{"slug":"prism-shadow-agent-evaluation","source_name":"prism-shadow/agent-evaluation","name":"Prism Shadow/Agent Evaluation","description":"Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.","version":1,"lift":{"pass_rate_delta_pts":-5.88,"pass_rate_pct":30.4,"total_cases":23,"passed_cases":7,"tokens_delta_pct":73.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-30T11:12:15.118300+00:00"},"skill_score":0.9348,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":-5.88,"with_pass_pct":47.1,"without_pass_pct":52.9,"tokens_delta_pct":73.3,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":20,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-30T11:12:15.118300+00:00","run_id":"afe7d0be-5e8e-4d36-bc68-d36beefa73c2","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":"Apache-2.0","install_count":0,"manifest_hash":"38f0132bc0d527c91e8fd0d82d0d352612e860070e6082eaea9c0e8efa940640","raw_url":"https://app.decimal.ai/s/prism-shadow-agent-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/prism-shadow-agent-evaluation"}