{"slug":"hashgraph-online-eval-regression","source_name":"hashgraph-online/eval-regression","name":"Hashgraph Online/Eval Regression","description":"Use when the user asks to check a plugin or skill with behavioral evals, compare it with HEAD, or investigate a behavioral regression.","version":1,"lift":{"pass_rate_delta_pts":58.33,"pass_rate_pct":75,"total_cases":24,"passed_cases":18,"tokens_delta_pct":-27.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-02T05:50:11.132604+00:00"},"skill_score":0.7500000000000001,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":58.33,"with_pass_pct":75,"without_pass_pct":16.7,"tokens_delta_pct":-27.2,"turns_delta_pct":0,"total_cases":24,"cases_aggregated":19,"verdict":"mixed","never_hurt":false,"completed_at":"2026-09-02T05:50:11.132604+00:00","run_id":"b6eb2c56-7140-4a83-bb6b-d472309cfd71","latest_attempt":{"id":"b6eb2c56-7140-4a83-bb6b-d472309cfd71","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-09-02T05:50:11.132604+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":"Apache-2.0","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"c227014a687e93de1c060785713943203a2a3fe079ca78ddd5a135c674ac2628","install_name":"hashgraph-online-eval-regression","version_id":"84f9fcb5-4434-46ec-b2bd-9a66fb9dc003","body_sha256":"c227014a687e93de1c060785713943203a2a3fe079ca78ddd5a135c674ac2628","render_hash":"4c7b2918b3a855ebd318f4c6f30e3c68aa4244582247411ef24751e6aa1b00b3","raw_url":"https://app.decimal.ai/s/hashgraph-online-eval-regression/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/hashgraph-online-eval-regression"}