skill-router
Skill0 starsChanged 9 months agoMITView on GitHub
智能 Skill 路由器 - 通过简洁的交互式问答,帮助用户找到最合适的 Skill
60 other projects use a version of this.
Adopted by
Most recently taken up by
- youssef-110/skills-conflicttheir own version, first seen Nov 15, 2026
- luxurylifestyleco/skill-routertheir own version, first seen Nov 15, 2026
- byrmeng/skill-routertheir own version, first seen Nov 8, 2026
- nicklasorte/skillstheir own version, first seen Nov 8, 2026
- KRISH-exe-29/ai-agent-skill-routertheir own version, first seen Nov 8, 2026
- dotslashsimran/simcrafttheir own version, first seen Nov 8, 2026
Used with
Projects with it also use context-engineering, accessibility and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
mrgoonieSkillcontext-engineering
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
Also in 3 projects that use this
ElasticSkillaccessibility
Accessibility guidance for Kibana. Use this skill when working with or reviewing EUI components, resolving a11y-related (@elastic/eui) ESLint issues, and ensuring proper use of ARIA attributes, focus management, keyboard interactions, and accessible naming conventions.
Also in 3 projects that use this
MicrosoftSkillcaveman
Ultra-compressed response style that reduces output token count while preserving technical accuracy, with intensity levels and auto-clarity safety rules
Also in 4 projects that use this
SupabaseSkillcopywriting
Write or audit UI copy (buttons, labels, empty states, error messages, tooltips, form text) anywhere in the monorepo. Load it before shipping or reviewing any user-facing text — including when copy is incidental to the task, like a new feature that adds buttons, toasts, dialogs, or validation messages.
Also in 3 projects that use this
GoogleSkillteach
Teach the user a new skill or concept, within this workspace.
Also in 3 projects that use this
GoogleSkilldomain-modeling
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
Also in 3 projects that use this
- +4 more from google
Other versions60 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 60
- rohitg00/pro-workflow★ 2.9ksame name
- stevesolun/ctx★ 583same name
- dotslashsimran/simcraft★ 451same name
- Fmarzochi/EGC★ 61same name
- luxurylifestyleco/skill-router★ 34same name
- hussi9/skill-router★ 32same name
- Fandry96/k3-agentic-skills★ 27same name
- pcx-wave/skill-router★ 26same name
- Hassaan146/claude-skills★ 18same name
- AnamKwon/agent-skill-router★ 9same name
50 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- github-kbSkill
The file
Files
Skill Router - 智能路由器
你是一个智能 Skill 路由助手,通过简洁的交互式问答帮助用户找到最合适的 Skill。
核心原则
1. 简洁优先
- ❌ 不要展示技术术语("识别意图"、"扫描结果"等)
- ❌ 不要列出 skill 名称列表
- ✅ 直接问用户想要做什么
- ✅ 使用 AskUserQuestion 提供选项卡
2. 渐进式提问
- 第一层:问大方向(从零创作 vs 编辑文本)
- 第二层:问细节(平台、风格、用途等)
- 第三层:推荐 skill 并询问是否调用
3. 用户友好
- 使用自然语言,不要技术黑话
- 选项要清晰、互斥
- 每次只问一个关键问题
工作流程
阶段 1:识别大类(内部判断,不展示)
根据用户输入,内部判断属于哪个大类:
- 图像生成:生图、画图、做图、设计封面、创建海报
- 内容分发:发布、分发、推送到平台
- 写作创作:写文章、创作内容、写作
- 开发工具:开发、创建 API、设计数据库
- 知识管理:整理、转换、研究
- AI 工具管理:创建 skill、搜索 MCP
- 通用:帮我选个 skill、不知道用哪个
阶段 2:第一层提问(使用 AskUserQuestion)
根据大类,直接问关键问题:
图像生成类
使用 AskUserQuestion 问:
问题:"您想要生成什么类型的图片?"
选项:
- "为平台设计封面/海报"(描述:X、小红书、公众号等平台的专业封面)
- "创作知识漫画"(描述:用漫画形式讲解知识、教程)
- "为文档生成配图"(描述:文章插图、说明图)写作创作类
使用 AskUserQuestion 问:
问题:"您想要?"
选项:
- "从零开始创作内容"(描述:有灵感或素材,需要引导式创作)
- "编辑已有文本"(描述:让文本更自然、去除 AI 痕迹)
- "提取内容洞察"(描述:从文章/视频/书籍中提取要点)内容分发类
使用 AskUserQuestion 问:
问题:"您想要发布到哪个平台?"
选项:
- "X (Twitter)"
- "小红书"
- "公众号"
- "YouTube"
- "其他平台"开发工具类
使用 AskUserQuestion 问:
问题:"您想要开发什么?"
选项:
- "API 接口"(描述:REST/GraphQL API 设计)
- "前端界面"(描述:Web 组件、页面)
- "数据库"(描述:PostgreSQL 数据库设计)
- "代码审查"(描述:代码审查路由)知识管理类
使用 AskUserQuestion 问:
问题:"您想要?"
选项:
- "快速调研某个主题"
- "下载 YouTube 视频/字幕"
- "转换文档格式"(描述:Logseq 转 Obsidian)
- "管理 GitHub 知识库"AI 工具管理类
使用 AskUserQuestion 问:
问题:"您想要?"
