{"query":"Mlx Tune","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_type":"exact","match_score":99,"raw_match_score":732.8,"semantic_relevance":100,"slug":"arahim3-mlx-tune","name":"Mlx Tune","description":"Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.","tagline":"Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.","category":"media-automation","tags":["speech-recognition","voice","ml-media","apple-silicon","deep-learning","huggingface","large-language-models","llm","llm-finetuning","local-llm"],"author":{"name":"ARahim3","verified":true,"url":"https://github.com/ARahim3"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"ARahim3/mlx-tune","creatorName":"ARahim3","creatorUrl":"https://github.com/ARahim3","sourceUrl":"https://github.com/ARahim3/mlx-tune","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/arahim3-mlx-tune#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":1327,"forks":85,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":60.56},"quality":{"score":91,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"1.3K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.3K stars, 85 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add ARahim3/mlx-tune"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/ARahim3/mlx-tune"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.3K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.3K stars, 85 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add ARahim3/mlx-tune"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/ARahim3/mlx-tune"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"1.3K GitHub stars","repoActivity":"1.3K stars, 85 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/ARahim3/mlx-tune","install":"npx skills add ARahim3/mlx-tune","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add ARahim3/mlx-tune","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["media-automation","speech-recognition","voice","ml-media","apple-silicon","deep-learning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":76,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","76/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"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":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"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.","reasons":["Safe-to-try audit","76/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add ARahim3/mlx-tune","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1327,"starsLabel":"1.3K","forks":85,"license":"Apache-2.0","qualityScore":91,"trustScore":85,"auditScore":88},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":60,"lastPushedAt":"2026-06-23T12:24:30+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","media-automation","speech-recognition","voice","ml-media","apple-silicon","deep-learning"]},"audit":{"audit_score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Multimodal media","role":"Primary pick","primary_fit":"Multimodal media","best_for":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Multimodal media 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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"arahim3-mlx-tune","name":"Mlx Tune","description":"Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.","category":"media-automation","url":"https://www.openagentskill.com/skills/arahim3-mlx-tune","repository":"https://github.com/ARahim3/mlx-tune","github_repo":"ARahim3/mlx-tune"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Python","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ARahim3/mlx-tune","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install arahim3-mlx-tune"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Tune\" agent skill from https://github.com/ARahim3/mlx-tune. 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: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"arahim3-mlx-tune\",\"task\":\"Install Mlx Tune\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Tune\" as a Claude Code skill from https://github.com/ARahim3/mlx-tune. 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: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"arahim3-mlx-tune\",\"task\":\"Install Mlx Tune\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Tune\" from https://github.com/ARahim3/mlx-tune 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: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"arahim3-mlx-tune\",\"task\":\"Install Mlx Tune\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/arahim3-mlx-tune/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/arahim3-mlx-tune"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.3K GitHub stars","repoActivity":"1.3K stars, 85 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/ARahim3/mlx-tune","install":"npx skills add ARahim3/mlx-tune","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","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":["media-automation","speech-recognition","voice","ml-media","apple-silicon","deep-learning"],"known_risks":["Documentation summary is thin"]},"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":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"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":91,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Mlx Tune in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 88/100 Safe to try","Safety: 76/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"arahim3-mlx-tune (Mlx Tune)","install_command":"npx skills add ARahim3/mlx-tune","risk_summary":"Safe to try; Reviewed; Low metadata risk","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":"arahim3-mlx-tune","task":"Use Mlx Tune in an 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/arahim3-mlx-tune","api":"https://www.openagentskill.com/api/agent/skills/arahim3-mlx-tune","audit":"https://www.openagentskill.com/skills/arahim3-mlx-tune/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=arahim3-mlx-tune&task=Use%20Mlx%20Tune%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Tune%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Tune%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/arahim3-mlx-tune/install","manifest":"https://www.openagentskill.com/api/registry/manifest/arahim3-mlx-tune"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"arahim3-mlx-tune","name":"Mlx Tune","description":"Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.","category":"media-automation","url":"https://www.openagentskill.com/skills/arahim3-mlx-tune","repository":"https://github.com/ARahim3/mlx-tune","github_repo":"ARahim3/mlx-tune"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Python","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ARahim3/mlx-tune","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install arahim3-mlx-tune"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Tune\" agent skill from https://github.com/ARahim3/mlx-tune. 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: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"arahim3-mlx-tune\",\"task\":\"Install Mlx Tune\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Tune\" as a Claude Code skill from https://github.com/ARahim3/mlx-tune. 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: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"arahim3-mlx-tune\",\"task\":\"Install Mlx Tune\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Tune\" from https://github.com/ARahim3/mlx-tune 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: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"arahim3-mlx-tune\",\"task\":\"Install Mlx Tune\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/arahim3-mlx-tune/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/arahim3-mlx-tune"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.3K GitHub stars","repoActivity":"1.3K stars, 85 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/ARahim3/mlx-tune","install":"npx skills add ARahim3/mlx-tune","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","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":["media-automation","speech-recognition","voice","ml-media","apple-silicon","deep-learning"],"known_risks":["Documentation summary is thin"]},"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":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"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":91,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Mlx Tune in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 88/100 Safe to try","Safety: 76/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"arahim3-mlx-tune (Mlx Tune)","install_command":"npx skills add ARahim3/mlx-tune","risk_summary":"Safe to try; Reviewed; Low metadata risk","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":"arahim3-mlx-tune","task":"Use Mlx Tune in an 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/arahim3-mlx-tune","api":"https://www.openagentskill.com/api/agent/skills/arahim3-mlx-tune","audit":"https://www.openagentskill.com/skills/arahim3-mlx-tune/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=arahim3-mlx-tune&task=Use%20Mlx%20Tune%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Tune%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Tune%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/arahim3-mlx-tune/install","manifest":"https://www.openagentskill.com/api/registry/manifest/arahim3-mlx-tune"}},"platforms":["Python","Speech"],"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add ARahim3/mlx-tune","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install arahim3-mlx-tune","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Mlx Tune\" agent skill from https://github.com/ARahim3/mlx-tune. 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: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"arahim3-mlx-tune\",\"task\":\"Install Mlx Tune\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Tune\" as a Claude Code skill from https://github.com/ARahim3/mlx-tune. 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: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"arahim3-mlx-tune\",\"task\":\"Install Mlx Tune\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Tune\" from https://github.com/ARahim3/mlx-tune 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: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"arahim3-mlx-tune\",\"task\":\"Install Mlx Tune\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/ARahim3/mlx-tune","github_repo":"ARahim3/mlx-tune","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"arahim3/mlx-tune","recommendation_reasons":["Matches task terms: mlx, tune","Useful GitHub adoption: 1,327 stars","Install handoff is available","Repository freshness signal is available","Registry match score 99"],"urls":{"web":"https://www.openagentskill.com/skills/arahim3-mlx-tune","api":"https://www.openagentskill.com/api/agent/skills/arahim3-mlx-tune","install_api":"https://www.openagentskill.com/api/skills/arahim3-mlx-tune/install","audit":"https://www.openagentskill.com/skills/arahim3-mlx-tune/audit","repository":"https://github.com/ARahim3/mlx-tune"}},{"rank":2,"match_type":"related","match_score":18,"raw_match_score":129.8,"semantic_relevance":30,"slug":"blaizzy-mlx-audio","name":"Mlx Audio","description":"A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.","tagline":"A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.","category":"media-automation","tags":["speech-recognition","voice","ml-media","apple-silicon","audio-processing","mlx","multimodal","speech-synthesis","speech-to-text","text-to-speech"],"author":{"name":"Blaizzy","verified":true,"url":"https://github.com/Blaizzy"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"Blaizzy/mlx-audio","creatorName":"Blaizzy","creatorUrl":"https://github.com/Blaizzy","sourceUrl":"https://github.com/Blaizzy/mlx-audio","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/blaizzy-mlx-audio#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":7409,"forks":645,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":65.79},"quality":{"score":98,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"7.4K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":89,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"7.4K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"7.4K stars, 645 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Blaizzy/mlx-audio"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Blaizzy/mlx-audio"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"7.4K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"7.4K stars, 645 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo 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/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Blaizzy/mlx-audio"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Blaizzy/mlx-audio"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"7.4K GitHub stars","repoActivity":"7.4K stars, 645 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Blaizzy/mlx-audio","install":"npx skills add Blaizzy/mlx-audio","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add Blaizzy/mlx-audio","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["media-automation","speech-recognition","voice","ml-media","apple-silicon","audio-processing"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":80,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","80/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"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":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"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.","reasons":["Safe-to-try audit","80/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"local-desktop","title":"Local desktop"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Blaizzy/mlx-audio","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":7409,"starsLabel":"7.4K","forks":645,"license":"MIT","qualityScore":98,"trustScore":89,"auditScore":92},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":63,"lastPushedAt":"2026-06-19T21:32:01+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","media-automation","speech-recognition","voice","ml-media","apple-silicon","audio-processing"]},"audit":{"audit_score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Multimodal media","role":"Primary pick","primary_fit":"Multimodal media","best_for":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Multimodal media 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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"blaizzy-mlx-audio","name":"Mlx Audio","description":"A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.","category":"media-automation","url":"https://www.openagentskill.com/skills/blaizzy-mlx-audio","repository":"https://github.com/Blaizzy/mlx-audio","github_repo":"Blaizzy/mlx-audio"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Python","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Blaizzy/mlx-audio","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install blaizzy-mlx-audio"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Audio\" agent skill from https://github.com/Blaizzy/mlx-audio. