# semble

> semble — minishlab-semble. Use this tool when you need to quickly locate specific code snippets or files within large repositories, solving problems of inefficient manual searching and facilitating faster development and debugging. Semble takes in repository URLs and search queries as inputs and returns relevant code results as outputs. Ideal for use cases where rapid code discovery is crucial, such as during software development, maintenance, or troubleshooting.

Canonical page: https://skillsregistry.net/skills/minishlab-semble  
JSON: https://api.skillsregistry.net/v1/skills/minishlab-semble

## Description

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

## Trust

- **Trust score (0–1):** 0.55
- **Verification tier:** scanned
- **Last scanned:** 2026-05-21

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** search
- **Updated:** 2026-09-27

## Source

- **Source listing:** [GitHub](https://github.com/MinishLab/semble)

## 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": "minishlab-semble"
    }
  }
}
```

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