aped-review

Community

Adversarially review code with evidence

Authoryabafre
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It helps you catch specification gaps, code quality issues, boundary bugs, and hallucinated identifiers before merging by running a disciplined, evidence-first review workflow on an APED story.

Core Features & Use Cases

  • Evidence-driven adversarial review: Validates that acceptance criteria and completed tasks have concrete test and code evidence.
  • Surface-aware auditing: Applies security, performance, reliability, and test-quality checks tailored to backend, frontend, infra, or cross-layer changes.
  • Boundary and hallucination detection: Audits edge cases and flags newly introduced production identifiers that are not actually implemented.
  • Frontend visual validation (optional): Conditionally performs a visual check via React Grab when applicable.

Quick Start

Use the aped-review skill to review a story by saying review code and providing the story key if you have it.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: aped-review
Download link: https://github.com/yabafre/aped-claude/archive/main.zip#aped-review

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.