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio\",\"task\":\"Install Mlx Audio\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Audio\" as a Claude Code skill from https://github.com/Blaizzy/mlx-audio. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio\",\"task\":\"Install Mlx Audio\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Audio\" from https://github.com/Blaizzy/mlx-audio into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio\",\"task\":\"Install Mlx Audio\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-audio"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"7.4K GitHub stars","repoActivity":"7.4K stars, 645 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Blaizzy/mlx-audio","install":"npx skills add Blaizzy/mlx-audio","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["media-automation","speech-recognition","voice","ml-media","apple-silicon","audio-processing"],"known_risks":["Documentation summary is thin"]},"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":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"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":98,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Mlx Audio in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 89/100 Production candidate","Audit: 92/100 Safe to try","Safety: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"blaizzy-mlx-audio (Mlx Audio)","install_command":"npx skills add Blaizzy/mlx-audio","risk_summary":"Safe to try; Reviewed; Low metadata risk","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":"blaizzy-mlx-audio","task":"Use Mlx Audio in an 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/blaizzy-mlx-audio","api":"https://www.openagentskill.com/api/agent/skills/blaizzy-mlx-audio","audit":"https://www.openagentskill.com/skills/blaizzy-mlx-audio/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=blaizzy-mlx-audio&task=Use%20Mlx%20Audio%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Audio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Audio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio/install","manifest":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-audio"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"blaizzy-mlx-audio","name":"Mlx Audio","description":"A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.","category":"media-automation","url":"https://www.openagentskill.com/skills/blaizzy-mlx-audio","repository":"https://github.com/Blaizzy/mlx-audio","github_repo":"Blaizzy/mlx-audio"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Python","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Blaizzy/mlx-audio","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install blaizzy-mlx-audio"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Audio\" agent skill from https://github.com/Blaizzy/mlx-audio. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio\",\"task\":\"Install Mlx Audio\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Audio\" as a Claude Code skill from https://github.com/Blaizzy/mlx-audio. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio\",\"task\":\"Install Mlx Audio\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Audio\" from https://github.com/Blaizzy/mlx-audio into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio\",\"task\":\"Install Mlx Audio\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-audio"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"7.4K GitHub stars","repoActivity":"7.4K stars, 645 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Blaizzy/mlx-audio","install":"npx skills add Blaizzy/mlx-audio","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["media-automation","speech-recognition","voice","ml-media","apple-silicon","audio-processing"],"known_risks":["Documentation summary is thin"]},"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":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"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":98,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Mlx Audio in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 89/100 Production candidate","Audit: 92/100 Safe to try","Safety: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"blaizzy-mlx-audio (Mlx Audio)","install_command":"npx skills add Blaizzy/mlx-audio","risk_summary":"Safe to try; Reviewed; Low metadata risk","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":"blaizzy-mlx-audio","task":"Use Mlx Audio in an 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/blaizzy-mlx-audio","api":"https://www.openagentskill.com/api/agent/skills/blaizzy-mlx-audio","audit":"https://www.openagentskill.com/skills/blaizzy-mlx-audio/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=blaizzy-mlx-audio&task=Use%20Mlx%20Audio%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Audio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Audio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio/install","manifest":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-audio"}},"platforms":["Python","Speech"],"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"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":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"}],"install":"npx skills add Blaizzy/mlx-audio","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install blaizzy-mlx-audio","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Mlx Audio\" agent skill from https://github.com/Blaizzy/mlx-audio. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio\",\"task\":\"Install Mlx Audio\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Audio\" as a Claude Code skill from https://github.com/Blaizzy/mlx-audio. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio\",\"task\":\"Install Mlx Audio\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Audio\" from https://github.com/Blaizzy/mlx-audio into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio\",\"task\":\"Install Mlx Audio\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/Blaizzy/mlx-audio","github_repo":"Blaizzy/mlx-audio","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"blaizzy/mlx-audio","recommendation_reasons":["Matches task terms: mlx","Useful GitHub adoption: 7,409 stars","Install handoff is available","Repository freshness signal is available","Registry match score 18"],"urls":{"web":"https://www.openagentskill.com/skills/blaizzy-mlx-audio","api":"https://www.openagentskill.com/api/agent/skills/blaizzy-mlx-audio","install_api":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio/install","audit":"https://www.openagentskill.com/skills/blaizzy-mlx-audio/audit","repository":"https://github.com/Blaizzy/mlx-audio"}},{"rank":3,"match_type":"related","match_score":16,"raw_match_score":114.8,"semantic_relevance":30,"slug":"blaizzy-mlx-audio-swift","name":"Mlx Audio Swift","description":"A modular Swift SDK for audio processing with MLX on Apple Silicon","tagline":"A modular Swift SDK for audio processing with MLX on Apple Silicon","category":"media-automation","tags":["text-to-speech","voice","ml-media","mlx","mlx-audio","mlx-audio-swift","mlx-swift-audio","speech-to-speech","speech-to-text","stt"],"author":{"name":"Blaizzy","verified":false,"url":"https://github.com/Blaizzy"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"Blaizzy/mlx-audio-swift","creatorName":"Blaizzy","creatorUrl":"https://github.com/Blaizzy","sourceUrl":"https://github.com/Blaizzy/mlx-audio-swift","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/blaizzy-mlx-audio-swift#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":675,"forks":114,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":50.51},"quality":{"score":74,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"675","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":76,"weight":0.13,"status":"info","detail":"675 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"675 stars, 114 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Blaizzy/mlx-audio-swift"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Blaizzy/mlx-audio-swift"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"675 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"675 stars, 114 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Blaizzy/mlx-audio-swift"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Blaizzy/mlx-audio-swift"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"675 GitHub stars","repoActivity":"675 stars, 114 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Blaizzy/mlx-audio-swift","install":"npx skills add Blaizzy/mlx-audio-swift","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add Blaizzy/mlx-audio-swift","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Swift","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["media-automation","text-to-speech","voice","ml-media","mlx","mlx-audio"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":69,"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":["Documentation summary is thin","69/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"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":["Documentation summary is thin","69/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Swift"],"install":{"ready":true,"command":"npx skills add Blaizzy/mlx-audio-swift","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":675,"starsLabel":"675","forks":114,"license":"MIT","qualityScore":74,"trustScore":79,"auditScore":81},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-14T19:31:52+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Design","Multimodal media","media-automation","text-to-speech","voice","ml-media","mlx","mlx-audio"]},"audit":{"audit_score":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":85,"readiness_label":"Production-ready","headline":"Primary pick for Multimodal media","role":"Primary pick","primary_fit":"Multimodal media","best_for":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Multimodal media 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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"blaizzy-mlx-audio-swift","name":"Mlx Audio Swift","description":"A modular Swift SDK for audio processing with MLX on Apple Silicon","category":"media-automation","url":"https://www.openagentskill.com/skills/blaizzy-mlx-audio-swift","repository":"https://github.com/Blaizzy/mlx-audio-swift","github_repo":"Blaizzy/mlx-audio-swift"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Swift","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Blaizzy/mlx-audio-swift","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install blaizzy-mlx-audio-swift"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Audio Swift\" agent skill from https://github.com/Blaizzy/mlx-audio-swift. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A modular Swift SDK for audio processing with MLX on Apple Silicon After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio-swift\",\"task\":\"Install Mlx Audio Swift\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Audio Swift\" as a Claude Code skill from https://github.com/Blaizzy/mlx-audio-swift. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A modular Swift SDK for audio processing with MLX on Apple Silicon After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio-swift\",\"task\":\"Install Mlx Audio Swift\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Audio Swift\" from https://github.com/Blaizzy/mlx-audio-swift into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A modular Swift SDK for audio processing with MLX on Apple Silicon After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio-swift\",\"task\":\"Install Mlx Audio Swift\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio-swift/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-audio-swift"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"675 GitHub stars","repoActivity":"675 stars, 114 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Blaizzy/mlx-audio-swift","install":"npx skills add Blaizzy/mlx-audio-swift","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","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":["media-automation","text-to-speech","voice","ml-media","mlx","mlx-audio"],"known_risks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","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."},"quality":{"score":74,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Mlx Audio Swift in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 81/100 Needs review","Safety: 69/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"blaizzy-mlx-audio-swift (Mlx Audio Swift)","install_command":"npx skills add Blaizzy/mlx-audio-swift","risk_summary":"Needs review; Reviewed with permission notes; 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":"blaizzy-mlx-audio-swift","task":"Use Mlx Audio Swift in an 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/blaizzy-mlx-audio-swift","api":"https://www.openagentskill.com/api/agent/skills/blaizzy-mlx-audio-swift","audit":"https://www.openagentskill.com/skills/blaizzy-mlx-audio-swift/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=blaizzy-mlx-audio-swift&task=Use%20Mlx%20Audio%20Swift%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Audio%20Swift%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Audio%20Swift%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio-swift/install","manifest":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-audio-swift"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"blaizzy-mlx-audio-swift","name":"Mlx Audio Swift","description":"A modular Swift SDK for audio processing with MLX on Apple Silicon","category":"media-automation","url":"https://www.openagentskill.com/skills/blaizzy-mlx-audio-swift","repository":"https://github.com/Blaizzy/mlx-audio-swift","github_repo":"Blaizzy/mlx-audio-swift"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Swift","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Blaizzy/mlx-audio-swift","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install blaizzy-mlx-audio-swift"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Audio Swift\" agent skill from https://github.com/Blaizzy/mlx-audio-swift. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A modular Swift SDK for audio processing with MLX on Apple Silicon After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio-swift\",\"task\":\"Install Mlx Audio Swift\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Audio Swift\" as a Claude Code skill from https://github.com/Blaizzy/mlx-audio-swift. