audit

Spawn parallel agents to audit codebase quality dimensions and produce a scored report.

3|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/willietran/autoboard --skill audit-willietran
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audit
Source: https://github.com/willietran/autoboard/tree/main/skills/audit
Command: npx skills add https://github.com/willietran/autoboard --skill audit-willietran

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep, multi-agent codebase quality audits surface strengths, weaknesses, and risks with an evidence-based synthesis, enabling teams to understand and improve their codebase holistically.

Core Features & Use Cases

  • Spawns one focused agent per quality dimension in parallel, each going deep with evidence-based analysis
  • Synthesizes findings into a final scored report to guide remediation and decision-making
  • Supports --checkpoint mode for layer coherence audits during orchestration to catch cross-session issues

Quick Start

Run the audit skill in the current working directory to perform a full, multi-dimension quality audit.

Frequently Asked Questions about audit

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

FAQPage Schema
How do I perform a multi-agent codebase audit on a monorepo?

A multi-agent codebase audit automates evidence-based analysis by spawning one focused agent per quality dimension. These agents independently analyze the monorepo, surface dimensional issues, and synthesize findings into a final scored report.

What is the best way to review code quality across multiple languages in a single project?

Reviewing code quality across multiple languages is handled by orchestration-driven workflows that spawn parallel agents. Each agent goes deep into specific dimensions, comparing patterns and risk areas across the full multi-language codebase to produce a scored synthesis.

How does checkpoint mode work for architecture layer coherence audits?

Checkpoint mode supports layer coherence audits during orchestration by catching cross-session issues. It evaluates architectural layer consistency across active sessions, ensuring dimensional quality patterns remain coherent throughout the multi-agent workflow.

Can I use static analysis to find architectural risk areas in a large codebase?

Static analysis through multi-agent static review surfaces architectural risk areas by independently evaluating quality dimensions. The parallel agents gather evidence-based findings across the entire codebase, highlighting dimensional weaknesses and patterns.

Does multi-agent code review work for multi-language projects?

Multi-agent code review explicitly supports multi-language projects and monorepos. The orchestration-driven workflow applies dimensional analysis across the full codebase independently of language constraints, producing a unified scored report.