skills.rest
MayMustAI
MayMustAIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

self-review

Analyze pull requests to verify declared intent against actual code changes.

1|Updated Apr 22, 2026
Search Tags:#code-review#pull-request#pr-review#structured-feedback#diff-analysis#self-review#intent-vs-implementation
One-click install
npx skills add https://github.com/MayMustAI/ai-dev-playbook --skill self-review-maymustai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: self-review
Source: https://github.com/MayMustAI/ai-dev-playbook/tree/main/plugins/maymust/skills/self-review
Command: npx skills add https://github.com/MayMustAI/ai-dev-playbook --skill self-review-maymustai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps you review a PR by comparing the author-intended Why/Design decisions/Out of scope with the actual implementation in the diff, producing a structured review of alignment, edge cases, complexity, and testing gaps.

Core Features & Use Cases

  • Applies the 5-step loop to validate that the PR's stated intent matches the implemented changes.
  • Generates structured feedback such as blockers, must-fix items, nitpicks, and positives, guiding faster and safer PR merges.
  • Handles session bias warnings and enforces a consistent, review-ready format.

Quick Start

Call the self-review command on your current PR to initiate the structured intent-vs-implementation review.

Frequently Asked Questions about self-review

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

FAQPage Schema
How do I automate PR review to check intent vs implementation alignment?▼

Automate PR review by applying a structured loop to compare the author's declared intent and design decisions against the actual diff changes. This validates alignment and produces structured feedback including blockers and must-fix items.

What is the best way to generate structured pull request feedback for blockers and nitpicks?▼

Generate structured pull request feedback by analyzing the diff and design notes to categorize findings into blockers, must-fix items, nitpicks, and positives. This enforces consistent review criteria and handles ambiguous statements.

Can I review a pull request when design notes or out-of-scope sections are missing?▼

Yes, you can review a pull request with missing sections. The analysis handles cases where design notes or out-of-scope statements are ambiguous or absent while still producing a structured review of edge cases and testing gaps.

How does diff analysis handle session bias during a self-review?▼

Diff analysis handles session bias by applying a consistent 5-step loop to validate intent against implementation. It enforces a review-ready format and issues session bias warnings to ensure objective feedback.

What are the limitations of automated intent-vs-implementation PR reviews?▼

Limitations include dependency on the clarity of the author's declared intent. If design notes are ambiguous or missing, the review focuses solely on diff analysis, potentially missing unstated edge cases or complexity issues.

Related Skills

Explore More Software Engineering Skills→
aurora-atomsaurora-atoms

reviewer-rehearsal

Identify design risks and missing evidence in software changes for formal review.

Community
Advanced
1natsu1721natsu172
1

1natsu-pr-review-handler

Automate GitHub PR reviews by reading comments, applying fixes, and posting replies.

Community
Advanced
nullmastermindnullmastermind
9

test

Plan and scope testing work with coverage maps and prioritized task lists.

Community
Intermediate
R2W1csR2W1cs
1

lint-and-validate

Lint and validate JavaScript and Python code for syntax and style issues.

Community
Intermediate