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A modular Swift SDK for audio processing with MLX on Apple Silicon After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio-swift\",\"task\":\"Install Mlx Audio Swift\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Audio Swift\" from https://github.com/Blaizzy/mlx-audio-swift into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A modular Swift SDK for audio processing with MLX on Apple Silicon After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio-swift\",\"task\":\"Install Mlx Audio Swift\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio-swift/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-audio-swift"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"675 GitHub stars","repoActivity":"675 stars, 114 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Blaizzy/mlx-audio-swift","install":"npx skills add Blaizzy/mlx-audio-swift","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","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":["media-automation","text-to-speech","voice","ml-media","mlx","mlx-audio"],"known_risks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","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."},"quality":{"score":74,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Mlx Audio Swift in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 81/100 Needs review","Safety: 69/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"blaizzy-mlx-audio-swift (Mlx Audio Swift)","install_command":"npx skills add Blaizzy/mlx-audio-swift","risk_summary":"Needs review; Reviewed with permission notes; 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":"blaizzy-mlx-audio-swift","task":"Use Mlx Audio Swift in an 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/blaizzy-mlx-audio-swift","api":"https://www.openagentskill.com/api/agent/skills/blaizzy-mlx-audio-swift","audit":"https://www.openagentskill.com/skills/blaizzy-mlx-audio-swift/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=blaizzy-mlx-audio-swift&task=Use%20Mlx%20Audio%20Swift%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Audio%20Swift%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Audio%20Swift%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio-swift/install","manifest":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-audio-swift"}},"platforms":["Swift","Voice"],"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add Blaizzy/mlx-audio-swift","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install blaizzy-mlx-audio-swift","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Mlx Audio Swift\" agent skill from https://github.com/Blaizzy/mlx-audio-swift. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A modular Swift SDK for audio processing with MLX on Apple Silicon After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio-swift\",\"task\":\"Install Mlx Audio Swift\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Audio Swift\" as a Claude Code skill from https://github.com/Blaizzy/mlx-audio-swift. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A modular Swift SDK for audio processing with MLX on Apple Silicon After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio-swift\",\"task\":\"Install Mlx Audio Swift\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Audio Swift\" from https://github.com/Blaizzy/mlx-audio-swift into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A modular Swift SDK for audio processing with MLX on Apple Silicon After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-audio-swift\",\"task\":\"Install Mlx Audio Swift\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/Blaizzy/mlx-audio-swift","github_repo":"Blaizzy/mlx-audio-swift","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"blaizzy/mlx-audio-swift","recommendation_reasons":["Matches task terms: mlx","Useful GitHub adoption: 675 stars","Install handoff is available","Repository freshness signal is available","Registry match score 16"],"urls":{"web":"https://www.openagentskill.com/skills/blaizzy-mlx-audio-swift","api":"https://www.openagentskill.com/api/agent/skills/blaizzy-mlx-audio-swift","install_api":"https://www.openagentskill.com/api/skills/blaizzy-mlx-audio-swift/install","audit":"https://www.openagentskill.com/skills/blaizzy-mlx-audio-swift/audit","repository":"https://github.com/Blaizzy/mlx-audio-swift"}},{"rank":4,"match_type":"related","match_score":15,"raw_match_score":112.8,"semantic_relevance":30,"slug":"cubist38-mlx-openai-server","name":"Mlx Openai Server","description":"A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.","tagline":"A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.","category":"media-automation","tags":["image-generation","media","ml-media","apple-silicon","continuous-batching","fastapi","flux","mlx","mlx-lm","mlx-vlm"],"author":{"name":"cubist38","verified":false,"url":"https://github.com/cubist38"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"cubist38/mlx-openai-server","creatorName":"cubist38","creatorUrl":"https://github.com/cubist38","sourceUrl":"https://github.com/cubist38/mlx-openai-server","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/cubist38-mlx-openai-server#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":345,"forks":65,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":48.47},"quality":{"score":77,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"345","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":77,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"345 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"345 stars, 65 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add cubist38/mlx-openai-server"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/cubist38/mlx-openai-server"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"345 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"345 stars, 65 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo 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/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add cubist38/mlx-openai-server"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/cubist38/mlx-openai-server"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin"],"evidence":{"stars":"345 GitHub stars","repoActivity":"345 stars, 65 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/cubist38/mlx-openai-server","install":"npx skills add cubist38/mlx-openai-server","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add cubist38/mlx-openai-server","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Image Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["media-automation","image-generation","media","ml-media","apple-silicon","continuous-batching"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin"]},"safety":{"score":70,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","70/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"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":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"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.","reasons":["Safe-to-try audit","70/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"design-creative","title":"Design and creative"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add cubist38/mlx-openai-server","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":345,"starsLabel":"345","forks":65,"license":"MIT","qualityScore":77,"trustScore":77,"auditScore":82},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":67,"lastPushedAt":"2026-06-15T18:06:30+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","media-automation","image-generation","media","ml-media","apple-silicon","continuous-batching"]},"audit":{"audit_score":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"decision":{"readiness_score":76,"readiness_label":"Strong shortlist","headline":"Companion skill for Multimodal media","role":"Companion skill","primary_fit":"Multimodal media","best_for":["Multimodal media workflows","OpenAI Agents teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Multimodal media 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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"cubist38-mlx-openai-server","name":"Mlx Openai Server","description":"A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.","category":"media-automation","url":"https://www.openagentskill.com/skills/cubist38-mlx-openai-server","repository":"https://github.com/cubist38/mlx-openai-server","github_repo":"cubist38/mlx-openai-server"},"suited_tasks":["Multimodal media workflows","OpenAI Agents teams","builders willing to evaluate younger projects","Read media metadata","Convert formats","Summarize visual or audio content","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Python","Image Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add cubist38/mlx-openai-server","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install cubist38-mlx-openai-server"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Openai Server\" agent skill from https://github.com/cubist38/mlx-openai-server. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cubist38-mlx-openai-server\",\"task\":\"Install Mlx Openai Server\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Openai Server\" as a Claude Code skill from https://github.com/cubist38/mlx-openai-server. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cubist38-mlx-openai-server\",\"task\":\"Install Mlx Openai Server\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Openai Server\" from https://github.com/cubist38/mlx-openai-server into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cubist38-mlx-openai-server\",\"task\":\"Install Mlx Openai Server\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/cubist38-mlx-openai-server/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/cubist38-mlx-openai-server"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"345 GitHub stars","repoActivity":"345 stars, 65 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/cubist38/mlx-openai-server","install":"npx skills add cubist38/mlx-openai-server","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","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":["media-automation","image-generation","media","ml-media","apple-silicon","continuous-batching"],"known_risks":["Quality score needs review","Documentation summary is thin"]},"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":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"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":77,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Mlx Openai Server in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 77/100 Strong shortlist","Audit: 82/100 Safe to try","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"cubist38-mlx-openai-server (Mlx Openai Server)","install_command":"npx skills add cubist38/mlx-openai-server","risk_summary":"Safe to try; Reviewed; 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":"cubist38-mlx-openai-server","task":"Use Mlx Openai Server in an 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/cubist38-mlx-openai-server","api":"https://www.openagentskill.com/api/agent/skills/cubist38-mlx-openai-server","audit":"https://www.openagentskill.com/skills/cubist38-mlx-openai-server/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=cubist38-mlx-openai-server&task=Use%20Mlx%20Openai%20Server%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Openai%20Server%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Openai%20Server%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/cubist38-mlx-openai-server/install","manifest":"https://www.openagentskill.com/api/registry/manifest/cubist38-mlx-openai-server"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"cubist38-mlx-openai-server","name":"Mlx Openai Server","description":"A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.","category":"media-automation","url":"https://www.openagentskill.com/skills/cubist38-mlx-openai-server","repository":"https://github.com/cubist38/mlx-openai-server","github_repo":"cubist38/mlx-openai-server"},"suited_tasks":["Multimodal media workflows","OpenAI Agents teams","builders willing to evaluate younger projects","Read media metadata","Convert formats","Summarize visual or audio content","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Python","Image Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add cubist38/mlx-openai-server","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install cubist38-mlx-openai-server"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Openai Server\" agent skill from https://github.com/cubist38/mlx-openai-server. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cubist38-mlx-openai-server\",\"task\":\"Install Mlx Openai Server\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Openai Server\" as a Claude Code skill from https://github.com/cubist38/mlx-openai-server. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cubist38-mlx-openai-server\",\"task\":\"Install Mlx Openai Server\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Openai Server\" from https://github.com/cubist38/mlx-openai-server into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cubist38-mlx-openai-server\",\"task\":\"Install Mlx Openai Server\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/cubist38-mlx-openai-server/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/cubist38-mlx-openai-server"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"345 GitHub stars","repoActivity":"345 stars, 65 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/cubist38/mlx-openai-server","install":"npx skills add cubist38/mlx-openai-server","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","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":["media-automation","image-generation","media","ml-media","apple-silicon","continuous-batching"],"known_risks":["Quality score needs review","Documentation summary is thin"]},"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":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"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":77,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Mlx Openai Server in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 77/100 Strong shortlist","Audit: 82/100 Safe to try","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"cubist38-mlx-openai-server (Mlx Openai Server)","install_command":"npx skills add cubist38/mlx-openai-server","risk_summary":"Safe to try; Reviewed; 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":"cubist38-mlx-openai-server","task":"Use Mlx Openai Server in an 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/cubist38-mlx-openai-server","api":"https://www.openagentskill.com/api/agent/skills/cubist38-mlx-openai-server","audit":"https://www.openagentskill.com/skills/cubist38-mlx-openai-server/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=cubist38-mlx-openai-server&task=Use%20Mlx%20Openai%20Server%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Openai%20Server%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Openai%20Server%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/cubist38-mlx-openai-server/install","manifest":"https://www.openagentskill.com/api/registry/manifest/cubist38-mlx-openai-server"}},"platforms":["Python","Image Generation","OpenAI Agents"],"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add cubist38/mlx-openai-server","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install cubist38-mlx-openai-server","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Mlx Openai Server\" agent skill from https://github.com/cubist38/mlx-openai-server. