{"slug":"hashgraph-online-eval-harness","source_name":"hashgraph-online/eval-harness","name":"Hashgraph Online/Eval Harness","description":"正式评估框架，实现 eval-driven development (EDD) 原则。 用于定义 pass/fail 标准、测量 pass@k 指标、创建回归测试套件。","version":1,"lift":{"pass_rate_delta_pts":50,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":12.1,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-15T16:58:02.936090+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":50,"with_pass_pct":81.8,"without_pass_pct":31.8,"tokens_delta_pct":12.1,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-15T16:58:02.936090+00:00","run_id":"de1466b2-cbf4-4e31-aefa-c7c76e8dce44","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":"d54230526d4f425dbcc6659441de68ed276af86b5de73cb351e72cbda4211051","raw_url":"https://app.decimal.ai/s/hashgraph-online-eval-harness/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/hashgraph-online-eval-harness"}