Progressive group routing for 393 professional skills via Rust daemon stdio shim.
Connect Skill Shelf (Rust Singleton Daemon) to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Progressive group routing for 393 professional skills via Rust daemon stdio shim. The skill shelf (rust singleton daemon) mcp server is what makes that connection.
Skill Shelf 连这个问题一起解决了：LLM 看见 MCP 工具就会自己去查、自己去用。你不需要记住每个 skill 的内容，也不需要判断什么时候该用——LLM 遇到合适的场景自己会去搜索和加载。
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
browse_shelf — 不传参返回 group catalog + 状态信息；传 group 返回组内 skill summariessearch_skills — 兜底搜索全部 skill，返回 top N 匹配结果read_skill — 默认读取 skill summary；full=true 时读取完整正文、资源、参考文件install_skills — 从目录安装 skill 包（支持新建和 LLM 辅助分组）validate_skills — 校验完整性；clean=true 时自动删除有问题的 skillmanage_group — 创建/更新/删除存储组（mode: create/update/delete）reclassify_skill — 将 skill 移至新的组（更新 frontmatter + 移动目录 + 重建索引）SKILL_SHELF_ROOT — /data/hubSKILL_SHELF_SEARCH_LIMIT — 8SKILL_SHELF_MAX_RELATED_SKILLS — 5SKILL_SHELF_WATCH — 1Configuration is passed through the environment: SKILL_SHELF_ROOT. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
The server ships on npm as npm, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Skill Shelf (Rust Singleton Daemon)'s toolset — browse_shelf, search_skills, read_skill and 8 more — is a fair guide to whether it matches your workflow. It is maintained by halflifezyf2680; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| browse_shelf | 不传参返回 group catalog + 状态信息；传 group 返回组内 skill summaries |
| search_skills | 兜底搜索全部 skill，返回 top N 匹配结果 |
| read_skill | 默认读取 skill summary；full=true 时读取完整正文、资源、参考文件 |
| install_skills | 从目录安装 skill 包（支持新建和 LLM 辅助分组） |
| validate_skills | 校验完整性；clean=true 时自动删除有问题的 skill |
| manage_group | 创建/更新/删除存储组（mode: create/update/delete） |
| reclassify_skill | 将 skill 移至新的组（更新 frontmatter + 移动目录 + 重建索引） |
| SKILL_SHELF_ROOT | <package>/data/hub |
| SKILL_SHELF_SEARCH_LIMIT | 8 |
| SKILL_SHELF_MAX_RELATED_SKILLS | 5 |
| SKILL_SHELF_WATCH | 1 |
MCP 客户端配置：
```json
{
"mcpServers": {
"skill-shelf": {
"command": "node",
"args": ["D:/Tools/Skill-Shelf/bin/skill-shelf.js", "mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| SKILL_SHELF_ROOT | Configuration value read at startup. | Optional |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.