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cubist38-mlx-openai-server\",\"task\":\"Install Mlx Openai Server\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Openai Server\" as a Claude Code skill from https://github.com/cubist38/mlx-openai-server. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cubist38-mlx-openai-server\",\"task\":\"Install Mlx Openai Server\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Openai Server\" from https://github.com/cubist38/mlx-openai-server into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cubist38-mlx-openai-server\",\"task\":\"Install Mlx Openai Server\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/cubist38/mlx-openai-server","github_repo":"cubist38/mlx-openai-server","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"cubist38/mlx-openai-server","recommendation_reasons":["Matches task terms: mlx","Install handoff is available","Repository freshness signal is available","Registry match score 15"],"urls":{"web":"https://www.openagentskill.com/skills/cubist38-mlx-openai-server","api":"https://www.openagentskill.com/api/agent/skills/cubist38-mlx-openai-server","install_api":"https://www.openagentskill.com/api/skills/cubist38-mlx-openai-server/install","audit":"https://www.openagentskill.com/skills/cubist38-mlx-openai-server/audit","repository":"https://github.com/cubist38/mlx-openai-server"}},{"rank":5,"match_type":"related","match_score":15,"raw_match_score":112.5,"semantic_relevance":30,"slug":"ziqi-jin-finetune-anything","name":"Finetune Anything","description":"Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ...  in specific scenarios","tagline":"Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ...  in specific scenarios","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","deep-learning","fine-tune","segment-anything","python","github"],"author":{"name":"ziqi-jin","verified":false,"url":"https://github.com/ziqi-jin"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"ziqi-jin/finetune-anything","creatorName":"ziqi-jin","creatorUrl":"https://github.com/ziqi-jin","sourceUrl":"https://github.com/ziqi-jin/finetune-anything","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/ziqi-jin-finetune-anything#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":864,"forks":63,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":39.26},"quality":{"score":50,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"864","tone":"positive"},{"label":"Freshness","value":"3y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":73,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":76,"weight":0.13,"status":"info","detail":"864 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"864 stars, 63 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add ziqi-jin/finetune-anything"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/ziqi-jin/finetune-anything"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"864 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"864 stars, 63 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y 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/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add ziqi-jin/finetune-anything"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/ziqi-jin/finetune-anything"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"],"evidence":{"stars":"864 GitHub stars","repoActivity":"864 stars, 63 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/ziqi-jin/finetune-anything","install":"npx skills add ziqi-jin/finetune-anything","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add ziqi-jin/finetune-anything","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3y since push"]},"agentCompatibility":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","computer-vision","automation","deep-learning","fine-tune","segment-anything"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"safety":{"score":52,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Repository appears stale","52/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Repository appears stale"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"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.","reasons":["Repository appears stale","52/100 agent safety score"]},"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":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add ziqi-jin/finetune-anything","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":864,"starsLabel":"864","forks":63,"license":"MIT","qualityScore":50,"trustScore":73,"auditScore":64},"maintenance":{"status":"stale","label":"3y since push","daysSincePush":1113,"lastPushedAt":"2023-08-05T13:33:13+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"coverageTags":["Coding","GitHub automation","robotics-iot","computer-vision","automation","deep-learning","fine-tune","segment-anything"]},"audit":{"audit_score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"decision":{"readiness_score":52,"readiness_label":"Needs manual review","headline":"Needs validation for GitHub automation","role":"Needs validation","primary_fit":"GitHub automation","best_for":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub 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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ziqi-jin-finetune-anything","name":"Finetune Anything","description":"Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ...  in specific scenarios","category":"robotics-iot","url":"https://www.openagentskill.com/skills/ziqi-jin-finetune-anything","repository":"https://github.com/ziqi-jin/finetune-anything","github_repo":"ziqi-jin/finetune-anything"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Move data between tools","Transform files"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ziqi-jin/finetune-anything","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install ziqi-jin-finetune-anything"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Finetune Anything\" agent skill from https://github.com/ziqi-jin/finetune-anything. 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: Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ziqi-jin-finetune-anything\",\"task\":\"Install Finetune Anything\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Finetune Anything\" as a Claude Code skill from https://github.com/ziqi-jin/finetune-anything. 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: Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ziqi-jin-finetune-anything\",\"task\":\"Install Finetune Anything\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Finetune Anything\" from https://github.com/ziqi-jin/finetune-anything 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: Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ziqi-jin-finetune-anything\",\"task\":\"Install Finetune Anything\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/ziqi-jin-finetune-anything/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ziqi-jin-finetune-anything"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"864 GitHub stars","repoActivity":"864 stars, 63 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/ziqi-jin/finetune-anything","install":"npx skills add ziqi-jin/finetune-anything","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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":["robotics-iot","computer-vision","automation","deep-learning","fine-tune","segment-anything"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"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":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"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":50,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"],"agent_contract":{"task_input":"Use Finetune Anything in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 64/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ziqi-jin-finetune-anything (Finetune Anything)","install_command":"npx skills add ziqi-jin/finetune-anything","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":"ziqi-jin-finetune-anything","task":"Use Finetune Anything in an 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/ziqi-jin-finetune-anything","api":"https://www.openagentskill.com/api/agent/skills/ziqi-jin-finetune-anything","audit":"https://www.openagentskill.com/skills/ziqi-jin-finetune-anything/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ziqi-jin-finetune-anything&task=Use%20Finetune%20Anything%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Finetune%20Anything%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Finetune%20Anything%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ziqi-jin-finetune-anything/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ziqi-jin-finetune-anything"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ziqi-jin-finetune-anything","name":"Finetune Anything","description":"Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ...  in specific scenarios","category":"robotics-iot","url":"https://www.openagentskill.com/skills/ziqi-jin-finetune-anything","repository":"https://github.com/ziqi-jin/finetune-anything","github_repo":"ziqi-jin/finetune-anything"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Move data between tools","Transform files"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ziqi-jin/finetune-anything","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install ziqi-jin-finetune-anything"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Finetune Anything\" agent skill from https://github.com/ziqi-jin/finetune-anything. 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: Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ziqi-jin-finetune-anything\",\"task\":\"Install Finetune Anything\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Finetune Anything\" as a Claude Code skill from https://github.com/ziqi-jin/finetune-anything. 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: Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ziqi-jin-finetune-anything\",\"task\":\"Install Finetune Anything\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Finetune Anything\" from https://github.com/ziqi-jin/finetune-anything 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: Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ziqi-jin-finetune-anything\",\"task\":\"Install Finetune Anything\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/ziqi-jin-finetune-anything/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ziqi-jin-finetune-anything"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"864 GitHub stars","repoActivity":"864 stars, 63 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/ziqi-jin/finetune-anything","install":"npx skills add ziqi-jin/finetune-anything","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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":["robotics-iot","computer-vision","automation","deep-learning","fine-tune","segment-anything"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"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":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"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":50,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"],"agent_contract":{"task_input":"Use Finetune Anything in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 64/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ziqi-jin-finetune-anything (Finetune Anything)","install_command":"npx skills add ziqi-jin/finetune-anything","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":"ziqi-jin-finetune-anything","task":"Use Finetune Anything in an 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/ziqi-jin-finetune-anything","api":"https://www.openagentskill.com/api/agent/skills/ziqi-jin-finetune-anything","audit":"https://www.openagentskill.com/skills/ziqi-jin-finetune-anything/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ziqi-jin-finetune-anything&task=Use%20Finetune%20Anything%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Finetune%20Anything%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Finetune%20Anything%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ziqi-jin-finetune-anything/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ziqi-jin-finetune-anything"}},"platforms":["Python","Computer Vision"],"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"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"}],"install":"npx skills add ziqi-jin/finetune-anything","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install ziqi-jin-finetune-anything","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Finetune Anything\" agent skill from https://github.com/ziqi-jin/finetune-anything. 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: Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ziqi-jin-finetune-anything\",\"task\":\"Install Finetune Anything\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Finetune Anything\" as a Claude Code skill from https://github.com/ziqi-jin/finetune-anything. 