{"slug":"prism-shadow-benchmark-design","source_name":"prism-shadow/benchmark-design","name":"Prism Shadow/Benchmark Design","description":"Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.","version":1,"lift":{"pass_rate_delta_pts":34.78,"pass_rate_pct":69.6,"total_cases":23,"passed_cases":16,"tokens_delta_pct":173.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-30T11:11:09.061440+00:00"},"skill_score":0.6957,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":34.78,"with_pass_pct":69.6,"without_pass_pct":34.8,"tokens_delta_pct":173.9,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":19,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-30T11:11:09.061440+00:00","run_id":"abf0e948-41af-4906-8285-bf4bda4a6455","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":"e7da32b2765c1992a6c2e8d3db33db9f996e8ece8db6656efc5654e23d7be564","raw_url":"https://app.decimal.ai/s/prism-shadow-benchmark-design/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/prism-shadow-benchmark-design"}