# guard

> guard — wangshanbo-guard. Use this tool when you need to ensure AI systems operate within established policies and contracts, preventing potential misuses or errors. Guard provides a policy and contract layer for AI development, integrating with Rust and MCP servers to enforce responsible AI behavior. It is ideal for use cases requiring strict adherence to guidelines, such as high-stakes AI applications, and can be easily installed into existing Cursor or Claude Code setups.

Canonical page: https://skillsregistry.net/skills/wangshanbo-guard  
JSON: https://api.skillsregistry.net/v1/skills/wangshanbo-guard

## Description

Policy / contract layer for AI development. MCP gives AI hands, Skills gives AI experience, Guard makes sure AI does not do the wrong thing. Rust + MCP server. One-line install into Cursor / Claude Code.

## Trust

- **Trust score (0–1):** 0.76
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/wangshanbo/guard)

## 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": "wangshanbo-guard"
    }
  }
}
```

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