# narwhal

> narwhal — yumingtao-narwhal. Use this tool when you need to maintain privacy and control over your conversations, projects, and work context, keeping all data local to your machine. The narwhal AI agent solves problems related to data security and privacy, ideal for sensitive or confidential work. It integrates with git, accepting local project inputs and providing secure, private outputs.

Canonical page: https://skillsregistry.net/skills/yumingtao-narwhal  
JSON: https://api.skillsregistry.net/v1/skills/yumingtao-narwhal

## Description

A local-first, privacy-first AI agent. Your conversations, projects, and work context stay on your machine.

## 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:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/yumingtao/narwhal)

## 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": "yumingtao-narwhal"
    }
  }
}
```

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