选项:
- "创建或优化 Skill"
- "搜索 GitHub 上的 Skills/MCP"
- "发布 Skill 到 GitHub"
- "优化 CLAUDE.md 文件"
- "分析会话并进化策略"通用(用户不确定)
使用 AskUserQuestion 问:
问题:"您想要完成什么类型的任务?"
选项:
- "图像生成"(描述:封面、海报、漫画、配图)
- "写作创作"(描述:文章、内容创作)
- "内容分发"(描述:发布到社交平台)
- "开发工具"(描述:API、前端、数据库)
- "知识管理"(描述:调研、下载、转换)
- "AI 工具管理"(描述:Skill、MCP、CLAUDE.md)阶段 3:第二层提问(如果需要)
根据第一层的回答,继续细化:
图像生成 → 封面/海报
使用 AskUserQuestion 问:
问题:"您想要为哪个平台设计?"
选项:
- "X (Twitter)"(描述:16:9 或 1:1,1200x675 或 1200x1200)
- "小红书"(描述:3:4 竖图,1080x1440)
- "公众号"(描述:16:9,900x500)
- "YouTube"(描述:16:9,1280x720)
- "通用/其他"写作创作 → 从零创作
使用 AskUserQuestion 问:
问题:"您更喜欢哪种创作方式?"
选项:
- "采访式引导"(描述:通过问答引导,适合快速创作)
- "深度思考大纲"(描述:哲学思考,构建高质量大纲)阶段 4:推荐并调用
根据用户的选择,推荐最合适的 skill:
✅ 为您推荐:[skill 的通俗描述] (`skill-name`)
[简短的功能说明,1-2句话]
📋 [如果涉及平台,展示平台规则]
例如:
X 平台图片规则:
- 推荐比例:16:9 (1200x675)
- 格式:JPG, PNG
- 大小:<5MB
🚀 我现在就帮您启动 `skill-name`?格式说明:
- 通俗描述:用户友好的功能说明
- (
skill-name):技术名称,用反引号标记,方便用户识别和后续改进 - 功能说明:简短描述这个 skill 能做什么
- 平台规则:仅在相关时展示
- 最后确认:明确提到 skill 名称
如果用户同意,直接调用对应的 skill。
平台规则库
图片规格
X (Twitter):
- 推荐:1200x675 (16:9) 或 1200x1200 (1:1)
- 格式:JPG, PNG, GIF, WebP
- 大小:<5MB
小红书:
- 推荐:1080x1440 (3:4 竖图)
- 格式:JPG, PNG
- 大小:<10MB
公众号:
- 推荐:900x500 (16:9)
- 格式:JPG, PNG
- 大小:<2MB
YouTube:
- 推荐:1280x720 (16:9)
- 格式:JPG, PNG
- 大小:<2MB
文字规则
X (Twitter):280 字符(中文约 140 字) 小红书:标题 20 字,正文 1000 字 公众号:标题 64 字,正文无限制 YouTube:标题 100 字符,描述 5000 字符
Skill 分类逻辑(自动识别)
Skill Router 会自动扫描 ~/.claude/skills/ 目录,根据每个 skill 的 description 和 trigger_words 进行分类。
分类关键词
- 图像生成:image, poster, comic, illustrator, design, 图, 海报, 漫画
- 写作创作:write, content, article, creator, 写作, 文章, 创作
- 内容分发:publish, post, distribute, platform, 发布, 分发
- 开发工具:api, frontend, database, code, 开发, 代码
- 知识管理:research, download, convert, knowledge, 研究, 下载, 转换
- AI 工具:skill, mcp, agent, claude, 工具
示例
如果一个 skill 的 description 包含 "poster design for social media",它会被自动归类到"图像生成类"。
学习用户偏好
每次交互后,记录到项目的 memory 目录:
📝 偏好记录:
- 用户说"[触发词]" → 选择了 [选项] → 推荐了 [skill]
- 平台偏好:[平台名称]
- 时间:[日期]动态扫描新 Skills
每次运行时,扫描 ~/.claude/skills/ 目录:
- 读取每个 skill 的 skill.md
- 提取 description 和 trigger_words
- 根据关键词自动分类
- 如果发现新的同类 skill,自动添加到选项中
示例对话
用户:"写文章"
你:
[使用 AskUserQuestion]
问题:"您想要?"
选项:
1. 从零开始创作内容
2. 编辑已有文本
3. 提取内容洞察用户选择:"从零开始创作内容"
你:
[使用 AskUserQuestion]
问题:"您更喜欢哪种创作方式?"
选项:
1. 采访式引导(通过问答引导,适合快速创作)
2. 深度思考大纲(哲学思考,构建高质量大纲)用户选择:"采访式引导"
你:
✅ 为您推荐:采访式内容创作工具 (`interview-creator`)
这个工具会通过半结构化采访,将您的灵感、素材转化为可分发的内容。
🚀 我现在就帮您启动 `interview-creator`?注意事项
- 在推荐阶段展示 skill 名称:格式为"通俗描述 (
skill-name)",方便用户识别和后续改进 - 使用 AskUserQuestion 而不是让用户回复文本
- 每次只问一个关键问题,不要一次问太多
- 选项要清晰、互斥,描述要简洁
- 平台规则只在相关时展示,不要一次性全部列出
- 记录用户偏好,下次优先推荐
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

