{"skill":{"slug":"multi-agent-collaboration","displayName":"Multi Agent Collaboration","summary":"Claude Grade 多智能体协作技能。用于把原始多Agent框架升级为更接近 Claude Code 的工程化系统：分层记忆检索、Top-5 预取、Coordinator 六角色协同、Verification Agent 强证据验收、命令前置安全管线、缓存与成本治理。适用于需要“多Agent不空转、记忆不瞎...","tags":{"latest":"2.0.0"},"stats":{"comments":0,"downloads":3086,"installsAllTime":38,"installsCurrent":36,"stars":1,"versions":2},"createdAt":1772163707489,"updatedAt":1777525435013},"latestVersion":{"version":"2.0.0","createdAt":1775203253516,"changelog":"- Major upgrade: Integrates Claude Code style mechanisms for multi-agent systems, emphasizing verifiable results and robust execution.\n- Added ClaudeMemorySystem with five-tier memory (identity, correction, task, project, reference) and top-5 retrieval before reasoning.\n- Introduced ClaudeCoordinator featuring six distinct agent roles to structure collaboration.\n- Added VerificationAgent to enforce strong evidence-based validation.\n- Implemented SafetyGatePipeline with 14 built-in guards for command pre-execution auditing.\n- Introduced CostGovernor for cache/call tracking and cost observability.\n- Provided direct usage examples, key source files, and templates for immediate integration.","license":"MIT-0"},"metadata":null,"owner":{"handle":"e2e5g","userId":"s177nbcv26z7ksbd8gps9thykh83hgt3","displayName":"e2e5g","image":"https://avatars.githubusercontent.com/u/130967590?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.4.5","updatedAt":1777525435013}}