# Diffguard

> Use this tool when you need to automate code review and ensure high-quality code submissions. DiffGuard analyzes code changes through Git Hook or GitHub Webhook, providing multi-dimensional AI-powered review and blocking problematic commits. It helps solve issues like code errors, security vulnerabilities, and formatting inconsistencies, making it ideal for pre-commit, pre-push, and pull request scenarios.

Canonical page: https://skillsregistry.net/skills/eleven-mouse-diffguard  
JSON: https://api.skillsregistry.net/v1/skills/eleven-mouse-diffguard

## Description

DiffGuard 是一个面向开发团队的 AI 代码审查系统，通过 分层审查编排、AST 语义理解 和 代码知识图谱 提供深度、精准的自动化 Code Review。

## Trust

- **Trust score (0–1):** 0.40
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-02

## Source

- **Source listing:** [GitHub](https://github.com/Eleven-Mouse/Diffguard)

## 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": "eleven-mouse-diffguard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/eleven-mouse-diffguard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/eleven-mouse-diffguard/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