{"slug":"vally-eval","source_name":"vally-eval","name":"Vally Eval","description":"Author, validate, and run Vally eval.yaml evaluation suites for agent skills. TRIGGERS: create eval, write eval, add eval, run eval, validate eval, vally eval, eval.yaml, add stimulus, map test to eval, migrate test to eval, eval graders, eval scoring.","version":2,"lift":{"pass_rate_delta_pts":78.26,"pass_rate_pct":95.7,"total_cases":23,"passed_cases":22,"tokens_delta_pct":13.4,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-02T15:09:02.725158+00:00"},"skill_score":0.9565000000000001,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":78.26,"with_pass_pct":95.7,"without_pass_pct":17.4,"tokens_delta_pct":13.4,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-02T15:09:02.725158+00:00","run_id":"4fcc2aea-8bc0-4db0-9c7a-f515e58ba2c5","latest_attempt":{"id":"4fcc2aea-8bc0-4db0-9c7a-f515e58ba2c5","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-08-02T15:09:02.725158+00:00","gate":null},"version_number":2,"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":"2f5f7238e38fcf04ff133d8c5e190c263aa3f4c4d84c44f1ec5cc3a41856d24c","install_name":"vally-eval","version_id":"edfe835a-1e8b-4c9f-ade9-a87470225547","body_sha256":"2f5f7238e38fcf04ff133d8c5e190c263aa3f4c4d84c44f1ec5cc3a41856d24c","render_hash":"37dd6b35d7426f03f0b48eb2fbc03b0e33c325843f7edb692c3b2c02557d5e12","raw_url":"https://app.decimal.ai/s/vally-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/vally-eval"}