04 Audit

Audit a codebase read-only across seven quality pillars into one ranked report. Use when the user wants to assess, health-check, or audit a codebase or one pillar. Not for fixing findings, reviewing a change, or checking a feature works.

564 stars 65 forksSoftware Development Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add ai-driven-dev/framework

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ai-driven-dev/framework --skill 04-audit
Manual install
git clone --depth 1 https://github.com/ai-driven-dev/framework.git /tmp/framework
mkdir -p ~/.claude/skills
cp -r /tmp/framework/plugins/aidd-dev/skills/04-audit ~/.claude/skills/04-audit

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Skill: audit

Diagnose a codebase against quality pillars and emit one ranked findings report. Read-only: it identifies and ranks problems, never changes code.

## Actions

| #   | Action         | Pillar       | Lens                                                                 |
| --- | -------------- | ------------ | -------------------------------------------------------------------- |
| 01  | `code-quality` | code-quality | Clean code (naming, SOLID, DRY, readability, smells) and tech debt (dead code, complexity, file/function size, error handling) |
| 02  | `architecture` | architecture | Conformance to C4 / ADRs, coupling, boundaries, layering             |
| 03  | `security`     | security     | OWASP risks, authz, input validation, secrets in code                |
| 04  | `dependencies` | dependencies | CVEs, licenses, outdated and unused deps, supply chain               |
| 05  | `performance`  | performance  | N+1 queries, hot paths, bundle size, heavy operations                |
| 06  | `tests`        | tests        | Critical-path coverage, flakiness, test pyramid balance              |
| 07  | `ui`           | ui           | Loading/error/empty states, visual hierarchy, design-system drift, responsive, a11y |

Run the one pillar named, or offer all seven when the request is unscoped.
Before running an action, read its file in `actions/`, not only the table or assets.

## Transversal rules

- Read-only: diagnose and rank, never edit code.
Read the full skill on GitHub

Details

Skill name
04-audit
Path
plugins/aidd-dev/skills/04-audit/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the 04 Audit skill do?

Audit a codebase read-only across seven quality pillars into one ranked report. Use when the user wants to assess, health-check, or audit a codebase or one pillar. Not for fixing findings, reviewing a change, or checking a feature works.

How do I install the 04 Audit skill?

Claude Code plugin: /plugin marketplace add ai-driven-dev/framework. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is 04 Audit popular?

It lives in ai-driven-dev/framework, which has 564 GitHub stars and 65 forks.

Related skills

00 Async Dev

564

ai-driven-dev/framework

Drive the async-dev pipeline from one entry point, whether setup, run, or review. Use when the user wants to install async dev, run a ready issue, or address PR review comments, or on a webhook trigger. Not for plain status checks.

Git & Code Review65

00 Init

564

ai-driven-dev/framework

Turn AIDD measurement on for a project after explicit consent, stop it, choose to be named on your own measurement, or delete what was measured. Use when the user wants to start or stop measuring what their work consumes, add or remove their name, or forget measured data. Not for answering what a period consumed.

Other65

00 Onboard

564

ai-driven-dev/framework

Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface.

Other65

05 Review

564

ai-driven-dev/framework

Reviews work and says whether it is ready, naming each defect with its fix. Use when the user wants a change or diff reviewed. Not for fixing what the review finds, and not for auditing a whole codebase.

Software Development65

03 Assert

564

ai-driven-dev/framework

Assert the work against the project's coding assertions into a pass or fail report. Use to verify an implementation. Not for fixing code, reviewing a diff, or writing tests.

Software Development65

07 Refactor

564

ai-driven-dev/framework

Improve code across four axes (cleanup, performance, security, architecture) by scanning and fixing, or applying a pushed audit report. Use when the user wants to refactor, optimize, harden, or remove code. Not for read-only diagnosis or adding tests.

Software Development65

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.