Model Architecture Diagram Finder
BBuf/AI-Infra-Auto-Driven-SKILLS
Looks up public original architecture diagrams for named LLM, vision-language, MoE, diffusion and OCR models and returns the image with its source attribution.
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。
MITAuto-check passed
Install Smart Model Switcher V5
$ npx skills add LeoYeAI/openclaw-master-skills --skill smart-model-switcher-v5 -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills smart-model-switcher-v5 --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/smart-model-switcher-v5 .claude/skills/smart-model-switcher-v5 && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "smart-model-switcher-v5" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/smart-model-switcher-v5 into .claude/skills/smart-model-switcher-v5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-model-switcher-v5", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/smart-model-switcher-v5Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill smart-model-switcher-v5 -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills smart-model-switcher-v5 --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/smart-model-switcher-v5 .agents/skills/smart-model-switcher-v5 && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "smart-model-switcher-v5" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/smart-model-switcher-v5 into .agents/skills/smart-model-switcher-v5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-model-switcher-v5", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill smart-model-switcher-v5 -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills smart-model-switcher-v5 --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/smart-model-switcher-v5 .cursor/skills/smart-model-switcher-v5 && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "smart-model-switcher-v5" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/smart-model-switcher-v5 into .cursor/skills/smart-model-switcher-v5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-model-switcher-v5", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/smart-model-switcher-v5--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill smart-model-switcher-v5 -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills smart-model-switcher-v5 --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/smart-model-switcher-v5 .gemini/skills/smart-model-switcher-v5 && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "smart-model-switcher-v5" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/smart-model-switcher-v5 into .gemini/skills/smart-model-switcher-v5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-model-switcher-v5", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills smart-model-switcher-v5Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill smart-model-switcher-v5 -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/smart-model-switcher-v5 .github/skills/smart-model-switcher-v5 && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "smart-model-switcher-v5" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/smart-model-switcher-v5 into .github/skills/smart-model-switcher-v5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-model-switcher-v5", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill smart-model-switcher-v5 -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills smart-model-switcher-v5 --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/smart-model-switcher-v5 .opencode/skills/smart-model-switcher-v5 && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "smart-model-switcher-v5" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/smart-model-switcher-v5 into .opencode/skills/smart-model-switcher-v5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-model-switcher-v5", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
smart-model-switcher-v5- GitHub stars
- 2.2k
- Token cost
- ~2.5k tokens
- SKILL.md length
- 509 words
- Files
- 5 (incl. scripts)
- Skills in repo
- 1,235
- Repo updated
- First seen
- Licence
- MIT
At a glance
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。
- Works in 4 steps: 主窗口检测（第一步） → 消息分析 → 模型选择 → …
- SKILL.md covers 🎯 V5.0.2 核心升级, ⚠️ 核心规则：主窗口限制, 🖼️ 多模态模型列表 and 🔄 自动切换规则, plus 4 more sections
- Runs JavaScript scripts from its folder
What it does
Smart Model Switcher V5 is an agent skill from LeoYeAI/openclaw-master-skills. 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。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts (for example `README.md`, `_meta.json` and `scripts/auto-switch.js`).
It works with Qwen, Zhipu GLM and MiniMax. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
Example prompts
- “/smart-model-switcher-v5”
Requirements
- Node.js
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (JavaScript), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Smart Model Switcher V5 loads about 2.5k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 509 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 509 words, ~2,456 tokens.
