{"slug":"hoangsonww-benchmark","source_name":"hoangsonww/benchmark","name":"Hoangsonww/Benchmark","description":"Benchmark one session (or a small recent set) against the rolling average using Agent Monitor data — cost, total tokens, tool count, and workflow complexity score — and report where each metric lands as a percentile of the population. Tells you whether a session was normal, cheap, or an outlier. Use when judging whether a session was typical or out of band.","version":1,"lift":{"pass_rate_delta_pts":39.13,"pass_rate_pct":78.3,"total_cases":23,"passed_cases":18,"tokens_delta_pct":19.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-15T22:54:55.766774+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":39.13,"with_pass_pct":78.3,"without_pass_pct":39.1,"tokens_delta_pct":19.5,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":18,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-15T22:54:55.766774+00:00","run_id":"da3a4cb4-e78c-44ad-8538-09404f092e28","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,"manifest_hash":"94769d067d0d221d5af7315d2a527793046de7f05dbe6de2b3d4f1d6fca6eadf","raw_url":"https://app.decimal.ai/s/hoangsonww-benchmark/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/hoangsonww-benchmark"}