{"eval":{"version":"openagentskill-skill-eval-v1","slug":"seleniumhq-docker-selenium","name":"Docker Selenium","generated_at":"2026-07-03T23:32:43.454Z","task_input":"Evaluate Docker Selenium before installing it in an AI agent workflow","status":"failed","score":84,"risk_level":"high","decision":{"recommendation":"do_not_auto_install","reason":"Permission surface: shell or command execution, filesystem or document access","auto_install_allowed":false,"policy":"block","human_review_required":true},"task_fit":{"score":94,"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","Inspect source files","Explain architecture"],"suited_agents":["Shell","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI","Browser agents","CLI"]},"install":{"command":"npx skills add SeleniumHQ/docker-selenium","ready":true,"policy":"review","safety_label":"Review before install","targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add SeleniumHQ/docker-selenium"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Docker Selenium\" agent skill from https://github.com/SeleniumHQ/docker-selenium. 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: Provides a simple way to run Selenium Grid with Chrome, Firefox, and Edge using Container Platform, making it easier to perform browser automation at scale"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Docker Selenium\" as a Claude Code skill from https://github.com/SeleniumHQ/docker-selenium. 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: Provides a simple way to run Selenium Grid with Chrome, Firefox, and Edge using Container Platform, making it easier to perform browser automation at scale"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Docker Selenium\" from https://github.com/SeleniumHQ/docker-selenium 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: Provides a simple way to run Selenium Grid with Chrome, Firefox, and Edge using Container Platform, making it easier to perform browser automation at scale"}]},"trust":{"score":83,"label":"Strong shortlist","version":"trust-score-v4","evidence":{"stars":"8.6K GitHub stars","repoActivity":"8.6K stars, 2.6K forks","lastPushed":"10d since push","license":"Unknown","repository":"https://github.com/SeleniumHQ/docker-selenium","install":"npx skills add SeleniumHQ/docker-selenium","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"}},"audit":{"score":89,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Dependency or permission surface needs review","Permission surface may require sandboxing","Permission surface needs review: shell or command execution, filesystem or document access","License clarity: Unknown","Dependency/runtime risk: command execution surface, external package install surface","Permission surface: shell or command execution, filesystem or document access"]},"safety_gate":{"score":57,"tier":"experimental","label":"Experimental","auto_install_policy":"review","blocked":false,"permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"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":["High-risk permission hints: Shell or command execution","License is unclear"]},"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":94,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate Docker Selenium before installing it in an AI agent workflow","devops","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 SeleniumHQ/docker-selenium"]},{"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 SeleniumHQ/docker-selenium"]},{"id":"trust_score","label":"Trust score","status":"pass","score":83,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","8.6K GitHub stars","Unknown"]},{"id":"audit_score","label":"Audit score","status":"warn","score":89,"required_for_auto_install":true,"detail":"Needs review","evidence":["License is unclear"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":57,"required_for_auto_install":true,"detail":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","evidence":["Test manually in an isolated workspace and compare against safer alternatives.","High-risk permission hints: Shell or command execution"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":90,"required_for_auto_install":false,"detail":"Metadata includes enough usage and workflow context","evidence":["Strong README/SKILL.md context"]},{"id":"license_clarity","label":"License clarity","status":"warn","score":42,"required_for_auto_install":true,"detail":"Unknown","evidence":["Unknown"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":100,"required_for_auto_install":false,"detail":"10d since push","evidence":["10d since push"]},{"id":"permission_surface","label":"Permission surface","status":"fail","score":48,"required_for_auto_install":true,"detail":"shell or command execution, filesystem or document access","evidence":["Shell or command execution: high","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":["kubernetes-kubernetes","traefik-traefik","etcd-io-etcd","hashicorp-terraform"]}],"blockers":["Permission surface: shell or command execution, filesystem or document access"],"warnings":["Audit score: Needs review","Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","License clarity: Unknown","High-risk permission hints: Shell or command execution","License is unclear","Dependency or permission surface needs review","Permission surface may require sandboxing","Permission surface needs review: shell or command execution, filesystem or document access","Dependency/runtime risk: command execution surface, external package install surface","Permission surface: shell or command execution, filesystem or document access"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No major risk signals from current metadata","High-risk permission hints: Shell or command execution","License is unclear","Dependency or permission surface needs review","Permission surface may require sandboxing","Permission surface needs review: shell or command execution, filesystem or document access"],"alternatives":[{"slug":"kubernetes-kubernetes","name":"Kubernetes","url":"https://www.openagentskill.com/skills/kubernetes-kubernetes","stars":123041,"install_command":"npx skills add kubernetes/kubernetes","trust_score":91,"audit_score":94},{"slug":"traefik-traefik","name":"Traefik","url":"https://www.openagentskill.com/skills/traefik-traefik","stars":63639,"install_command":"npx skills add traefik/traefik","trust_score":91,"audit_score":94},{"slug":"etcd-io-etcd","name":"Etcd","url":"https://www.openagentskill.com/skills/etcd-io-etcd","stars":51836,"install_command":"npx skills add