Download SKILL.mdSave it as
.claude/skills/smart-model-switcher-v5/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- smart-model-switcher-v5
- description
- 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。
- version
- 5.1.0
- author
- davidme6
🧠 Smart Model Switcher V5.0.2 (多模态感知增强版)
自动识别任务类型 • 智能切换最优模型 • 零感知 • 无需手动
🎯 V5.0.2 核心升级
| 特性 | V4 | V5.0.2 |
|---|---|---|
| 多模态感知 | ✅ 图片 | ✅ 图片 + 视频 + 音频 |
| Office 模式 | ❌ 无 | ✅ MiniMax-M2.5 |
| 视频理解 | ❌ 不支持 | ✅ 自动切换 qwen3.5-plus |
| 音频理解 | ❌ 不支持 | ✅ 自动切换 qwen3.5-plus |
| 主窗口限制 | ❌ 无限制 | ✅ 仅主窗口生效，子代理不切换 |
| 任务感知 | 智能上下文分析 | 智能上下文分析 + 文件检测 |
⚠️ 核心规则：主窗口限制
🔒 智能切换仅限主窗口
智能模型切换只对主窗口（主会话）生效！
| 会话类型 | 是否执行智能切换 | 说明 |
|---|---|---|
| 主窗口 | ✅ 执行 | 用户直接对话的会话（飞书、WebChat、Telegram 等） |
| 子代理 | ❌ 不执行 | 团队成员办公室（马云CEO、技术专家、市场猎手等） |
| Spawned Session | ❌ 不执行 | 通过 sessions_spawn 创建的所有会话 |
为什么这样设计？
- 子代理有固定模型 - 各专业人员的模型是预设的（技术专家用 glm-5，推理用 qwq-plus）
- 避免干扰 - 智能切换不应该覆盖子代理的专业模型配置
- 职责分明 - 主窗口处理用户意图，子代理专注执行任务
判断方式
当前会话是主窗口？
├── YES → 执行智能切换逻辑
└── NO → 跳过切换，使用该会话预设模型检测方法：
- 主窗口：
depth = 0或无subagent context标记 - 子代理：消息开头有
[Subagent Context]或depth > 0
🖼️ 多模态模型列表
视觉/音视频模型（支持图片/视频/音频）
| 模型 ID | Provider | 能力 | 推荐场景 |
|---|---|---|---|
qwen3.5-plus | Bailian | 图片/视频/音频 ⭐⭐⭐⭐⭐ | 多模态任务首选 |
qwen3-vl-plus | Bailian | 图片 ⭐⭐⭐⭐⭐ | 纯图片理解、OCR |
qvq-max | Bailian | 图片 ⭐⭐⭐⭐⭐ | 复杂视觉推理 |
glm-4v | GLM | 图片 ⭐⭐⭐⭐ | 图片理解 |
代码模型（编程专用）
| 模型 ID | Provider | 代码能力 | 推荐场景 |
|---|---|---|---|
glm-5 | Bailian/GLM | ⭐⭐⭐⭐⭐ | 代码生成、Debug、重构 |
qwen3-coder-plus | Bailian | ⭐⭐⭐⭐⭐ | 代码补全、项目开发 |
qwen-coder-turbo | Bailian | ⭐⭐⭐⭐ | 快速代码任务 |
推理模型（复杂思维）
| 模型 ID | Provider | 推理能力 | 推荐场景 |
|---|---|---|---|
qwq-plus | Bailian | ⭐⭐⭐⭐⭐ | 复杂推理、数学证明 |
qwen3-max | Bailian | ⭐⭐⭐⭐⭐ | 深度思考、分析 |
glm-5 | Bailian/GLM | ⭐⭐⭐⭐ | 逻辑推理 |
Office 文档模型
| 模型 ID | Provider | 能力 | 推荐场景 |
|---|---|---|---|
MiniMax-M2.5 | Bailian | ⭐⭐⭐⭐⭐ | Office 文档处理 |
通用模型
| 模型 ID | Provider | 综合能力 | 推荐场景 |
|---|---|---|---|
qwen3.5-plus | Bailian | ⭐⭐⭐⭐ | 日常对话、写作、翻译 |
qwen-plus | Bailian | ⭐⭐⭐ | 快速任务 |
qwen-turbo | Bailian | ⭐⭐ | 简单任务、低成本 |
🔄 自动切换规则
规则 0: 主窗口检测（最高优先级）
IF 当前会话不是主窗口 → 跳过所有切换逻辑，使用预设模型规则 1: 多模态检测优先（图片/视频/音频）
IF 消息包含图片/视频/音频 → 切换到 qwen3.5-plus
├── 图片 + 代码相关 → qwen3.5-plus (视觉+代码)
