{"slug":"majiayu000-agentic-eval","source_name":"majiayu000/agentic-eval","name":"Majiayu000/Agentic Eval","description":"Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when implementing self-critique and reflection loops, building evaluator-optimizer pipelines for quality-critical generation, creating test-driven code refinement workflows, designing rubric-based or LLM-as-judge evaluation systems, adding iterative improvement to agent outputs (code, reports, analysis), and measuring agent response quality.","version":1,"lift":{"pass_rate_delta_pts":40.91,"pass_rate_pct":77.3,"total_cases":22,"passed_cases":17,"tokens_delta_pct":46,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-03T20:28:02.243682+00:00"},"skill_score":0.7727,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":40.91,"with_pass_pct":77.3,"without_pass_pct":36.4,"tokens_delta_pct":46,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-03T20:28:02.243682+00:00","run_id":"861a899d-dbd9-4f87-9cce-c33306b6908a","latest_attempt":{"id":"861a899d-dbd9-4f87-9cce-c33306b6908a","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-09-03T20:28:02.243682+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":"a511e1fcb03ecd9c81d718d0c9ce3c025ca2ce6b4619e9d44da44959c32b0a7c","install_name":"majiayu000-agentic-eval","version_id":"fb63e28f-598d-4517-9603-fed50c6a7400","body_sha256":"a511e1fcb03ecd9c81d718d0c9ce3c025ca2ce6b4619e9d44da44959c32b0a7c","render_hash":"f8bbd7c88cd32b286b282633d352f8feb4b253887b1c5270d53ad9202bc5483a","raw_url":"https://app.decimal.ai/s/majiayu000-agentic-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/majiayu000-agentic-eval"}