etcd-io/etcd","trust_score":92,"audit_score":94},{"slug":"hashicorp-terraform","name":"Terraform","url":"https://www.openagentskill.com/skills/hashicorp-terraform","stars":48719,"install_command":"npx skills add hashicorp/terraform","trust_score":90,"audit_score":93}],"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"seleniumhq-docker-selenium","name":"Docker Selenium","description":"Provides a simple way to run Selenium Grid with Chrome, Firefox, and Edge using Container Platform, making it easier to perform browser automation at scale","category":"devops","url":"https://www.openagentskill.com/skills/seleniumhq-docker-selenium","repository":"https://github.com/SeleniumHQ/docker-selenium","github_repo":"SeleniumHQ/docker-selenium"},"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","Inspect source files","Explain architecture"],"suited_agents":["Shell","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI","Browser agents","CLI"],"install":{"command":"npx skills add SeleniumHQ/docker-selenium","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add SeleniumHQ/docker-selenium"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Docker Selenium\" agent skill from https://github.com/SeleniumHQ/docker-selenium. 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: Provides a simple way to run Selenium Grid with Chrome, Firefox, and Edge using Container Platform, making it easier to perform browser automation at scale"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Docker Selenium\" as a Claude Code skill from https://github.com/SeleniumHQ/docker-selenium. 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: Provides a simple way to run Selenium Grid with Chrome, Firefox, and Edge using Container Platform, making it easier to perform browser automation at scale"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Docker Selenium\" from https://github.com/SeleniumHQ/docker-selenium 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: Provides a simple way to run Selenium Grid with Chrome, Firefox, and Edge using Container Platform, making it easier to perform browser automation at scale"}],"handoff_url":"https://www.openagentskill.com/api/skills/seleniumhq-docker-selenium/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/seleniumhq-docker-selenium"},"trust":{"score":83,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"8.6K GitHub stars","repoActivity":"8.6K stars, 2.6K forks","lastPushed":"10d since push","license":"Unknown","repository":"https://github.com/SeleniumHQ/docker-selenium","install":"npx skills add SeleniumHQ/docker-selenium","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["devops","kubernetes","containerization","distributed-systems","docker","docker-selenium-grid"],"known_risks":["License is unclear","Permission surface needs review: shell or command execution, filesystem or document access","License clarity: Unknown","Dependency/runtime risk: command execution surface, external package install surface","Permission surface: shell or command execution, filesystem or document access"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":89,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Dependency or permission surface needs review","Permission surface may require sandboxing","Permission surface needs review: shell or command execution, filesystem or document access","License clarity: Unknown","Dependency/runtime risk: command execution surface, external package install surface","Permission surface: shell or command execution, filesystem or document access"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"10d since push","risk":"Needs review"},"alternative_skills":[{"slug":"kubernetes-kubernetes","name":"Kubernetes","url":"https://www.openagentskill.com/skills/kubernetes-kubernetes","stars":123041,"install_command":"npx skills add kubernetes/kubernetes","trust_score":91,"audit_score":94},{"slug":"traefik-traefik","name":"Traefik","url":"https://www.openagentskill.com/skills/traefik-traefik","stars":63639,"install_command":"npx skills add traefik/traefik","trust_score":91,"audit_score":94},{"slug":"etcd-io-etcd","name":"Etcd","url":"https://www.openagentskill.com/skills/etcd-io-etcd","stars":51836,"install_command":"npx skills add etcd-io/etcd","trust_score":92,"audit_score":94},{"slug":"hashicorp-terraform","name":"Terraform","url":"https://www.openagentskill.com/skills/hashicorp-terraform","stars":48719,"install_command":"npx skills add hashicorp/terraform","trust_score":90,"audit_score":93}],"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","High-risk permission hints: Shell or command execution","License is unclear","Dependency or permission surface needs review","Permission surface may require sandboxing","Permission surface needs review: shell or command execution, filesystem or document access"],"agent_contract":{"task_input":"Evaluate Docker Selenium before installing it in an AI agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 83/100 Strong shortlist","Audit: 89/100 Needs review","Safety: 57/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"seleniumhq-docker-selenium (Docker Selenium)","install_command":"npx skills add SeleniumHQ/docker-selenium","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"seleniumhq-docker-selenium","task":"Evaluate Docker Selenium before installing it in an AI agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/seleniumhq-docker-selenium","api":"https://www.openagentskill.com/api/agent/skills/seleniumhq-docker-selenium","audit":"https://www.openagentskill.com/skills/seleniumhq-docker-selenium/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=seleniumhq-docker-selenium&task=Evaluate%20Docker%20Selenium%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Docker%20Selenium%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Evaluate%20Docker%20Selenium%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/seleniumhq-docker-selenium/install","manifest":"https://www.openagentskill.com/api/registry/manifest/seleniumhq-docker-selenium"}},"endpoints":{"web":"https://www.openagentskill.com/skills/seleniumhq-docker-selenium","api":"https://www.openagentskill.com/api/agent/skills/seleniumhq-docker-selenium","eval":"https://www.openagentskill.com/api/agent/evals?slug=seleniumhq-docker-selenium","audit":"https://www.openagentskill.com/skills/seleniumhq-docker-selenium/audit","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Docker%20Selenium%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium"}},"meta":{"endpoint":"/api/agent/evals","mode":"skill_eval","purpose":"Pre-install eval contract for a single skill. Agents should read this before installing a reusable skill.","generated_at":"2026-07-03T23:32:43.454Z"}}