{"skill":{"slug":"smart-model-switcher-v2","displayName":"Smart Model Switcher V2","summary":"智能模型自动切换 V5.0.2 - 多模态感知，自动识别图片/视频/音频/代码/文本任务，切换到最适合的模型。支持图片理解(qwen3-vl-plus)、视频音频(qwen3.5-plus)、代码(glm-5)、Office文档(MiniMax-M2.5)、推理等场景。零感知切换，无需手动操作。","tags":{"ai":"2.0.0","latest":"2.1.0","model":"2.0.0","openclaw":"2.0.0","optimization":"2.0.0","switcher":"2.0.0","zero-latency":"2.0.0"},"stats":{"comments":0,"downloads":356,"installsAllTime":2,"installsCurrent":2,"stars":0,"versions":2},"createdAt":1773086215198,"updatedAt":1777527462072},"latestVersion":{"version":"2.1.0","createdAt":1775228043271,"changelog":"**Smart Model Switcher now features multimodal awareness, enhanced Office mode, and main-window-only switching.**\n\n- Added automatic detection and model switching for video (.mp4, .avi, .mov, .mkv, etc.) and audio (.mp3, .wav, .m4a, .ogg, etc.) files.\n- Introduced Office mode supporting MiniMax-M2.5 for Office document processing.\n- Implemented \"main window restriction\": intelligent model switching now only occurs in the main chat window; subagents always use their preset models.\n- Clarified model assignment rules: GLM-5 is for pure coding tasks only; qwen3.5-plus prioritized for all multimodal inputs.\n- Updated decision logic and keyword rules for more accurate task-type recognition.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"davidme6","userId":"s17aperbk8h3dswpc0vbsayk4d83hweb","displayName":"davidme6","image":"https://avatars.githubusercontent.com/u/198009354?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.4.5","updatedAt":1777527462072}}