skills.rest
yabafre
yabafreCOMMUNITY
Explore all skills by this author →
GitHub

aped-review

Audit APED story tests, code, boundaries, and production identifier consistency.

2|Updated Mar 12, 2026
Search Tags:#code review#acceptance criteria#visual review#test evidence#boundary testing#adversarial auditing
One-click install
npx skills add https://github.com/yabafre/aped-claude --skill aped-review
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: aped-review
Source: https://github.com/yabafre/aped-claude/tree/main/src/templates/skills/aped-review
Command: npx skills add https://github.com/yabafre/aped-claude --skill aped-review

SYSTEM DOCUMENTATION & REQUIREMENTS

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.

Frequently Asked Questions about aped-review

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

FAQPage Schema
How do I verify test evidence and acceptance criteria during code review?▼

Adversarial code review catches specification gaps, boundary bugs, and hallucinated production identifiers by validating that acceptance criteria have concrete test and code evidence before merging.

How do I review code for boundary bugs and unimplemented production identifiers?▼

Review code for boundary bugs by auditing edge cases and adversarially validating that newly introduced production identifiers are actually implemented, flagging any hallucinated references before merging.

Does this code review workflow support both backend and frontend changes?▼

This code review workflow supports backend, frontend, infra, and cross-layer changes by applying security, performance, and reliability checks tailored to each surface, with optional visual validation for eligible frontend stories.

How do I perform a visual review for frontend stories?▼

Perform a visual review for eligible frontend stories by conditionally triggering a visual check via React Grab, validating that the UI matches the expected output alongside the standard test evidence gate.

What is an evidence gate in adversarial code review?▼

An evidence gate in adversarial code review is a strict validation step requiring fresh context loading and concrete test or code proof before producing a verdict of approved or changes requested.

When should I not use automated adversarial auditing for code review?▼

Avoid automated adversarial auditing when you lack a review-status APED story file to update, as this workflow requires driving fix iterations and reflecting unresolved findings inside the story record.

Related Skills

Explore More Software Engineering Skills→
wsmanwsman
18

story-done

Verify development story completion against acceptance criteria and governance artifacts.

Community
Advanced
bricerisingbricerising
7

review

Run a four-phase adversarial code review with evidence-backed findings and verdicts.

Community
Advanced
NEXUZ-SYSNEXUZ-SYS
1

autonomous-loop

Automate story execution in PREVC with agent dispatch and TDD gates.

Official
Advanced
robotijnrobotijn
3

ai-code-quality-reviewer

Detect AI-specific code flaws like hallucinated imports and vacuous assertions.

Community
Advanced