# savile

> savile — mr8lu-savile. Use this tool when you need to manage and synchronize AI agent prompts and skills across local environments, leveraging a high-fidelity MCP server and protocol for versioning and evaluating AI capabilities. It solves problems related to data consistency, collaboration, and offline access, providing a robust interface for storing and syncing AI assets. Ideal for use cases requiring local-first development, testing, and deployment of AI models, with git integration for seamless version control.

Canonical page: https://skillsregistry.net/skills/mr8lu-savile  
JSON: https://api.skillsregistry.net/v1/skills/mr8lu-savile

## Description

A high-fidelity, local-first MCP server and protocol for storing, versioning, syncing, and evaluating AI agent prompts and skills

## Trust

- **Trust score (0–1):** 0.83
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/mr8lu/savile)

## 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": "mr8lu-savile"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mr8lu-savile` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mr8lu-savile/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