{"skill":{"slug":"model-switchboard","displayName":"Model Switchboard","summary":"Safely configure OpenClaw AI models by validating roles, autoloading backups, blocking unsafe changes, and managing via CLI or Canvas UI.","tags":{"latest":"3.0.0"},"stats":{"comments":0,"downloads":375,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1772067280160,"updatedAt":1777525400839},"latestVersion":{"version":"3.0.0","createdAt":1772067280160,"changelog":"- Major upgrade: introduces robust safeguards for managing AI models in OpenClaw.\n- All model assignments must use provided commands; direct JSON edits are strictly forbidden.\n- Automatic validation, backup (30 rolling), and instant rollback for every config change.\n- Prevents unsafe assignments (e.g., image models as LLMs) and enforces strict validation rules.\n- Adds visual management dashboard (Canvas UI) and full CLI reference.\n- Advanced redundancy, import/export, health diagnostics, and troubleshooting support included.","license":null},"metadata":null,"owner":{"handle":"frank-bot07","userId":"publishers:frank-bot07","displayName":"frank-bot07","image":"https://avatars.githubusercontent.com/u/259001718?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.install_untrusted_source"],"summary":"Detected: suspicious.install_untrusted_source","engineVersion":"v2.4.5","updatedAt":1777525400839}}