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: Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ziqi-jin-finetune-anything\",\"task\":\"Install Finetune Anything\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Finetune Anything\" from https://github.com/ziqi-jin/finetune-anything 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: Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ziqi-jin-finetune-anything\",\"task\":\"Install Finetune Anything\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/ziqi-jin/finetune-anything","github_repo":"ziqi-jin/finetune-anything","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"ziqi-jin/finetune-anything","recommendation_reasons":["Matches task terms: tune","Useful GitHub adoption: 864 stars","Install handoff is available","Repository freshness signal is available","Registry match score 15"],"urls":{"web":"https://www.openagentskill.com/skills/ziqi-jin-finetune-anything","api":"https://www.openagentskill.com/api/agent/skills/ziqi-jin-finetune-anything","install_api":"https://www.openagentskill.com/api/skills/ziqi-jin-finetune-anything/install","audit":"https://www.openagentskill.com/skills/ziqi-jin-finetune-anything/audit","repository":"https://github.com/ziqi-jin/finetune-anything"}},{"rank":6,"match_type":"related","match_score":15,"raw_match_score":111.6,"semantic_relevance":30,"slug":"lucasnewman-f5-tts-mlx","name":"F5 Tts Mlx","description":"Implementation of F5-TTS in MLX","tagline":"Implementation of F5-TTS in MLX","category":"media-automation","tags":["text-to-speech","voice","ml-media","diffusion-transformer","flow-matching","mlx","tts","python","github"],"author":{"name":"lucasnewman","verified":false,"url":"https://github.com/lucasnewman"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"lucasnewman/f5-tts-mlx","creatorName":"lucasnewman","creatorUrl":"https://github.com/lucasnewman","sourceUrl":"https://github.com/lucasnewman/f5-tts-mlx","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/lucasnewman-f5-tts-mlx#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":635,"forks":65,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":38.32},"quality":{"score":48,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"635","tone":"positive"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":73,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":76,"weight":0.13,"status":"info","detail":"635 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"635 stars, 65 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add lucasnewman/f5-tts-mlx"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/lucasnewman/f5-tts-mlx"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"635 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"635 stars, 65 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add lucasnewman/f5-tts-mlx"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/lucasnewman/f5-tts-mlx"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"635 GitHub stars","repoActivity":"635 stars, 65 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/lucasnewman/f5-tts-mlx","install":"npx skills add lucasnewman/f5-tts-mlx","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add lucasnewman/f5-tts-mlx","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1y since push"]},"agentCompatibility":["Python","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["media-automation","text-to-speech","voice","ml-media","diffusion-transformer","flow-matching"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":53,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Documentation summary is thin","53/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"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.","reasons":["Documentation summary is thin","53/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add lucasnewman/f5-tts-mlx","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":635,"starsLabel":"635","forks":65,"license":"MIT","qualityScore":48,"trustScore":73,"auditScore":65},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":521,"lastPushedAt":"2025-03-19T02:10:28+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"coverageTags":["Design","Multimodal media","media-automation","text-to-speech","voice","ml-media","diffusion-transformer","flow-matching"]},"audit":{"audit_score":65,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"decision":{"readiness_score":50,"readiness_label":"Needs manual review","headline":"Needs validation for Browser automation","role":"Needs validation","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"lucasnewman-f5-tts-mlx","name":"F5 Tts Mlx","description":"Implementation of F5-TTS in MLX","category":"media-automation","url":"https://www.openagentskill.com/skills/lucasnewman-f5-tts-mlx","repository":"https://github.com/lucasnewman/f5-tts-mlx","github_repo":"lucasnewman/f5-tts-mlx"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add lucasnewman/f5-tts-mlx","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install lucasnewman-f5-tts-mlx"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"F5 Tts Mlx\" agent skill from https://github.com/lucasnewman/f5-tts-mlx. 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: Implementation of F5-TTS in MLX After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"lucasnewman-f5-tts-mlx\",\"task\":\"Install F5 Tts Mlx\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"F5 Tts Mlx\" as a Claude Code skill from https://github.com/lucasnewman/f5-tts-mlx. 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: Implementation of F5-TTS in MLX After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"lucasnewman-f5-tts-mlx\",\"task\":\"Install F5 Tts Mlx\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"F5 Tts Mlx\" from https://github.com/lucasnewman/f5-tts-mlx 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: Implementation of F5-TTS in MLX After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"lucasnewman-f5-tts-mlx\",\"task\":\"Install F5 Tts Mlx\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/lucasnewman-f5-tts-mlx/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/lucasnewman-f5-tts-mlx"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"635 GitHub stars","repoActivity":"635 stars, 65 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/lucasnewman/f5-tts-mlx","install":"npx skills add lucasnewman/f5-tts-mlx","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","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":["media-automation","text-to-speech","voice","ml-media","diffusion-transformer","flow-matching"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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":65,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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":48,"label":"Needs review"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push"],"agent_contract":{"task_input":"Use F5 Tts Mlx in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 65/100 Needs review","Safety: 53/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"lucasnewman-f5-tts-mlx (F5 Tts Mlx)","install_command":"npx skills add lucasnewman/f5-tts-mlx","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":"lucasnewman-f5-tts-mlx","task":"Use F5 Tts Mlx in an 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/lucasnewman-f5-tts-mlx","api":"https://www.openagentskill.com/api/agent/skills/lucasnewman-f5-tts-mlx","audit":"https://www.openagentskill.com/skills/lucasnewman-f5-tts-mlx/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=lucasnewman-f5-tts-mlx&task=Use%20F5%20Tts%20Mlx%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20F5%20Tts%20Mlx%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20F5%20Tts%20Mlx%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/lucasnewman-f5-tts-mlx/install","manifest":"https://www.openagentskill.com/api/registry/manifest/lucasnewman-f5-tts-mlx"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"lucasnewman-f5-tts-mlx","name":"F5 Tts Mlx","description":"Implementation of F5-TTS in MLX","category":"media-automation","url":"https://www.openagentskill.com/skills/lucasnewman-f5-tts-mlx","repository":"https://github.com/lucasnewman/f5-tts-mlx","github_repo":"lucasnewman/f5-tts-mlx"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add lucasnewman/f5-tts-mlx","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install lucasnewman-f5-tts-mlx"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"F5 Tts Mlx\" agent skill from https://github.com/lucasnewman/f5-tts-mlx. 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: Implementation of F5-TTS in MLX After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"lucasnewman-f5-tts-mlx\",\"task\":\"Install F5 Tts Mlx\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"F5 Tts Mlx\" as a Claude Code skill from https://github.com/lucasnewman/f5-tts-mlx. 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: Implementation of F5-TTS in MLX After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"lucasnewman-f5-tts-mlx\",\"task\":\"Install F5 Tts Mlx\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"F5 Tts Mlx\" from https://github.com/lucasnewman/f5-tts-mlx 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: Implementation of F5-TTS in MLX After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"lucasnewman-f5-tts-mlx\",\"task\":\"Install F5 Tts Mlx\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/lucasnewman-f5-tts-mlx/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/lucasnewman-f5-tts-mlx"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"635 GitHub stars","repoActivity":"635 stars, 65 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/lucasnewman/f5-tts-mlx","install":"npx skills add lucasnewman/f5-tts-mlx","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","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":["media-automation","text-to-speech","voice","ml-media","diffusion-transformer","flow-matching"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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":65,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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":48,"label":"Needs review"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push"],"agent_contract":{"task_input":"Use F5 Tts Mlx in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 65/100 Needs review","Safety: 53/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"lucasnewman-f5-tts-mlx (F5 Tts Mlx)","install_command":"npx skills add lucasnewman/f5-tts-mlx","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":"lucasnewman-f5-tts-mlx","task":"Use F5 Tts Mlx in an 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/lucasnewman-f5-tts-mlx","api":"https://www.openagentskill.com/api/agent/skills/lucasnewman-f5-tts-mlx","audit":"https://www.openagentskill.com/skills/lucasnewman-f5-tts-mlx/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=lucasnewman-f5-tts-mlx&task=Use%20F5%20Tts%20Mlx%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20F5%20Tts%20Mlx%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20F5%20Tts%20Mlx%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/lucasnewman-f5-tts-mlx/install","manifest":"https://www.openagentskill.com/api/registry/manifest/lucasnewman-f5-tts-mlx"}},"platforms":["Python","Voice"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add lucasnewman/f5-tts-mlx","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install lucasnewman-f5-tts-mlx","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"F5 Tts Mlx\" agent skill from https://github.com/lucasnewman/f5-tts-mlx. 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: Implementation of F5-TTS in MLX After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"lucasnewman-f5-tts-mlx\",\"task\":\"Install F5 Tts Mlx\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"F5 Tts Mlx\" as a Claude Code skill from https://github.com/lucasnewman/f5-tts-mlx. 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: Implementation of F5-TTS in MLX After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"lucasnewman-f5-tts-mlx\",\"task\":\"Install F5 Tts Mlx\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"F5 Tts Mlx\" from https://github.com/lucasnewman/f5-tts-mlx 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: Implementation of F5-TTS in MLX After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"lucasnewman-f5-tts-mlx\",\"task\":\"Install F5 Tts Mlx\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/lucasnewman/f5-tts-mlx","github_repo":"lucasnewman/f5-tts-mlx","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"lucasnewman/f5-tts-mlx","recommendation_reasons":["Matches task terms: mlx","Useful GitHub adoption: 635 stars","Install handoff is available","Repository freshness signal is available","Registry match score 15"],"urls":{"web":"https://www.openagentskill.com/skills/lucasnewman-f5-tts-mlx","api":"https://www.openagentskill.com/api/agent/skills/lucasnewman-f5-tts-mlx","install_api":"https://www.openagentskill.com/api/skills/lucasnewman-f5-tts-mlx/install","audit":"https://www.openagentskill.com/skills/lucasnewman-f5-tts-mlx/audit","repository":"https://github.com/lucasnewman/f5-tts-mlx"}},{"rank":7,"match_type":"related","match_score":15,"raw_match_score":109.5,"semantic_relevance":30,"slug":"claimed-framework-mlx","name":"Mlx","description":"Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine","tagline":"Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine","category":"devops","tags":["kubernetes","devops","datasets","kubeflow-pipeline","machine-learning","mlx","mlx-catalog","models","notebook-jupyter","openshift"],"author":{"name":"claimed-framework","verified":false,"url":"https://github.com/claimed-framework"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"claimed-framework/mlx","creatorName":"claimed-framework","creatorUrl":"https://github.com/claimed-framework","sourceUrl":"https://github.com/claimed-framework/mlx","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/claimed-framework-mlx#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":220,"forks":54,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":39.11},"quality":{"score":57,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"220","tone":"neutral"},{"label":"Freshness","value":"11mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"220 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"220 stars, 54 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add claimed-framework/mlx"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/claimed-framework/mlx"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"220 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"220 stars, 54 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"11mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add claimed-framework/mlx"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/claimed-framework/mlx"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Documentation summary is thin"],"evidence":{"stars":"220 GitHub stars","repoActivity":"220 stars, 54 forks","lastPushed":"11mo since push","license":"Apache-2.0","repository":"https://github.com/claimed-framework/mlx","install":"npx skills add claimed-framework/mlx","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add claimed-framework/mlx","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","11mo since push","Financial domain: human review is required before use in a live investment workflow."]},"agentCompatibility":["Python","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["devops","kubernetes","datasets","kubeflow-pipeline","machine-learning","mlx"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Documentation summary is thin"]},"safety":{"score":60,"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":["Documentation summary is thin","60/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"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":["Documentation summary is thin","60/100 agent safety score"]},"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":"data-analysis","title":"Data analysis"},{"slug":"sales-crm","title":"Sales and CRM"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add claimed-framework/mlx","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":220,"starsLabel":"220","forks":54,"license":"Apache-2.0","qualityScore":57,"trustScore":75,"auditScore":72},"maintenance":{"status":"stable","label":"11mo since push","daysSincePush":334,"lastPushedAt":"2025-09-22T10:04:35+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Needs review"]},"coverageTags":["Coding","Coding agents","devops","kubernetes","datasets","kubeflow-pipeline","machine-learning","mlx"]},"audit":{"audit_score":72,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"decision":{"readiness_score":47,"readiness_label":"Needs manual review","headline":"Needs validation for Data analysis","role":"Needs validation","primary_fit":"Data analysis","best_for":["Data analysis workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Data analysis 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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"claimed-framework-mlx","name":"Mlx","description":"Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine","category":"devops","url":"https://www.openagentskill.com/skills/claimed-framework-mlx","repository":"https://github.com/claimed-framework/mlx","github_repo":"claimed-framework/mlx"},"suited_tasks":["Data analysis workflows","general agent builders","builders willing to evaluate younger projects","Load tabular data","Calculate trends","Summarize findings clearly","Research accounts","Extract contact details"],"suited_agents":["Python","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add claimed-framework/mlx","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install claimed-framework-mlx"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx\" agent skill from https://github.com/claimed-framework/mlx. 