# cowork-semantic-search

> cowork-semantic-search — zhubit-cowork-semantic-search. Use this tool when you need to perform local offline searches over various document types, solving problems of information retrieval and document discovery in multilingual environments. It indexes folders and supports hybrid vector and keyword searches, providing a self-contained solution without requiring API keys, cloud services, or Docker. Ideal for use cases where data privacy and offline access are essential, such as research, documentation, and knowledge management.

Canonical page: https://skillsregistry.net/skills/zhubit-cowork-semantic-search  
JSON: https://api.skillsregistry.net/v1/skills/zhubit-cowork-semantic-search

## Description

Local offline semantic search over documents (txt, md, pdf, docx, pptx, csv). Indexes folders into a LanceDB vector database with multilingual embeddings and supports hybrid vector + keyword search via Reciprocal Rank Fusion. No API keys, no cloud, no Docker required.

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/wl2pbitgz7)
- **Repository:** <https://github.com/ZhuBit/cowork-semantic-search>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "zhubit-cowork-semantic-search"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zhubit-cowork-semantic-search` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zhubit-cowork-semantic-search/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt