ワンクリックで
review
Review implementation code for issues and produce a written report
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Review implementation code for issues and produce a written report
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Review an Equal Experts Gen AI Engineer take-home test submission (typically a RAG pipeline exercise) against the EE assessment rubric. Use when reviewing a candidate's Gen AI / LLM / RAG take-home test, assessing a retrieval-augmented-generation or prompt-engineering exercise, or scoring a THT for a Gen AI Engineer role.
Review an Equal Experts Backend Software Engineer take-home test submission against the EE assessment rubric. Use when reviewing a candidate's backend / general software engineering take-home test (non Gen AI), assessing a coding exercise submission, or scoring a THT for a backend role.
Generate a single-line commit message from conversation context and git diff, then optionally commit
Shared code and test patterns for the story pipeline skills
Write tests and implementation together for a user story
Final quality review producing a human-readable report
| name | review |
| description | Review implementation code for issues and produce a written report |
Review all code changes for a user story and produce an actionable report. Be thorough but pragmatic — only flag genuine issues, not style preferences already within the project's conventions.
$ARGUMENTS is the path to a story file.
Read the file at $ARGUMENTS. Understand the acceptance criteria — the review must verify the implementation satisfies them.
Before reviewing, understand what "correct" looks like:
Run git diff --name-only HEAD and git status --short to find all changed, staged, and untracked files. Include everything — implementation files, test files, schema changes, configuration.
Use the Read tool on each file. Read the full file, not just the diff — context matters for architectural correctness.
Evaluate the code against each of these categories:
Correctness
Security
Architecture
Test Quality
Code Style
Naming
Performance
Consistency
Derive story-slug from the story filename. Write to docs/reviews/{story-slug}/02-review.md:
# Code Review
**Story:** {story file path}
**Date:** {ISO date}
**Status:** {PASS | ISSUES_FOUND}
## Summary
{One paragraph overall assessment}
## Critical
{Must fix. Each finding with file path and description.}
- `path/to/file:line` — {description of issue and what to fix}
## Warnings
{Should fix. Lower severity but still worth addressing.}
- `path/to/file:line` — {description}
## Suggestions
{Optional improvements. Not blocking.}
- {suggestion}
## Acceptance Criteria Check
| Criterion | Status | Evidence |
| ----------- | --------- | ------------------------ |
| {criterion} | PASS/FAIL | {test or code reference} |
## Files Reviewed
- `path/to/file` — {brief description}
If there are no Critical or Warning findings, set Status to PASS. Otherwise ISSUES_FOUND.
After writing the report, output a brief summary: total findings by severity and the report file path.