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: Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"claimed-framework-mlx\",\"task\":\"Install Mlx\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx\" as a Claude Code skill from https://github.com/claimed-framework/mlx. 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: Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"claimed-framework-mlx\",\"task\":\"Install Mlx\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx\" from https://github.com/claimed-framework/mlx 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: Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"claimed-framework-mlx\",\"task\":\"Install Mlx\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/claimed-framework-mlx/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/claimed-framework-mlx"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"220 GitHub stars","repoActivity":"220 stars, 54 forks","lastPushed":"11mo since push","license":"Apache-2.0","repository":"https://github.com/claimed-framework/mlx","install":"npx skills add claimed-framework/mlx","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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","datasets","kubeflow-pipeline","machine-learning","mlx"],"known_risks":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Documentation summary is thin"]},"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":72,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","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."},"quality":{"score":57,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"11mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Mlx in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 72/100 Needs review","Safety: 60/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"claimed-framework-mlx (Mlx)","install_command":"npx skills add claimed-framework/mlx","risk_summary":"Needs review; Reviewed with permission notes; 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":"claimed-framework-mlx","task":"Use Mlx in an 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/claimed-framework-mlx","api":"https://www.openagentskill.com/api/agent/skills/claimed-framework-mlx","audit":"https://www.openagentskill.com/skills/claimed-framework-mlx/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=claimed-framework-mlx&task=Use%20Mlx%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/claimed-framework-mlx/install","manifest":"https://www.openagentskill.com/api/registry/manifest/claimed-framework-mlx"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"claimed-framework-mlx","name":"Mlx","description":"Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine","category":"devops","url":"https://www.openagentskill.com/skills/claimed-framework-mlx","repository":"https://github.com/claimed-framework/mlx","github_repo":"claimed-framework/mlx"},"suited_tasks":["Data analysis workflows","general agent builders","builders willing to evaluate younger projects","Load tabular data","Calculate trends","Summarize findings clearly","Research accounts","Extract contact details"],"suited_agents":["Python","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add claimed-framework/mlx","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install claimed-framework-mlx"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx\" agent skill from https://github.com/claimed-framework/mlx. 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: Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"claimed-framework-mlx\",\"task\":\"Install Mlx\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx\" as a Claude Code skill from https://github.com/claimed-framework/mlx. 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: Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"claimed-framework-mlx\",\"task\":\"Install Mlx\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx\" from https://github.com/claimed-framework/mlx 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: Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"claimed-framework-mlx\",\"task\":\"Install Mlx\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/claimed-framework-mlx/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/claimed-framework-mlx"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"220 GitHub stars","repoActivity":"220 stars, 54 forks","lastPushed":"11mo since push","license":"Apache-2.0","repository":"https://github.com/claimed-framework/mlx","install":"npx skills add claimed-framework/mlx","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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","datasets","kubeflow-pipeline","machine-learning","mlx"],"known_risks":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Documentation summary is thin"]},"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":72,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","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."},"quality":{"score":57,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"11mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Mlx in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 72/100 Needs review","Safety: 60/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"claimed-framework-mlx (Mlx)","install_command":"npx skills add claimed-framework/mlx","risk_summary":"Needs review; Reviewed with permission notes; 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":"claimed-framework-mlx","task":"Use Mlx in an 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/claimed-framework-mlx","api":"https://www.openagentskill.com/api/agent/skills/claimed-framework-mlx","audit":"https://www.openagentskill.com/skills/claimed-framework-mlx/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=claimed-framework-mlx&task=Use%20Mlx%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/claimed-framework-mlx/install","manifest":"https://www.openagentskill.com/api/registry/manifest/claimed-framework-mlx"}},"platforms":["Python","Kubernetes"],"use_cases":[{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"},{"slug":"sales-crm","title":"Sales and CRM","url":"https://www.openagentskill.com/use-cases/sales-crm"},{"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"}],"install":"npx skills add claimed-framework/mlx","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install claimed-framework-mlx","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Mlx\" agent skill from https://github.com/claimed-framework/mlx. 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: Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"claimed-framework-mlx\",\"task\":\"Install Mlx\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx\" as a Claude Code skill from https://github.com/claimed-framework/mlx. 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: Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"claimed-framework-mlx\",\"task\":\"Install Mlx\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx\" from https://github.com/claimed-framework/mlx 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: Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"claimed-framework-mlx\",\"task\":\"Install Mlx\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/claimed-framework/mlx","github_repo":"claimed-framework/mlx","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"claimed-framework/mlx","recommendation_reasons":["Matches task terms: mlx","Install handoff is available","Repository freshness signal is available","Registry match score 15"],"urls":{"web":"https://www.openagentskill.com/skills/claimed-framework-mlx","api":"https://www.openagentskill.com/api/agent/skills/claimed-framework-mlx","install_api":"https://www.openagentskill.com/api/skills/claimed-framework-mlx/install","audit":"https://www.openagentskill.com/skills/claimed-framework-mlx/audit","repository":"https://github.com/claimed-framework/mlx"}},{"rank":8,"match_type":"related","match_score":13,"raw_match_score":99.5,"semantic_relevance":30,"slug":"yeyupiaoling-whisper-finetune","name":"Whisper Finetune","description":"Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment","tagline":"Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment","category":"media-automation","tags":["speech-recognition","voice","ml-media","android","asr","chinese","ctranslate2","huggingface","lora","pytorch"],"author":{"name":"yeyupiaoling","verified":true,"url":"https://github.com/yeyupiaoling"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"yeyupiaoling/Whisper-Finetune","creatorName":"yeyupiaoling","creatorUrl":"https://github.com/yeyupiaoling","sourceUrl":"https://github.com/yeyupiaoling/Whisper-Finetune","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/yeyupiaoling-whisper-finetune#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":1216,"forks":219,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":56.3},"quality":{"score":92,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"1.2K","tone":"positive"},{"label":"Freshness","value":"4mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":86,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.2K stars, 219 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"4mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add yeyupiaoling/Whisper-Finetune"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/yeyupiaoling/Whisper-Finetune"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.2K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.2K stars, 219 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"4mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add yeyupiaoling/Whisper-Finetune"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/yeyupiaoling/Whisper-Finetune"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 219 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/yeyupiaoling/Whisper-Finetune","install":"npx skills add yeyupiaoling/Whisper-Finetune","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add yeyupiaoling/Whisper-Finetune","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","4mo since push"]},"agentCompatibility":["C","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["media-automation","speech-recognition","voice","ml-media","android","asr"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":75,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","75/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"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":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"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.","reasons":["Safe-to-try audit","75/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"local-desktop","title":"Local desktop"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","C"],"install":{"ready":true,"command":"npx skills add yeyupiaoling/Whisper-Finetune","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1216,"starsLabel":"1.2K","forks":219,"license":"Apache-2.0","qualityScore":92,"trustScore":86,"auditScore":87},"maintenance":{"status":"active","label":"4mo since push","daysSincePush":106,"lastPushedAt":"2026-05-08T01:23:47+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","media-automation","speech-recognition","voice","ml-media","android","asr"]},"audit":{"audit_score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Local desktop","role":"Primary pick","primary_fit":"Local desktop","best_for":["Local desktop workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"yeyupiaoling-whisper-finetune","name":"Whisper Finetune","description":"Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment","category":"media-automation","url":"https://www.openagentskill.com/skills/yeyupiaoling-whisper-finetune","repository":"https://github.com/yeyupiaoling/Whisper-Finetune","github_repo":"yeyupiaoling/Whisper-Finetune"},"suited_tasks":["Local desktop workflows","general agent builders","teams that value GitHub adoption signals","Navigate local resources","Run repeatable desktop actions","Verify file outputs","Navigate pages","Click and type safely"],"suited_agents":["C","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add yeyupiaoling/Whisper-Finetune","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install yeyupiaoling-whisper-finetune"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Whisper Finetune\" agent skill from https://github.com/yeyupiaoling/Whisper-Finetune. 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: Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yeyupiaoling-whisper-finetune\",\"task\":\"Install Whisper Finetune\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Whisper Finetune\" as a Claude Code skill from https://github.com/yeyupiaoling/Whisper-Finetune. 