills/crawl4ai","stars":68947,"install_command":"npx skills add unclecode/crawl4ai","trust_score":97,"audit_score":96},{"slug":"scrapy-scrapy","name":"Scrapy","url":"https://www.openagentskill.com/skills/scrapy-scrapy","stars":62204,"install_command":"npx skills add scrapy/scrapy","trust_score":96,"audit_score":96},{"slug":"d4vinci-scrapling","name":"Scrapling","url":"https://www.openagentskill.com/skills/d4vinci-scrapling","stars":54175,"install_command":"npx skills add D4Vinci/Scrapling","trust_score":86,"audit_score":89},{"slug":"naibowang-easyspider","name":"EasySpider","url":"https://www.openagentskill.com/skills/naibowang-easyspider","stars":44121,"install_command":"npx skills add NaiboWang/EasySpider","trust_score":99,"audit_score":97}],"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"browser-use","name":"Browser Use","description":"Make AI agents interact with websites using natural language","category":"web-automation","url":"https://www.openagentskill.com/skills/browser-use","repository":"https://github.com/browser-use/browser-use","github_repo":"browser-use/browser-use"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Crawl target URLs","Extract tables and metadata"],"suited_agents":["Claude","GPT-4","LangChain","OpenClaw","Codex","Claude Code","OpenAI Agents","Browser agents"],"install":{"command":"npx skills add browser-use/browser-use","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add browser-use/browser-use"},{"id":"codex","label":"Codex","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 AI agents interact with websites using natural language"},{"id":"claude-code","label":"Claude Code","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 AI agents interact with websites using natural language"},{"id":"cursor","label":"Cursor","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 AI agents interact with websites using natural language"}],"handoff_url":"https://www.openagentskill.com/api/skills/browser-use/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/browser-use"},"trust":{"score":92,"label":"Production candidate","version":"trust-score-v3","install_policy":"agent_install_candidate","evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 11K forks","lastPushed":"18d since push","license":"MIT","repository":"https://github.com/browser-use/browser-use","install":"npx skills add browser-use/browser-use","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata"}},"audit":{"score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Testing and QA","maintenance":"18d since push","risk":"Safe to try"},"alternative_skills":[{"slug":"crawl4ai","name":"Crawl4AI","url":"https://www.openagentskill.com/skills/crawl4ai","stars":68947,"install_command":"npx skills add unclecode/crawl4ai","trust_score":97,"audit_score":96},{"slug":"scrapy-scrapy","name":"Scrapy","url":"https://www.openagentskill.com/skills/scrapy-scrapy","stars":62204,"install_command":"npx skills add scrapy/scrapy","trust_score":96,"audit_score":96},{"slug":"d4vinci-scrapling","name":"Scrapling","url":"https://www.openagentskill.com/skills/d4vinci-scrapling","stars":54175,"install_command":"npx skills add D4Vinci/Scrapling","trust_score":86,"audit_score":89},{"slug":"naibowang-easyspider","name":"EasySpider","url":"https://www.openagentskill.com/skills/naibowang-easyspider","stars":44121,"install_command":"npx skills add NaiboWang/EasySpider","trust_score":99,"audit_score":97}],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No major risk signals from current metadata","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Evaluate Browser Use before installing it in an AI agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 92/100 Production candidate","Audit: 94/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"browser-use (Browser Use)","install_command":"npx skills add browser-use/browser-use","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"endpoints":{"web":"https://www.openagentskill.com/skills/browser-use","api":"https://www.openagentskill.com/api/agent/skills/browser-use","audit":"https://www.openagentskill.com/skills/browser-use/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=browser-use&task=Evaluate%20Browser%20Use%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Browser%20Use%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium","install":"https://www.openagentskill.com/api/skills/browser-use/install","manifest":"https://www.openagentskill.com/api/registry/manifest/browser-use"}},"endpoints":{"web":"https://www.openagentskill.com/skills/browser-use","api":"https://www.openagentskill.com/api/agent/skills/browser-use","eval":"https://www.openagentskill.com/api/agent/evals?slug=browser-use","audit":"https://www.openagentskill.com/skills/browser-use/audit","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Browser%20Use%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium"}},"meta":{"endpoint":"/api/agent/evals","mode":"skill_eval","purpose":"Pre-install eval contract for a single skill. Agents should read this before installing a reusable skill.","generated_at":"2026-06-20T17:47:59.562Z"}}