{"slug":"majiayu000-ai-evaluation-suite","source_name":"majiayu000/ai-evaluation-suite","name":"Majiayu000/AI Evaluation Suite","description":"Comprehensive AI/LLM evaluation toolkit for production AI systems. Covers LLM output quality, prompt engineering, RAG evaluation, agent performance, hallucination detection, bias assessment, cost/token optimization, latency metrics, model comparison, and fine-tuning evaluation. Includes BLEU/ROUGE metrics, perplexity, F1 scores, LLM-as-judge patterns, and benchmarks like MMLU and HumanEval.","version":1,"lift":{"pass_rate_delta_pts":27.27,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":97.8,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-03T20:51:37.686810+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":27.27,"with_pass_pct":90.9,"without_pass_pct":63.6,"tokens_delta_pct":97.8,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-03T20:51:37.686810+00:00","run_id":"785fc74c-63ba-4347-bbc0-163a231af6c2","latest_attempt":{"id":"785fc74c-63ba-4347-bbc0-163a231af6c2","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-09-03T20:51:37.686810+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":96,"total_users":4,"manifest_hash":"73c385219834d22e99881e8ab323f710e4d4f3e71547729aeb48db67afef7635","install_name":"majiayu000-ai-evaluation-suite","version_id":"36d42cd4-3306-495d-8e47-e0b19eb505b0","body_sha256":"73c385219834d22e99881e8ab323f710e4d4f3e71547729aeb48db67afef7635","render_hash":"1fb4dec196a28c1bc9afa5ce4ce76b8b8aad051f79292aff3c00e3f775e02bd3","raw_url":"https://app.decimal.ai/s/majiayu000-ai-evaluation-suite/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/majiayu000-ai-evaluation-suite"}