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: Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yeyupiaoling-whisper-finetune\",\"task\":\"Install Whisper Finetune\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Whisper Finetune\" from https://github.com/yeyupiaoling/Whisper-Finetune 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: Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yeyupiaoling-whisper-finetune\",\"task\":\"Install Whisper Finetune\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/yeyupiaoling-whisper-finetune/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/yeyupiaoling-whisper-finetune"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 219 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/yeyupiaoling/Whisper-Finetune","install":"npx skills add yeyupiaoling/Whisper-Finetune","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["media-automation","speech-recognition","voice","ml-media","android","asr"],"known_risks":["Documentation summary is thin"]},"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":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"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":92,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"4mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Whisper Finetune in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"yeyupiaoling-whisper-finetune (Whisper Finetune)","install_command":"npx skills add yeyupiaoling/Whisper-Finetune","risk_summary":"Safe to try; Reviewed; Low metadata risk","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":"yeyupiaoling-whisper-finetune","task":"Use Whisper Finetune in an 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/yeyupiaoling-whisper-finetune","api":"https://www.openagentskill.com/api/agent/skills/yeyupiaoling-whisper-finetune","audit":"https://www.openagentskill.com/skills/yeyupiaoling-whisper-finetune/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=yeyupiaoling-whisper-finetune&task=Use%20Whisper%20Finetune%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Whisper%20Finetune%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Whisper%20Finetune%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/yeyupiaoling-whisper-finetune/install","manifest":"https://www.openagentskill.com/api/registry/manifest/yeyupiaoling-whisper-finetune"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"yeyupiaoling-whisper-finetune","name":"Whisper Finetune","description":"Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment","category":"media-automation","url":"https://www.openagentskill.com/skills/yeyupiaoling-whisper-finetune","repository":"https://github.com/yeyupiaoling/Whisper-Finetune","github_repo":"yeyupiaoling/Whisper-Finetune"},"suited_tasks":["Local desktop workflows","general agent builders","teams that value GitHub adoption signals","Navigate local resources","Run repeatable desktop actions","Verify file outputs","Navigate pages","Click and type safely"],"suited_agents":["C","Speech","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add yeyupiaoling/Whisper-Finetune","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install yeyupiaoling-whisper-finetune"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Whisper Finetune\" agent skill from https://github.com/yeyupiaoling/Whisper-Finetune. 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: Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yeyupiaoling-whisper-finetune\",\"task\":\"Install Whisper Finetune\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Whisper Finetune\" as a Claude Code skill from https://github.com/yeyupiaoling/Whisper-Finetune. 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: Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yeyupiaoling-whisper-finetune\",\"task\":\"Install Whisper Finetune\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Whisper Finetune\" from https://github.com/yeyupiaoling/Whisper-Finetune 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: Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yeyupiaoling-whisper-finetune\",\"task\":\"Install Whisper Finetune\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/yeyupiaoling-whisper-finetune/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/yeyupiaoling-whisper-finetune"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 219 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/yeyupiaoling/Whisper-Finetune","install":"npx skills add yeyupiaoling/Whisper-Finetune","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["media-automation","speech-recognition","voice","ml-media","android","asr"],"known_risks":["Documentation summary is thin"]},"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":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"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":92,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"4mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Whisper Finetune in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"yeyupiaoling-whisper-finetune (Whisper Finetune)","install_command":"npx skills add yeyupiaoling/Whisper-Finetune","risk_summary":"Safe to try; Reviewed; Low metadata risk","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":"yeyupiaoling-whisper-finetune","task":"Use Whisper Finetune in an 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/yeyupiaoling-whisper-finetune","api":"https://www.openagentskill.com/api/agent/skills/yeyupiaoling-whisper-finetune","audit":"https://www.openagentskill.com/skills/yeyupiaoling-whisper-finetune/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=yeyupiaoling-whisper-finetune&task=Use%20Whisper%20Finetune%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Whisper%20Finetune%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Whisper%20Finetune%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/yeyupiaoling-whisper-finetune/install","manifest":"https://www.openagentskill.com/api/registry/manifest/yeyupiaoling-whisper-finetune"}},"platforms":["C","Speech"],"use_cases":[{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"}],"install":"npx skills add yeyupiaoling/Whisper-Finetune","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install yeyupiaoling-whisper-finetune","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Whisper Finetune\" agent skill from https://github.com/yeyupiaoling/Whisper-Finetune. 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: Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yeyupiaoling-whisper-finetune\",\"task\":\"Install Whisper Finetune\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Whisper Finetune\" as a Claude Code skill from https://github.com/yeyupiaoling/Whisper-Finetune. 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: Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yeyupiaoling-whisper-finetune\",\"task\":\"Install Whisper Finetune\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Whisper Finetune\" from https://github.com/yeyupiaoling/Whisper-Finetune 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: Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yeyupiaoling-whisper-finetune\",\"task\":\"Install Whisper Finetune\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/yeyupiaoling/Whisper-Finetune","github_repo":"yeyupiaoling/Whisper-Finetune","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"yeyupiaoling/whisper-finetune","recommendation_reasons":["Matches task terms: tune","Useful GitHub adoption: 1,216 stars","Install handoff is available","Repository freshness signal is available","Registry match score 13"],"urls":{"web":"https://www.openagentskill.com/skills/yeyupiaoling-whisper-finetune","api":"https://www.openagentskill.com/api/agent/skills/yeyupiaoling-whisper-finetune","install_api":"https://www.openagentskill.com/api/skills/yeyupiaoling-whisper-finetune/install","audit":"https://www.openagentskill.com/skills/yeyupiaoling-whisper-finetune/audit","repository":"https://github.com/yeyupiaoling/Whisper-Finetune"}},{"rank":9,"match_type":"related","match_score":12,"raw_match_score":91.2,"semantic_relevance":30,"slug":"jjang-ai-mlxstudio","name":"Mlxstudio","description":"MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)","tagline":"MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)","category":"agent-frameworks","tags":["agents","ai-agents","ai","anthropic","anthropic-api","apple-silicon","inference","inference-engine","llm","lmstudio"],"author":{"name":"jjang-ai","verified":false,"url":"https://github.com/jjang-ai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"jjang-ai/mlxstudio","creatorName":"jjang-ai","creatorUrl":"https://github.com/jjang-ai","sourceUrl":"https://github.com/jjang-ai/mlxstudio","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/jjang-ai-mlxstudio#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":778,"forks":49,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":50.94},"quality":{"score":69,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"778","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":76,"weight":0.13,"status":"info","detail":"778 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":65,"weight":0.08,"status":"info","detail":"778 stars, 49 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add jjang-ai/mlxstudio"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/jjang-ai/mlxstudio"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"778 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"778 stars, 49 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add jjang-ai/mlxstudio"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/jjang-ai/mlxstudio"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"778 GitHub stars","repoActivity":"778 stars, 49 forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/jjang-ai/mlxstudio","install":"npx skills add jjang-ai/mlxstudio","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add jjang-ai/mlxstudio","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["agent-frameworks","agents","ai-agents","ai","anthropic","anthropic-api"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":65,"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":["License is unclear","65/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"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":["License is unclear","65/100 agent safety score"]},"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":"multimodal-media","title":"Multimodal media"},{"slug":"local-desktop","title":"Local desktop"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","AI Agents"],"install":{"ready":true,"command":"npx skills add jjang-ai/mlxstudio","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":778,"starsLabel":"778","forks":49,"license":"Unknown","qualityScore":69,"trustScore":75,"auditScore":77},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":71,"lastPushedAt":"2026-06-12T00:32:50+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","Needs review"]},"coverageTags":["Coding","Coding agents","agent-frameworks","agents","ai-agents","ai","anthropic","anthropic-api"]},"audit":{"audit_score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown"]},"decision":{"readiness_score":80,"readiness_label":"Strong shortlist","headline":"Companion skill for Coding agents","role":"Companion skill","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"jjang-ai-mlxstudio","name":"Mlxstudio","description":"MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/jjang-ai-mlxstudio","repository":"https://github.com/jjang-ai/mlxstudio","github_repo":"jjang-ai/mlxstudio"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Read media metadata","Convert formats"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add jjang-ai/mlxstudio","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install jjang-ai-mlxstudio"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlxstudio\" agent skill from https://github.com/jjang-ai/mlxstudio. 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: MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jjang-ai-mlxstudio\",\"task\":\"Install Mlxstudio\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlxstudio\" as a Claude Code skill from https://github.com/jjang-ai/mlxstudio. 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: MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jjang-ai-mlxstudio\",\"task\":\"Install Mlxstudio\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlxstudio\" from https://github.com/jjang-ai/mlxstudio 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: MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jjang-ai-mlxstudio\",\"task\":\"Install Mlxstudio\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/jjang-ai-mlxstudio/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/jjang-ai-mlxstudio"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"778 GitHub stars","repoActivity":"778 stars, 49 forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/jjang-ai/mlxstudio","install":"npx skills add jjang-ai/mlxstudio","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","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":["agent-frameworks","agents","ai-agents","ai","anthropic","anthropic-api"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","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."},"quality":{"score":69,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Mlxstudio in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"jjang-ai-mlxstudio (Mlxstudio)","install_command":"npx skills add jjang-ai/mlxstudio","risk_summary":"Needs review; Reviewed with permission notes; 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":"jjang-ai-mlxstudio","task":"Use Mlxstudio in an 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/jjang-ai-mlxstudio","api":"https://www.openagentskill.com/api/agent/skills/jjang-ai-mlxstudio","audit":"https://www.openagentskill.com/skills/jjang-ai-mlxstudio/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jjang-ai-mlxstudio&task=Use%20Mlxstudio%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlxstudio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlxstudio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/jjang-ai-mlxstudio/install","manifest":"https://www.openagentskill.com/api/registry/manifest/jjang-ai-mlxstudio"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"jjang-ai-mlxstudio","name":"Mlxstudio","description":"MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/jjang-ai-mlxstudio","repository":"https://github.com/jjang-ai/mlxstudio","github_repo":"jjang-ai/mlxstudio"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Read media metadata","Convert formats"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add jjang-ai/mlxstudio","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install jjang-ai-mlxstudio"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlxstudio\" agent skill from https://github.com/jjang-ai/mlxstudio. 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: MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jjang-ai-mlxstudio\",\"task\":\"Install Mlxstudio\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlxstudio\" as a Claude Code skill from https://github.com/jjang-ai/mlxstudio. 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: MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jjang-ai-mlxstudio\",\"task\":\"Install Mlxstudio\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlxstudio\" from https://github.com/jjang-ai/mlxstudio 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: MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jjang-ai-mlxstudio\",\"task\":\"Install Mlxstudio\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/jjang-ai-mlxstudio/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/jjang-ai-mlxstudio"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"778 GitHub stars","repoActivity":"778 stars, 49 forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/jjang-ai/mlxstudio","install":"npx skills add jjang-ai/mlxstudio","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","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":["agent-frameworks","agents","ai-agents","ai","anthropic","anthropic-api"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","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."