{"skill":{"slug":"model-advisor","displayName":"Model Advisor","summary":"模型推荐 + OpenClaw 安全系数分析工具。当用户询问\"用哪个模型\"、\"推荐模型\"、\"适合什么模型\"、\"安全系数\"、\"openclaw 安全\"、\"根据历史\"时触发。功能：(1) 根据历史会话自动分析任务类型并推荐最优的 Claude 模型（auto 模式），(2) 根据用户描述的任务推荐最优模型（recom...","tags":{"latest":"0.1.0"},"stats":{"comments":0,"downloads":316,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":1},"createdAt":1773129674744,"updatedAt":1777527693987},"latestVersion":{"version":"0.1.0","createdAt":1773129674744,"changelog":"Initial release of model-advisor skill.\n\n- Automatically recommends the best Claude model based on recent user task history or specified task description.\n- Analyzes OpenClaw security settings from local configuration and outputs a security score (0-100) with improvement suggestions.\n- Supports four modes: history-based recommendation, description-based recommendation, security score, and full report.\n- Provides reference tables for model selection and security evaluation dimensions.","license":"MIT-0"},"metadata":null,"owner":{"handle":"mrkangzubin","userId":"publishers:mrkangzubin","displayName":"MrKangZuBin","image":"https://avatars.githubusercontent.com/u/21353325?v=4"},"moderation":null}