├── 视频文件 → qwen3.5-plus (唯一支持视频)
├── 音频文件 → qwen3.5-plus (唯一支持音频)
└── 纯图片理解 → qwen3-vl-plus 或 qwen3.5-plus视频文件扩展名：.mp4, .avi, .mov, .mkv, .wmv, .flv, .webm, .m4v
音频文件扩展名：.mp3, .wav, .m4a, .ogg, .flac, .aac, .wma
图片文件扩展名：.png, .jpg, .jpeg, .gif, .webp, .bmp, .svg
规则 2: 代码任务
IF 消息包含代码关键词 → 切换到代码模型
├── 复杂代码任务 → glm-5 (最强代码)
├── 快速代码补全 → qwen-coder-turbo
└── 项目级开发 → qwen3-coder-plus规则 3: 推理任务
IF 消息包含推理关键词 → 切换到推理模型
├── 复杂推理 → qwq-plus (最强推理)
├── 数学/证明 → qwen3-max
└── 一般分析 → glm-5规则 4: Office 模式
IF 用户说 "Office模式" / "切换Office" / "MiniMax" → 切换到 MiniMax-M2.5
└── Office 文档处理 → MiniMax-M2.5规则 5: 文本任务
IF 纯文本任务 → 使用通用模型
├── 长文档 → qwen3.5-plus (1M context)
├── 写作/翻译 → qwen3.5-plus
└── 简单对话 → qwen-plus / qwen-turbo📋 切换决策树（完整版）
收到消息
│
├── 🔒 是否为主窗口（主会话）？
│ ├── NO → 跳过切换，使用该会话预设模型
│ │
│ └── YES ↓
│
├── 🖼️ 包含图片/视频/音频？
│ ├── 视频文件 (.mp4/.avi/.mov/.mkv/...) → qwen3.5-plus ⭐多模态优先
│ ├── 音频文件 (.mp3/.wav/.m4a/.ogg/...) → qwen3.5-plus ⭐多模态优先
│ ├── 图片 + 代码关键词 → qwen3.5-plus (视觉+代码)
│ └── 纯图片 → qwen3-vl-plus 或 qwen3.5-plus
│
├── 💻 代码关键词？
│ └── YES → glm-5 (最强代码)
│
├── 🧠 推理关键词？
│ └── YES → qwq-plus / qwen3-max
│
├── 📎 Office 关键词？
│ └── YES → MiniMax-M2.5
│
└── 📝 通用任务 → qwen3.5-plus🎯 关键词识别
多模态检测（最高优先级）
- 图片：消息中有
image类型内容，文件扩展名 .png, .jpg, .jpeg, .gif, .webp, .bmp - 视频：文件扩展名 .mp4, .avi, .mov, .mkv, .wmv, .flv, .webm, .m4v
- 音频：文件扩展名 .mp3, .wav, .m4a, .ogg, .flac, .aac, .wma
- 用户说："看这个图"、"视频里是什么"、"听这个音频"、"截图"
代码关键词
- 编程相关：代码、编程、python、js、javascript、函数、debug、bug、报错、错误、修复
- 文件类型：.py, .js, .ts, .html, .css, .json, .yaml, .sh
- 操作词：写一个、帮我写、优化、重构、解释这段代码
推理关键词
- 推理、逻辑、证明、数学、计算、分析、思考
- 为什么、怎么推导、能不能推出、关系
Office 关键词
- Office、Office模式、切换Office、MiniMax、文档处理
- Word、Excel、PPT、PowerPoint、表格处理
写作关键词
- 写、作文、文章、小说、故事、文案、邮件、报告
🔧 配置示例
用户配置的最强模型
{
"modelPreferences": {
"multimodal": "qwen3.5-plus", // 视频/音频/图片
"vision": "qwen3-vl-plus", // 纯图片
"coding": "glm-5", // 代码最强
"reasoning": "qwq-plus", // 推理最强
"office": "MiniMax-M2.5", // Office 文档
"general": "qwen3.5-plus", // 通用最强
"fast": "qwen-turbo" // 快速任务
}
}📊 使用示例
示例 1: 主窗口发送视频文件
用户: [发送一个 .mp4 文件] "帮我分析这个视频"
环境: 主窗口 (WebChat)
检测: 视频文件 + 主窗口
切换: qwen3.5-plus (唯一支持视频的模型)
执行: 分析视频内容示例 2: 子代理处理代码任务
用户: "让技术专家写个爬虫"
环境: 技术专家办公室 (子代理)