},"quality":{"score":69,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Mlxstudio in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"jjang-ai-mlxstudio (Mlxstudio)","install_command":"npx skills add jjang-ai/mlxstudio","risk_summary":"Needs review; Reviewed with permission notes; 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":"jjang-ai-mlxstudio","task":"Use Mlxstudio in an 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/jjang-ai-mlxstudio","api":"https://www.openagentskill.com/api/agent/skills/jjang-ai-mlxstudio","audit":"https://www.openagentskill.com/skills/jjang-ai-mlxstudio/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jjang-ai-mlxstudio&task=Use%20Mlxstudio%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlxstudio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlxstudio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/jjang-ai-mlxstudio/install","manifest":"https://www.openagentskill.com/api/registry/manifest/jjang-ai-mlxstudio"}},"platforms":["AI Agents","Claude Code"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"install":"npx skills add jjang-ai/mlxstudio","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install jjang-ai-mlxstudio","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Mlxstudio\" agent skill from https://github.com/jjang-ai/mlxstudio. 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: MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jjang-ai-mlxstudio\",\"task\":\"Install Mlxstudio\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlxstudio\" as a Claude Code skill from https://github.com/jjang-ai/mlxstudio. 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: MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jjang-ai-mlxstudio\",\"task\":\"Install Mlxstudio\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlxstudio\" from https://github.com/jjang-ai/mlxstudio 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: MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jjang-ai-mlxstudio\",\"task\":\"Install Mlxstudio\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/jjang-ai/mlxstudio","github_repo":"jjang-ai/mlxstudio","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"jjang-ai/mlxstudio","recommendation_reasons":["Matches task terms: mlx","Useful GitHub adoption: 778 stars","Install handoff is available","Repository freshness signal is available","Registry match score 12"],"urls":{"web":"https://www.openagentskill.com/skills/jjang-ai-mlxstudio","api":"https://www.openagentskill.com/api/agent/skills/jjang-ai-mlxstudio","install_api":"https://www.openagentskill.com/api/skills/jjang-ai-mlxstudio/install","audit":"https://www.openagentskill.com/skills/jjang-ai-mlxstudio/audit","repository":"https://github.com/jjang-ai/mlxstudio"}},{"rank":10,"match_type":"related","match_score":12,"raw_match_score":88.3,"semantic_relevance":30,"slug":"blaizzy-mlx-embeddings","name":"Mlx Embeddings","description":"MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.","tagline":"MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.","category":"support-automation","tags":["chatbot","support","automation","customer-support","embeddings","llms","rag","retrieval-augmented-generation","python","github"],"author":{"name":"Blaizzy","verified":false,"url":"https://github.com/Blaizzy"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"Blaizzy/mlx-embeddings","creatorName":"Blaizzy","creatorUrl":"https://github.com/Blaizzy","sourceUrl":"https://github.com/Blaizzy/mlx-embeddings","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/blaizzy-mlx-embeddings#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":404,"forks":54,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":44.95},"quality":{"score":62,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"404","tone":"neutral"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":74,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"404 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"404 stars, 54 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Blaizzy/mlx-embeddings"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Blaizzy/mlx-embeddings"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"404 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"404 stars, 54 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Blaizzy/mlx-embeddings"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Blaizzy/mlx-embeddings"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"404 GitHub stars","repoActivity":"404 stars, 54 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/Blaizzy/mlx-embeddings","install":"npx skills add Blaizzy/mlx-embeddings","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add Blaizzy/mlx-embeddings","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["Python","Chatbot","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["support-automation","chatbot","support","automation","customer-support","embeddings"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":62,"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":["License is unclear","62/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"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":["License is unclear","62/100 agent safety score"]},"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":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"customer-support","title":"Customer support"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Blaizzy/mlx-embeddings","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":404,"starsLabel":"404","forks":54,"license":"Unknown","qualityScore":62,"trustScore":74,"auditScore":74},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":100,"lastPushedAt":"2026-05-13T19:55:12+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","Needs review"]},"coverageTags":["Coding","GitHub automation","support-automation","chatbot","support","automation","customer-support","embeddings"]},"audit":{"audit_score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown"]},"decision":{"readiness_score":61,"readiness_label":"Prototype first","headline":"Fallback candidate for RAG and knowledge","role":"Fallback candidate","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge 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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"blaizzy-mlx-embeddings","name":"Mlx Embeddings","description":"MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.","category":"support-automation","url":"https://www.openagentskill.com/skills/blaizzy-mlx-embeddings","repository":"https://github.com/Blaizzy/mlx-embeddings","github_repo":"Blaizzy/mlx-embeddings"},"suited_tasks":["RAG and knowledge workflows","general agent builders","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Chatbot","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Blaizzy/mlx-embeddings","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install blaizzy-mlx-embeddings"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Embeddings\" agent skill from https://github.com/Blaizzy/mlx-embeddings. 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: MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-embeddings\",\"task\":\"Install Mlx Embeddings\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Embeddings\" as a Claude Code skill from https://github.com/Blaizzy/mlx-embeddings. 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: MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-embeddings\",\"task\":\"Install Mlx Embeddings\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Embeddings\" from https://github.com/Blaizzy/mlx-embeddings 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: MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-embeddings\",\"task\":\"Install Mlx Embeddings\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/blaizzy-mlx-embeddings/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-embeddings"},"trust":{"score":74,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"404 GitHub stars","repoActivity":"404 stars, 54 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/Blaizzy/mlx-embeddings","install":"npx skills add Blaizzy/mlx-embeddings","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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":["support-automation","chatbot","support","automation","customer-support","embeddings"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","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."},"quality":{"score":62,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Mlx Embeddings in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 74/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"blaizzy-mlx-embeddings (Mlx Embeddings)","install_command":"npx skills add Blaizzy/mlx-embeddings","risk_summary":"Needs review; Reviewed with permission notes; 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":"blaizzy-mlx-embeddings","task":"Use Mlx Embeddings in an 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/blaizzy-mlx-embeddings","api":"https://www.openagentskill.com/api/agent/skills/blaizzy-mlx-embeddings","audit":"https://www.openagentskill.com/skills/blaizzy-mlx-embeddings/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=blaizzy-mlx-embeddings&task=Use%20Mlx%20Embeddings%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Embeddings%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Embeddings%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/blaizzy-mlx-embeddings/install","manifest":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-embeddings"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"blaizzy-mlx-embeddings","name":"Mlx Embeddings","description":"MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.","category":"support-automation","url":"https://www.openagentskill.com/skills/blaizzy-mlx-embeddings","repository":"https://github.com/Blaizzy/mlx-embeddings","github_repo":"Blaizzy/mlx-embeddings"},"suited_tasks":["RAG and knowledge workflows","general agent builders","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Chatbot","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Blaizzy/mlx-embeddings","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install blaizzy-mlx-embeddings"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mlx Embeddings\" agent skill from https://github.com/Blaizzy/mlx-embeddings. 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: MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-embeddings\",\"task\":\"Install Mlx Embeddings\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mlx Embeddings\" as a Claude Code skill from https://github.com/Blaizzy/mlx-embeddings. 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: MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-embeddings\",\"task\":\"Install Mlx Embeddings\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mlx Embeddings\" from https://github.com/Blaizzy/mlx-embeddings 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: MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-embeddings\",\"task\":\"Install Mlx Embeddings\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/blaizzy-mlx-embeddings/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-embeddings"},"trust":{"score":74,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"404 GitHub stars","repoActivity":"404 stars, 54 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/Blaizzy/mlx-embeddings","install":"npx skills add Blaizzy/mlx-embeddings","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","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":["support-automation","chatbot","support","automation","customer-support","embeddings"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"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":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","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."},"quality":{"score":62,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Mlx Embeddings in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 74/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"blaizzy-mlx-embeddings (Mlx Embeddings)","install_command":"npx skills add Blaizzy/mlx-embeddings","risk_summary":"Needs review; Reviewed with permission notes; 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":"blaizzy-mlx-embeddings","task":"Use Mlx Embeddings in an 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/blaizzy-mlx-embeddings","api":"https://www.openagentskill.com/api/agent/skills/blaizzy-mlx-embeddings","audit":"https://www.openagentskill.com/skills/blaizzy-mlx-embeddings/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=blaizzy-mlx-embeddings&task=Use%20Mlx%20Embeddings%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mlx%20Embeddings%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mlx%20Embeddings%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/blaizzy-mlx-embeddings/install","manifest":"https://www.openagentskill.com/api/registry/manifest/blaizzy-mlx-embeddings"}},"platforms":["Python","Chatbot"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"customer-support","title":"Customer support","url":"https://www.openagentskill.com/use-cases/customer-support"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"install":"npx skills add Blaizzy/mlx-embeddings","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install blaizzy-mlx-embeddings","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Mlx Embeddings\" agent skill from https://github.com/Blaizzy/mlx-embeddings. 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: MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-embeddings\",\"task\":\"Install Mlx Embeddings\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Embeddings\" as a Claude Code skill from https://github.com/Blaizzy/mlx-embeddings. 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: MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-embeddings\",\"task\":\"Install Mlx Embeddings\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","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 \"Mlx Embeddings\" from https://github.com/Blaizzy/mlx-embeddings 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: MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"blaizzy-mlx-embeddings\",\"task\":\"Install Mlx Embeddings\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/Blaizzy/mlx-embeddings","github_repo":"Blaizzy/mlx-embeddings","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"blaizzy/mlx-embeddings","recommendation_reasons":["Matches task terms: mlx","Install handoff is available","Repository freshness signal is available","Registry match score 12"],"urls":{"web":"https://www.openagentskill.com/skills/blaizzy-mlx-embeddings","api":"https://www.openagentskill.com/api/agent/skills/blaizzy-mlx-embeddings","install_api":"https://www.openagentskill.com/api/skills/blaizzy-mlx-embeddings/install","audit":"https://www.openagentskill.com/skills/blaizzy-mlx-embeddings/audit","repository":"https://github.com/Blaizzy/mlx-embeddings"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","lookup_intent":false,"exact_match_found":true,"match_counts":{"exact":1,"near":0,"related":9},"no_match_message":null,"safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-08-22T14:37:48.510Z"}}