audit

Generate structured AUDIT.md reports from codebase audit targets.

1|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/kelsi-andrewss/claude-multi-agent-pipeline --skill audit-kelsi-andrewss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audit
Source: https://github.com/kelsi-andrewss/claude-multi-agent-pipeline/tree/main/skills/audit
Command: npx skills add https://github.com/kelsi-andrewss/claude-multi-agent-pipeline --skill audit-kelsi-andrewss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits a codebase and generates a comprehensive, structured AUDIT.md report via an autonomous agent that reads targets, scopes, and open stories to surface actionable findings.

Core Features & Use Cases

  • Scope-aware auditing: supports full-project audits, targeted file/directory scopes, story-diff analysis, and time-bounded queries.
  • Cross-reference and traceability: links findings to open stories and writes annotations for traceability.
  • Flexible outputs: produces AUDIT.md by default, with optional JSON output and append mode.

Quick Start

Run the audit with your targets to generate a complete report.

Frequently Asked Questions about audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a structured codebase audit report for my repository?

You can generate a codebase audit report by running an autonomous agent that parses your repository targets, resolves the project root, and writes a structured AUDIT.md file with actionable findings and traceability annotations.

Can I audit only specific files or branches instead of the full codebase?

Yes, scope-aware auditing supports targeted file and directory scopes, branch story-diff analysis, and time-bounded queries, allowing you to audit specific repository sections instead of running a full-project scan.

What is codebase diff-analysis and how does it link to open stories?

Codebase diff-analysis evaluates branch changes and cross-references them with open stories, linking audit findings to those stories to provide traceability and context for the generated report.

Does the audit report support JSON output or appending to existing files?

Yes, the audit process produces an AUDIT.md file by default but also supports optional JSON output and append mode, allowing you to integrate findings into existing documentation or structured data pipelines.

What do I need to locate before starting an automated codebase audit?

Before starting an automated codebase audit, you need to define your audit targets and ensure the agent can resolve the project root and locate a requirements document to cross-reference during the analysis.