检测: 代码关键词 + 子代理环境
结果: 不执行智能切换，使用技术专家预设模型 (glm-5)
执行: 生成爬虫代码示例 3: 主窗口 Office 模式
用户: "切换到 Office 模式"
环境: 主窗口 (飞书)
检测: Office 关键词 + 主窗口
切换: MiniMax-M2.5
提示: "🧠 已切换到 MiniMax-M2.5（Office 模式）"示例 4: 主窗口发送音频文件
用户: [发送一个 .mp3 文件] "转录这段录音"
环境: 主窗口 (Telegram)
检测: 音频文件 + 主窗口
切换: qwen3.5-plus (唯一支持音频的模型)
执行: 转录音频内容示例 5: 子代理执行推理任务
用户: "让推理专家证明根号2是无理数"
环境: 推理专家办公室 (子代理)
检测: 推理关键词 + 子代理环境
结果: 不执行智能切换，使用推理专家预设模型 (qwq-plus)
执行: 给出证明过程🚀 实现逻辑
Step 0: 主窗口检测（第一步）
检测当前会话:
1. 是否有 [Subagent Context] 标记？
2. 是否有 depth > 0？
3. 是否是 spawned session？
└── YES → 跳过所有智能切换，使用预设模型
└── NO → 继续执行智能切换逻辑Step 1: 消息分析
分析用户消息:
1. 是否包含图片/视频/音频附件 ← 最高优先级
2. 提取关键词
3. 识别任务类型
4. 确定上下文需求Step 2: 模型选择
选择最优模型:
1. 根据任务类型查找最佳模型
2. 检查模型可用性 (API Key + 套餐)
3. 应用 fallback 逻辑
4. 记录选择原因Step 3: 执行切换
切换模型:
1. 调用 session_status(model: "xxx")
2. 发送提示信息给用户
3. 执行任务
4. 记录性能数据⚠️ 核心原则
- 主窗口限制 - 智能切换仅限主窗口，子代理保持预设模型
- 多模态优先 - 图片/视频/音频一律走 qwen3.5-plus，绝不走 GLM-5
- 代码专用 - GLM-5 只用于纯代码/纯技术任务
- Office 独立 - MiniMax-M2.5 专门处理 Office 文档
- 检测优先级 - 主窗口 > 图片/视频/音频 > 代码 > 推理 > Office > 通用
- 自动切换 - 用户无需手动操作，系统自动识别
- fallback - 如果首选模型不可用，自动降级到备选
Show full SKILL.md (188 more words)Show less
📝 更新日志
V5.0.2 (2026-03-25)
- ✅ 新增视频文件自动检测 (.mp4, .avi, .mov, .mkv 等)
- ✅ 新增音频文件自动检测 (.mp3, .wav, .m4a, .ogg 等)
- ✅ 新增 Office 模式，支持 MiniMax-M2.5
- ✅ 新增主窗口限制，子代理不执行智能切换
- ✅ 更新决策树，主窗口检测为最高优先级
- ✅ 明确 GLM-5 只用于纯代码任务
V4.0.0 (2026-03-23)
- ✅ 新增多模态感知，自动识别图片
- ✅ 新增视觉模型支持 (qwen3-vl-plus, qwen3.5-plus)
- ✅ 优化切换决策树，图片检测优先
- ✅ 更新关键词识别规则
V3.0.0
- ✅ 全平台支持
- ✅ API Key 验证
- ✅ 套餐检测
🤖 AI Agent 自动行为指南
重要：AI Agent 在每次响应前，必须执行以下检测流程！
🔒 规则 0：主窗口检测（第一步！）
智能切换只对主窗口生效！子代理不要执行模型切换！
Step 0: 检测当前会话类型
├── 消息开头有 [Subagent Context]？
│ └── YES → 这是子代理，跳过智能切换，使用预设模型
│
├── 有 depth 标记且 depth > 0？
│ └── YES → 这是子代理，跳过智能切换，使用预设模型
│
├── 是 spawned session？
│ └── YES → 这是子代理，跳过智能切换，使用预设模型
│
└── NO → 这是主窗口，继续执行智能切换逻辑子代理示例：
[Wed 2026-03-25 21:05 GMT+8] [Subagent Context] You are running as a subagent...[Subagent Task]: ...depth=1或任何depth > 0
主窗口示例：
- 用户直接在 WebChat/飞书/Telegram 发消息
- 无
[Subagent Context]标记 depth=0或无 depth 标记
⚠️ 会话级别切换（重要！）
模型切换是会话级别的，不影响其他通道！
- WebChat 发视频 → 只在 WebChat 切换多模态模型
- 飞书写代码 → 只在飞书会话切换代码模型
- Telegram 聊天 → 只在 Telegram 会话切换模型
不同通道独立，互不影响！
切换方法（会话级别）
