{"slug":"code-yeongyu-eval-integrity","source_name":"code-yeongyu/eval-integrity","name":"Code Yeongyu/Eval Integrity","description":"Assess integrity of an eval, benchmark, metric, A/B test, holdout, LLM-judge, or user-study claim when the question is whether measurement, comparison, or evidence is independent and trustworthy.","version":1,"lift":{"pass_rate_delta_pts":4.55,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":46.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-11-05T12:57:54.000816+00:00"},"skill_score":0.8182,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":4.55,"with_pass_pct":81.8,"without_pass_pct":77.3,"tokens_delta_pct":46.5,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-11-05T12:57:54.000816+00:00","run_id":"14948c1c-6a73-4dd8-818b-75145efb1145","latest_attempt":{"id":"14948c1c-6a73-4dd8-818b-75145efb1145","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-11-05T12:57:54.000816+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":"NOASSERTION","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"18d822ca0ae262e6256b5d25cb950eaca2a4a327eeff6448a1339f9ccfdce390","install_name":"code-yeongyu-eval-integrity","version_id":"a003d627-5e84-4654-899b-95fad17d4eea","body_sha256":"18d822ca0ae262e6256b5d25cb950eaca2a4a327eeff6448a1339f9ccfdce390","render_hash":"8e399d8f0a5dde3faac749ff641442fa37c240f595e6ed360962e71a856f73f9","raw_url":"https://app.decimal.ai/s/code-yeongyu-eval-integrity/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/code-yeongyu-eval-integrity"}