# yuanzhu

> yuanzhu — ravenwangchina-yuanzhu. Use this tool when you need to automate recurring work into governed AI workflow assets, solving problems of inefficiency and lack of standardization in workflow management. It takes in recurring work processes and outputs governed AI workflow assets through its interface, which includes an MCP server, Claude Code plugin, and dsh plugin. Utilize yuanzhu in contexts where workflow optimization and AI-driven automation are crucial, such as in DevOps and IT operations.

Canonical page: https://skillsregistry.net/skills/ravenwangchina-yuanzhu  
JSON: https://api.skillsregistry.net/v1/skills/ravenwangchina-yuanzhu

## Description

Meta-Forge Workshop: turn recurring work into governed AI workflow assets. MCP server + Claude Code plugin + dsh plugin — staged writes, evals-gated forging, inference engine. 元铸工坊 SOSOFAST：把最佳实践铸成可治理的 AI 工作流资产

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** AGPL-3.0
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/RavenWangChina/yuanzhu)

## 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": "ravenwangchina-yuanzhu"
    }
  }
}
```

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