使用 session_status 工具，带上当前会话的 sessionKey：
// 当前会话切换（不影响其他通道）
session_status(model: "bailian/glm-5")
// 切换其他会话的模型（需要指定 sessionKey）
session_status(sessionKey: "feishu/xxx", model: "bailian/qwen3.5-plus")默认行为：不带 sessionKey 时，只切换当前会话的模型。
检测流程（每次响应前）
Step 0: 主窗口检测 ← 第一步！
├── 是子代理？ → 跳过切换，使用预设模型
└── 是主窗口？ → 继续
Step 1: 检测消息内容
├── 是否包含图片/视频/音频？
│ └── YES → 切换到 qwen3.5-plus（多模态模型）
│
├── 是否包含代码关键词？
│ └── YES → 切换到代码模型 (glm-5)
│
├── 是否包含推理关键词？
│ └── YES → 切换到推理模型 (qwq-plus)
│
├── 是否包含 Office 关键词？
│ └── YES → 切换到 Office 模型 (MiniMax-M2.5)
│
└── 否则保持当前模型切换方法
使用 session_status 工具切换模型：
session_status(model: "bailian/qwen3.5-plus") // 多模态
session_status(model: "bailian/glm-5") // 代码
session_status(model: "bailian/qwq-plus") // 推理
session_status(model: "bailian/MiniMax-M2.5") // Office切换提示
切换成功后，给用户一个简短提示：
- "🧠 已切换到 qwen3.5-plus（视频/音频理解）"
- "🧠 已切换到 qwen3.5-plus（图片理解）"
- "🧠 已切换到 glm-5（代码任务）"
- "🧠 已切换到 qwq-plus（推理任务）"
- "🧠 已切换到 MiniMax-M2.5（Office 模式）"
示例行为
场景 A: 主窗口发送视频
────────────────────────
用户: [发送一个 .mp4 视频文件] "帮我分析这个视频"
AI 行为:
1. 检测: 无 [Subagent Context] → 是主窗口
2. 检测到视频文件 → 需要多模态模型
3. 决策: 使用 qwen3.5-plus（唯一支持视频）
4. 调用: session_status(model: "bailian/qwen3.5-plus")
5. 提示: "🧠 已切换到 qwen3.5-plus（视频理解）"
6. 分析视频内容
场景 B: 子代理处理代码任务
────────────────────────
消息: [Subagent Context] You are running as a subagent...
任务: 技术专家，写一个爬虫
AI 行为:
1. 检测: 有 [Subagent Context] → 是子代理
2. 决策: 跳过智能切换，使用预设模型 (glm-5)
3. 不调用 session_status
4. 直接执行任务注意事项
- 主窗口限制 - 只有主窗口才执行智能切换，子代理保持预设模型
- 不要重复切换 - 如果当前模型已经是最优选择，不要切换
- 切换要快 - 使用简短提示，不要长篇大论
- 记录切换 - 如果模型切换成功，记住当前使用的模型
- 优先级 - 主窗口检测 > 图片/视频/音频 > 代码 > 推理 > Office > 通用
- 多模态内容绝不走 GLM-5 - 视频/音频/图片必须用 qwen3.5-plus
📋 快速参考
| 场景 | 是否切换 | 最优模型 |
|---|---|---|
| 🏠 主窗口 + 视频 | ✅ 切换 | qwen3.5-plus |
| 🏠 主窗口 + 音频 | ✅ 切换 | qwen3.5-plus |
| 🏠 主窗口 + 图片 | ✅ 切换 | qwen3.5-plus |
| 🏠 主窗口 + 代码 | ✅ 切换 | glm-5 |
| 🏠 主窗口 + 推理 | ✅ 切换 | qwq-plus |
| 🏠 主窗口 + Office | ✅ 切换 | MiniMax-M2.5 |
| 🤖 子代理 + 代码 | ❌ 不切换 | 使用预设模型 |
| 🤖 子代理 + 推理 | ❌ 不切换 | 使用预设模型 |
| 🤖 子代理 + 任何 | ❌ 不切换 | 使用预设模型 |
V5.0.2 核心亮点：主窗口智能切换，子代理保持预设，发图片/视频/音频自动切换多模态模型，完全无感！ 🚀
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts) in skills/smart-model-switcher-v5 of LeoYeAI/openclaw-master-skills.
