{"slug":"sickn33-hugging-face-evaluation","source_name":"sickn33/hugging-face-evaluation","name":"Sickn33/Hugging Face Evaluation","description":"Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.","version":2,"lift":{"pass_rate_delta_pts":59.09,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":216,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-29T02:26:22.737003+00:00"},"skill_score":0.8182,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":59.09,"with_pass_pct":81.8,"without_pass_pct":22.7,"tokens_delta_pct":216,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":19,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-29T02:26:22.737003+00:00","run_id":"421070cb-8a83-4297-92d7-1f8457651987","version_number":1,"is_latest_version":false,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":null,"content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"cde3e7c3a14b603feac302cf83e98b142e9cf3216285011c9430f913a2dfed57","raw_url":"https://app.decimal.ai/s/sickn33-hugging-face-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/sickn33-hugging-face-evaluation"}