md-audit

Agent Skills › chaitanyagiri/munder-difflin › md-audit

md-audit

GitHub

对当前工作目录进行只读代码质量审计，扫描常见漏洞、死代码及安全热点，生成按严重程度排序的发现报告，不修改任何文件。

resources/skills/md-audit/SKILL.md chaitanyagiri/munder-difflin

Trigger Scenarios

audit the code quick audit find issues code scan what's wrong with this codebase

Install

npx skills add chaitanyagiri/munder-difflin --skill md-audit -g -y

More Options

Non-standard path

npx skills add https://github.com/chaitanyagiri/munder-difflin/tree/main/resources/skills/md-audit -g -y

Use without installing

npx skills use chaitanyagiri/munder-difflin@md-audit

指定 Agent (Claude Code)

npx skills add chaitanyagiri/munder-difflin --skill md-audit -a claude-code -g -y

安装 repo 全部 skill

npx skills add chaitanyagiri/munder-difflin --all -g -y

预览 repo 内 skill

npx skills add chaitanyagiri/munder-difflin --list

SKILL.md

Frontmatter

{
    "name": "md-audit",
    "version": "1.0.0",
    "description": "Read-only code quality audit — scan the current working directory for common\nissues (bugs, dead code, security hotspots, missing error handling) and return\na prioritised findings report. No files are edited.\nUse when asked to \"audit the code\", \"quick audit\", \"find issues\", \"code scan\",\nor \"what's wrong with this codebase\". (munder-difflin)\n",
    "allowed-tools": [
        "Read",
        "Bash",
        "Grep"
    ]
}

Code Audit (read-only)

Perform a read-only code quality scan and return a findings report. Do NOT edit any files.

Steps:

Scope — identify the primary language and entry points (package.json, Cargo.toml, go.mod, pyproject.toml, or similar).
Scan — use Grep and Read to look for:
- Unhandled promise rejections / ignored errors
- Hard-coded secrets or credentials (keys, tokens, passwords)
- TODO/FIXME/HACK comments that signal known debt
- Dead exports (exported symbols with no in-repo import)
- Obvious type-safety gaps (unchecked any, missing null guards)

Report — output a findings list sorted by severity (Critical → High → Medium → Low):

## Audit Report — <project name>

### Critical
- [file:line] <description>

### High
- ...

### Summary
<total count> findings across <file count> files scanned.