{"id":"cmuxhww1a0fqqad07c2axbv8r","slug":"fine-tuning-with-trl","publicId":"3b38448f-e3c3-47fe-aabb-504f8df8e74b","name":"trl-fine-tuning","description":"TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.","version":"1.0.1","author":"Orchestra Research","license":"MIT","compatibility":"","status":"completed","overallGrade":"B","scannerVersion":11,"fileCount":7,"hasSkillMd":true,"hasScripts":false,"hasReferences":true,"hasEvals":false,"hasAssets":false,"sourceType":"github","sourceUrl":"https://github.com/NousResearch/hermes-agent/tree/main/optional-skills/mlops/training/trl-fine-tuning","createdAt":"2026-10-07T02:35:51.903Z","completedAt":"2026-10-07T02:35:51.901Z","visibility":"public","publishedAt":"2026-07-29T11:30:40.410Z","category":"","frameworks":[],"badgeStatus":"conditional","downloadCount":0,"verdictRationale":{"summary":"Skill has warnings: 1 warning in security or structure checks.","verdict":"warn","scanners":[{"source":"vettd","weight":1,"verdict":"warn"},{"source":"cisco","weight":0.8,"verdict":"pass"}],"consensus":"warn","warnTriggers":["References external URL — review for indirect prompt injection risk"],"policyVersion":"consensus-v1","hardFailTriggers":[]},"verdictPolicyVersion":"consensus-v1","skillId":"cmsq52wsb0j9gad09lyoxu8ne","findings":[{"id":"cmuxhww1a0fqrad07xz52uzfc","source":"vettd","category":"security","label":"References external URL — review for indirect prompt injection risk","detail":"External URL(s) detected in SKILL.md — referenced content can change after audit","severity":"medium","ruleId":"VTD-0088","owaspLlmCategory":null,"intent":null,"chainId":null,"fingerprint":"42638a8b7e9fc5df27449992eaebc724","filepath":"SKILL.md"}],"scannerRuns":[{"source":"cisco","status":"success","verdict":null,"grade":"A","findingCount":0,"criticalCount":0,"highCount":0},{"source":"vettd","status":"success","verdict":null,"grade":"B","findingCount":1,"criticalCount":0,"highCount":0}],"user":{"name":"Justin Pacella","image":"https://avatars.githubusercontent.com/u/97124458?v=4"},"repository":{"owner":"NousResearch","name":"hermes-agent"},"freshness":{"status":"verified_unchanged","reason":null,"retryable":false,"renamedTo":null,"lastCheckedAt":"2026-10-21T17:05:41.141Z","lastVerifiedAt":"2026-10-21T17:05:41.141Z","lastChangeDetectedAt":"2026-08-25T11:23:23.462Z","scannedHash":"c38a9b42d635606f154fafc450859cfe6182da83","latestUpstreamHash":"c38a9b42d635606f154fafc450859cfe6182da83","nextCheckDueAt":"2026-10-22T18:01:26.969Z"},"signalCategories":[{"category":"safety","label":"Safety","form":"graded","verdict":null,"rows":[]},{"category":"reliability","label":"Reliability & Quality","form":"graded","verdict":null,"rows":[]},{"category":"performance","label":"Performance","form":"measured","verdict":{"form":"measured","magnitudes":[{"ruleId":"performance/static-context-tokens","label":"Static context tokens","value":3499,"unit":null,"method":"tiktoken/cl100k_base/skill-md-body"}]},"rows":[{"origin":"signal","id":"cmuxhwwvb0fxtad07p1clk842","subjectType":"skill_audit","subjectId":"cmuxhww1a0fqqad07c2axbv8r","relatedType":"","relatedId":"","dataCategory":"performance","sourceClass":"scan","source":"vettd","ruleId":"performance/progressive-disclosure","severity":null,"label":"Progressive disclosure","detail":null,"valueNum":null,"valueText":"present","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T02:35:49.000Z","payload":null},{"origin":"signal","id":"cmuxhww9i0fslad074t6sp539","subjectType":"skill_audit","subjectId":"cmuxhww1a0fqqad07c2axbv8r","relatedType":"","relatedId":"","dataCategory":"performance","sourceClass":"scan","source":"vettd","ruleId":"performance/static-context-tokens","severity":null,"label":"Static context tokens","detail":null,"valueNum":3499,"valueText":null,"unit":null,"method":"tiktoken/cl100k_base/skill-md-body","derivation":null,"confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T02:35:49.000Z","payload":null}]},{"category":"cost","label":"Cost","form":"measured","verdict":null,"rows":[]},{"category":"compatibility","label":"Compatibility","form":"unjudged","verdict":{"form":"unjudged"},"rows":[{"origin":"signal","id":"cmuxhwwc30ft6ad078ux5i0j3","subjectType":"skill_audit","subjectId":"cmuxhww1a0fqqad07c2axbv8r","relatedType":"","relatedId":"","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-environment-assumptions","severity":null,"label":"Declared environment assumptions","detail":null,"valueNum":null,"valueText":"","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T02:35:49.000Z","payload":null},{"origin":"signal","id":"cmuxhwwkb0fv7ad07uw4hx1f1","subjectType":"skill_audit","subjectId":"cmuxhww1a0fqqad07c2axbv8r","relatedType":"","relatedId":"","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-name","severity":null,"label":"Declared skill name","detail":null,"valueNum":null,"valueText":"trl-fine-tuning","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T02:35:49.000Z","payload":null}]},{"category":"sentiment","label":"Popularity","form":"unjudged","verdict":null,"rows":[]},{"category":"characteristics","label":"Characteristics","form":"unjudged","verdict":null,"rows":[]}],"signalCount":24,"publisherSupplied":["name","description","author","version","license"]}