# derive

> derive — derive-to-derive. Use this tool when you need to review and approve work generated by AI agents, ensuring fairness and transparency in the approval process. It solves problems related to quality control and validation of AI-produced content, providing a self-hostable and MCP-native solution. With git integration, it streamlines the review process, taking in AI-generated work as input and producing approved, validated output.

Canonical page: https://skillsregistry.net/skills/derive-to-derive  
JSON: https://api.skillsregistry.net/v1/skills/derive-to-derive

## Description

Review and approval for work made by AI agents. Fair Source, self-hostable, and MCP-native.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-26

## Source

- **Source listing:** [GitHub](https://github.com/derive-to/derive)

## 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": "derive-to-derive"
    }
  }
}
```

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