- SKILL.md
- LICENSE.txt
- README.md
- _meta.json
- scripts/auto-switch.js
Open the folder on GitHubat commit e5199b5
Compare with similar skills
Smart Model Switcher V5 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Smart Model Switcher V5 this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.5k | Automated safety check: Pass | MIT | |
| Model Architecture Diagram FinderBBuf/AI-Infra-Auto-Driven-SKILLS | 938 | — | ~1.2k | Automated safety check: Pass | None | |
| Image Genopen-octo/octo-agent | 125 | — | ~3.1k | Automated safety check: Notes | MIT | |
| LLM Council on Fireworks AIdair-ai/dair-academy-plugins | 614 | — | ~5k | Automated safety check: Notes | MIT | |
| AI Image Generation and Editingzhayujie/CowAgent | 47k | — | ~1.3k | Automated safety check: Pass | MIT | |
| AI Search Hubminsight-ai-info/AI-Search-Hub | 1.3k | — | ~1.3k | Automated safety check: Pass | None |
Similar skills
Image Gen
open-octo/octo-agent
Acquire images as files — generate them with an AI image model (14 providers: OpenAI/gpt-image, Gemini, Qwen, Zhipu, Volcengine, Stability, FLUX, Ideogram, MiniMax, and more), search openly-licensed…
LLM Council on Fireworks AI
dair-ai/dair-academy-plugins
Has several open-weight models answer a question, rank each other's anonymized answers, then lets a chairman model write the final response through Fireworks AI.
AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
AI Search Hub
minsight-ai-info/AI-Search-Hub
Run the AI Search Hub browser automation scripts for Yuanbao, LongCat, Doubao, Qwen, Gemini, Grok, and MiniMax.
Weave Router Local Testing
weave-os/router
Stands up the Weave model router in Docker Compose and drives it with claude -p against a real or mocked upstream to reproduce and verify routing and streaming behavior.
More from LeoYeAI/openclaw-master-skills
All 1,235 skills in this repoDevOps Pipeline Management
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
Feishu Document Collaboration
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
Files Memory System
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
GEO-Claw AI Visibility Agent
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
Google Workspace CLI
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
HealthFit Health Advisors
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Related
Questions about Smart Model Switcher V5
What does Smart Model Switcher V5 do?
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。. Smart Model Switcher V5 is an agent skill from LeoYeAI/openclaw-master-skills.
How do I install Smart Model Switcher V5 in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill smart-model-switcher-v5 -a claude-code`. Or copy the skill folder (skills/smart-model-switcher-v5 in LeoYeAI/openclaw-master-skills) into .claude/skills/smart-model-switcher-v5 in your project. Claude Code loads it when a task matches its description.
How do I install Smart Model Switcher V5 in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill smart-model-switcher-v5 -a codex`. Or copy the skill folder (skills/smart-model-switcher-v5 in LeoYeAI/openclaw-master-skills) into .agents/skills/smart-model-switcher-v5 in your project. Codex loads it when a task matches its description.
Can I use Smart Model Switcher V5 in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill smart-model-switcher-v5 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/smart-model-switcher-v5, .gemini/skills/smart-model-switcher-v5, .github/skills/smart-model-switcher-v5 and .opencode/skills/smart-model-switcher-v5 in your project.
What does Smart Model Switcher V5 need to run?
Going by SKILL.md and its folder, Smart Model Switcher V5 needs JavaScript for the scripts in its folder. Our summary lists: Node.js.
Does Smart Model Switcher V5 access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Smart Model Switcher V5 safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Smart Model Switcher V5 use?
Smart Model Switcher V5 is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Smart Model Switcher V5 use?
About 2.5k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Smart Model Switcher V5?
Skills that share tags, products or a category with Smart Model Switcher V5: Model Architecture Diagram Finder (BBuf/AI-Infra-Auto-Driven-SKILLS, 938 stars), Image Gen (open-octo/octo-agent, 125 stars), LLM Council on Fireworks AI (dair-ai/dair-academy-plugins, 614 stars) and AI Image Generation and Editing (zhayujie/CowAgent, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Smart Model Switcher V5?
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.