{"slug":"miosa-osa-eval-audit","source_name":"miosa-osa/eval-audit","name":"Miosa Osa/Eval Audit","description":"Audit an LLM evaluation pipeline for correctness, coverage, and reliability. 6 diagnostic areas with structured Check/Finding output. Produces prioritized findings by severity and recommends next skills to run. Catches common eval pitfalls before they corrupt your metrics. Triggers on: \"eval audit\", \"audit evals\", \"evaluation audit\", \"check eval pipeline\", \"eval health\"","version":1,"lift":{"pass_rate_delta_pts":34.78,"pass_rate_pct":78.3,"total_cases":23,"passed_cases":18,"tokens_delta_pct":0.4,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-27T09:08:40.321916+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":34.78,"with_pass_pct":78.3,"without_pass_pct":43.5,"tokens_delta_pct":0.4,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":21,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-27T09:08:40.321916+00:00","run_id":"ff15c810-ea49-4b35-83f5-4bda4433b0a6","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":null,"install_count":0,"manifest_hash":"a204b81503e6a11560d68d45d387f90b138f3a1bdcb71eb52b2bb36f6ffa89c4","raw_url":"https://app.decimal.ai/s/miosa-osa-eval-audit/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/miosa-osa-eval-audit"}