# unch

> unch — uchebnick-unch. Use this tool when you need to efficiently search and annotate code repositories using semantic search capabilities. It solves problems of manual code review and discovery by utilizing GGUF embeddings and sqlite-vec to provide accurate search results. The tool takes in repository annotations as input and outputs relevant code matches, ideal for use cases involving large-scale codebase navigation and knowledge retrieval within git repositories.

Canonical page: https://skillsregistry.net/skills/uchebnick-unch  
JSON: https://api.skillsregistry.net/v1/skills/uchebnick-unch

## Description

Local-first semantic code search for repository annotations via GGUF embeddings and sqlite-vec.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/uchebnick/unch)

## 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": "uchebnick-unch"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/uchebnick-unch` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/uchebnick-unch/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