Smart Model Switcher Pro

智能模型自动切换 Pro V6.0.0（类 Trae 模式）- 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...

This skill is coherent with its stated purpose (automatic multi-modal model switching), but it implicitly expects the ability to affect 'all sessions' and sub-agents and references a user OpenClaw config/log directory that it did not declare as required. If you consider installing: - Only run the provided scripts after manually inspecting them. They are plain-text PowerShell scripts that will write logs to $env:USERPROFILE\.openclaw and could be executed as a background monitor if you run them. - Be cautious about giving this skill or any agent permission to change models for sub-agents or global sessions; ensure you understand and consent to that scope. - If you need to test, run the scripts in a sandboxed environment or a test account first and back up your OpenClaw config (openclaw.json). - Ask the author for explicit documentation about what data (config files) the skill reads/writes and for a signed/verified homepage or source. Given the missing declaration of config access and the broad instruction to change sub-agent models, treat this skill as suspicious until you confirm the exact scope and permissions.

Type: OpenClaw Skill Name: smart-model-switcher-pro Version: 6.0.0 The skill bundle is a model selection utility designed to help an AI agent automatically switch between different LLMs (e.g., Qwen, GLM, MiniMax) based on the input type (multimodal vs. text) and task category (coding, reasoning, writing). The SKILL.md file provides clear logic for the agent to follow, and the included PowerShell scripts (auto-monitor.txt and runtime-switch.txt) provide a framework for logging and keyword-based task classification. The scripts do not perform any unauthorized network calls, data exfiltration, or persistence mechanisms; they primarily interact with a local log file in the user's profile. The garbled text in the scripts is simply UTF-8 encoded Chinese characters (e.g., '代码' for code, '编程' for programming) and does not represent obfuscation.