audit-style

Flag design-rule violations in code diffs as non-blocking findings.

4|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/leocosta/octopus --skill audit-style-leocosta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audit-style
Source: https://github.com/leocosta/octopus/tree/main/skills/audit-style
Command: npx skills add https://github.com/leocosta/octopus --skill audit-style-leocosta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Flag design-rule violations in code diffs without blocking changes, helping reviewers surface conformity gaps to the house rules.

Core Features & Use Cases

  • Emission of two finding types: rule-violation for non-conforming changes and over-engineering for premature abstractions.
  • Non-blocking, signal-only feedback during codereview, pr-review, or implement steps.
  • Uses the repository’s design rules (exceptions, patterns, coding-style, active stack) as the source of truth and guides human decisions.

Quick Start

Run the audit-style check on the current diff to surface rule-violation and over-engineering findings.

Frequently Asked Questions about audit-style

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

FAQPage Schema
How do I flag design-rule violations in code diffs without blocking changes?

Run a signal-only audit on your code diff to emit non-blocking findings categorized as rule-violation or over-engineering. This surfaces conformity gaps against your team's house rules during code review without interrupting the pipeline.

What is over-engineering detection in static analysis?

Over-engineering detection in static analysis identifies premature abstractions in code changes. It functions as a non-blocking finding type emitted during code review to guide human decisions against unnecessary complexity.

Can I use diff analysis to check pull requests against my team's coding style?

Yes, you can use diff analysis to check pull requests against your team's coding style. The audit loads the repository's design rules, exceptions, and patterns as the source of truth to evaluate pull request changes.

How do I detect rule violations in a pull request review?

You detect rule violations in a pull request review by applying the repository's design rules to the code diff. The system evaluates the changes and emits findings to guide human reviewers without blocking the pull request.

Does non-blocking code review feedback work with existing static analysis tools?

Non-blocking code review feedback works alongside static analysis by loading the repository's design rules, exceptions, and coding-style references. It emits signal-only findings during implement or pr-review flows to guide human decisions.