{"slug":"majiayu000-build-your-evaluation-skill","source_name":"majiayu000/build-your-evaluation-skill","name":"Majiayu000/Build Your Evaluation Skill","description":"Create a reusable skill for evaluating fine-tuned models, benchmarking performance, and detecting quality regressions","version":1,"lift":{"pass_rate_delta_pts":31.82,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":45.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-03T20:10:47.528181+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":31.82,"with_pass_pct":90.9,"without_pass_pct":59.1,"tokens_delta_pct":45.3,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-03T20:10:47.528181+00:00","run_id":"55307f5b-d137-4c25-a1b5-31fe146ab24d","latest_attempt":{"id":"55307f5b-d137-4c25-a1b5-31fe146ab24d","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-09-03T20:10:47.528181+00:00","gate":null},"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":"MIT","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"20707dfafb3ab788c1fdf2c54b4b407d4503fb20c221d01a113e56813c22d593","install_name":"majiayu000-build-your-evaluation-skill","version_id":"32f5433f-46a0-46af-a502-2ccb6734b514","body_sha256":"20707dfafb3ab788c1fdf2c54b4b407d4503fb20c221d01a113e56813c22d593","render_hash":"a3317ad1acf078875d906d83e3275bbd23484e604eb596e9caa5ba0de4951d70","raw_url":"https://app.decimal.ai/s/majiayu000-build-your-evaluation-skill/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/majiayu000-build-your-evaluation-skill"}