{"skill":{"slug":"mult-call","displayName":"Mult Call","summary":"多路召回skill ,用于将意图识别skill中的指标和维度信息进行分析，通过向量知识库召回QA问答对，通过图数据库召回表的定义结构。","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":216,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":1},"createdAt":1773710927770,"updatedAt":1777625571616},"latestVersion":{"version":"1.0.0","createdAt":1773710927770,"changelog":"Summary: Initial public release for multi_call skill, enabling multi-path recall of QA pairs and table schema based on intent recognition results.\n\n- Retrieves QA pairs using a vector knowledge base (Milvus) and table definitions using a graph database (Neo4j).\n- Extracts and analyzes metric and dimension information from recognized intent outputs.\n- Outputs include table DDL structure and similar QA pairs, with configurable recall weights for each data source.\n- Independent failure handling: gracefully degrades if either Milvus or Neo4j service fails.\n- Includes .env configuration for service credentials and supports standalone execution from the command line.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"lovenervermore","userId":"s179eehz3gk12qcjky3an7t6sx83pxjj","displayName":"LoveNerverMore","image":"https://avatars.githubusercontent.com/u/68802221?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.dangerous_exec"],"summary":"Detected: suspicious.dangerous_exec","engineVersion":"v2.4.22","updatedAt":1777625571616}}