{"skill":{"slug":"agent-eval","displayName":"Agent Eval","summary":"基于Karpathy AutoResearch和多Agent复盘的闭环量化评估体系，实现任务自动yes/no评判与持续优化升级。","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":133,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":1},"createdAt":1775779996654,"updatedAt":1775780508511},"latestVersion":{"version":"1.0.0","createdAt":1775779996654,"changelog":"Initial release introducing a modular, quantifiable agent evaluation framework with self-improvement feedback loops.\n\n- Provides standardized yes/no checklists and scoring rules for diverse agent types (Content, Legal, Science, Literature, Analysis, Medical, etc.)\n- Establishes weighted, dimension-specific evaluation items and time-based auto-evaluation workflows (daily self-review, weekly CEO reports).\n- Defines clear scoring tiers with actionable triggers for optimization and tracking.\n- Integrates with existing memory, quality, and research systems for seamless agent evolution.\n- Prioritizes real-world task sets and explicit improvement cycles.","license":"MIT-0"},"metadata":null,"owner":{"handle":"luaqnyin","userId":"s178qe0kda29njgnhv2hnwpbc983kt75","displayName":"luaqnyin","image":"https://avatars.githubusercontent.com/u/162386609?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1775780508511}}