{"eval":{"version":"openagentskill-skill-eval-v1","slug":"databrickslabs-dbx","name":"Dbx","generated_at":"2026-07-03T21:37:01.590Z","task_input":"Evaluate Dbx before installing it in an AI agent workflow","status":"failed","score":70,"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":["GitHub automation workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","MLOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"]},"install":{"command":"npx skills add databrickslabs/dbx","ready":true,"policy":"review","safety_label":"Avoid automatic install","targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add databrickslabs/dbx"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Dbx\" agent skill from https://github.com/databrickslabs/dbx. 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: 🧱 Databricks CLI eXtensions - aka dbx is a CLI tool for development and advanced Databricks workflows management."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Dbx\" as a Claude Code skill from https://github.com/databrickslabs/dbx. 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: 🧱 Databricks CLI eXtensions - aka dbx is a CLI tool for development and advanced Databricks workflows management."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Dbx\" from https://github.com/databrickslabs/dbx 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: 🧱 Databricks CLI eXtensions - aka dbx is a CLI tool for development and advanced Databricks workflows management."}]},"trust":{"score":71,"label":"Manual review","version":"trust-score-v4","evidence":{"stars":"462 GitHub stars","repoActivity":"462 stars, 128 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/databrickslabs/dbx","install":"npx skills add databrickslabs/dbx","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":75,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","License clarity: Unknown","Permission surface: shell or command execution, filesystem or document access"]},"safety_gate":{"score":47,"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":"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 Dbx before installing it in an AI agent workflow","ml-automation","GitHub automation workflows; Claude Code teams; builders willing to evaluate younger projects"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add databrickslabs/dbx"]},{"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 databrickslabs/dbx"]},{"id":"trust_score","label":"Trust score","status":"warn","score":71,"required_for_auto_install":true,"detail":"Potentially useful, but at least one trust signal needs human inspection.","evidence":["Manual review","462 GitHub stars","Unknown"]},{"id":"audit_score","label":"Audit score","status":"warn","score":75,"required_for_auto_install":true,"detail":"Needs review","evidence":["License is unclear"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":47,"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":"warn","score":76,"required_for_auto_install":false,"detail":"3mo since push","evidence":["3mo 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","Network access: medium","Filesystem access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"pass","score":82,"required_for_auto_install":false,"detail":"Alternative skills are available for comparison.","evidence":["tensorflow-tensorflow","huggingface-transformers","pytorch-pytorch","rasbt-llms-from-scratch"]}],"blockers":["Permission surface: shell or command execution, filesystem or document access"],"warnings":["Trust score: Potentially useful, but at least one trust signal needs human inspection.","Audit score: Needs review","Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","License clarity: Unknown","Recent maintenance: 3mo since push","High-risk permission hints: Shell or command execution","License is unclear","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","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","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access"],"alternatives":[{"slug":"tensorflow-tensorflow","name":"Tensorflow","url":"https://www.openagentskill.com/skills/tensorflow-tensorflow","stars":195681,"install_command":"npx skills add tensorflow/tensorflow","trust_score":91,"audit_score":94},{"slug":"huggingface-transformers","name":"Transformers","url":"https://www.openagentskill.com/skills/huggingface-transformers","stars":161622,"install_command":"npx skills add huggingface/transformers","trust_score":94,"audit_score":95},{"slug":"pytorch-pytorch","name":"Pytorch","url":"https://www.openagentskill.com/skills/pytorch-pytorch","stars":100810,"install_command":"npx skills add pytorch/pytorch","trust_score":88,"audit_score":92},{"slug":"rasbt-llms-from-scratch","name":"LLMs From Scratch","url":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","stars":97256,"install_command":"npx skills add rasbt/LLMs-from-scratch","trust_score":87,"audit_score":90}],"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"databrickslabs-dbx","name":"Dbx","description":"🧱 Databricks CLI eXtensions - aka dbx is a CLI tool for development and advanced Databricks workflows management.","category":"ml-automation","url":"https://www.openagentskill.com/skills/databrickslabs-dbx","repository":"https://github.com/databrickslabs/dbx","github_repo":"databrickslabs/dbx"},"suited_tasks":["GitHub automation workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","MLOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add databrickslabs/dbx","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add databrickslabs/dbx"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Dbx\" agent skill from https://github.com/databrickslabs/dbx. 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: 🧱 Databricks CLI eXtensions - aka dbx is a CLI tool for development and advanced Databricks workflows management."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Dbx\" as a Claude Code skill from https://github.com/databrickslabs/dbx. 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: 🧱 Databricks CLI eXtensions - aka dbx is a CLI tool for development and advanced Databricks workflows management."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Dbx\" from https://github.com/databrickslabs/dbx 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: 🧱 Databricks CLI eXtensions - aka dbx is a CLI tool for development and advanced Databricks workflows management."}],"handoff_url":"https://www.openagentskill.com/api/skills/databrickslabs-dbx/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/databrickslabs-dbx"},"trust":{"score":71,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"462 GitHub stars","repoActivity":"462 stars, 128 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/databrickslabs/dbx","install":"npx skills add databrickslabs/dbx","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":["ml-automation","mlops","machine-learning","ml-media","ci","cicd"],"known_risks":["License is unclear","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","License clarity: Unknown","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":75,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","License clarity: Unknown","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":73,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[{"slug":"tensorflow-tensorflow","name":"Tensorflow","url":"https://www.openagentskill.com/skills/tensorflow-tensorflow","stars":195681,"install_command":"npx skills add tensorflow/tensorflow","trust_score":91,"audit_score":94},{"slug":"huggingface-transformers","name":"Transformers","url":"https://www.openagentskill.com/skills/huggingface-transformers","stars":161622,"install_command":"npx skills add huggingface/transformers","trust_score":94,"audit_score":95},{"slug":"pytorch-pytorch","name":"Pytorch","url":"https://www.openagentskill.com/skills/pytorch-pytorch","stars":100810,"install_command":"npx skills add pytorch/pytorch","trust_score":88,"audit_score":92},{"slug":"rasbt-llms-from-scratch","name":"LLMs From Scratch","url":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","stars":97256,"install_command":"npx skills add rasbt/LLMs-from-scratch","trust_score":87,"audit_score":90}],"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","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access"],"agent_contract":{"task_input":"Evaluate Dbx 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: 71/100 Manual review","Audit: 75/100 Needs review","Safety: 47/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"databrickslabs-dbx (Dbx)","install_command":"npx skills add databrickslabs/dbx","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":"databrickslabs-dbx","task":"Evaluate Dbx 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/databrickslabs-dbx","api":"https://www.openagentskill.com/api/agent/skills/databrickslabs-dbx","audit":"https://www.openagentskill.com/skills/databrickslabs-dbx/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=databrickslabs-dbx&task=Evaluate%20Dbx%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Dbx%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Evaluate%20Dbx%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/databrickslabs-dbx/install","manifest":"https://www.openagentskill.com/api/registry/manifest/databrickslabs-dbx"}},"endpoints":{"web":"https://www.openagentskill.com/skills/databrickslabs-dbx","api":"https://www.openagentskill.com/api/agent/skills/databrickslabs-dbx","eval":"https://www.openagentskill.com/api/agent/evals?slug=databrickslabs-dbx","audit":"https://www.openagentskill.com/skills/databrickslabs-dbx/audit","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Dbx%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":"2026-07-03T21:37:01.590Z"}}