Requesting Code Review — The Quality Gate
> **Type:** Rigid for mandatory triggers, flexible for optional
Best use case
Requesting Code Review — The Quality Gate is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
> **Type:** Rigid for mandatory triggers, flexible for optional
Teams using Requesting Code Review — The Quality Gate should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/requesting-code-review/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Requesting Code Review — The Quality Gate Compares
| Feature / Agent | Requesting Code Review — The Quality Gate | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
> **Type:** Rigid for mandatory triggers, flexible for optional
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Requesting Code Review — The Quality Gate > **Type:** Rigid for mandatory triggers, flexible for optional > **Trigger:** After completing tasks, major features, or before merging ## Iron Law ``` NO MERGE WITHOUT CODE REVIEW — NO REVIEW WITHOUT COMPLETE WORK ``` ## Purpose Ensures code quality through structured review requests. Dispatches a code reviewer (subagent or human) with the right context to catch issues before they reach the main branch. ## When to Request Review ### Mandatory (always request): - Before merging any feature branch - After completing a major feature (3+ tasks) - Before deploying to production - When changing shared/core code ### Optional (use judgment): - After completing individual tasks (if complex) - For config/documentation changes - For refactoring-only changes ## Process ### Step 1: Prepare Review Context ``` - BASE_SHA: The commit before your changes - HEAD_SHA: Your latest commit - Changed files list: `git diff --name-only BASE..HEAD` - Summary: What was built and why ``` ### Step 2: Dispatch Code Reviewer Provide the reviewer with: - The spec/plan that was being implemented - The file diff (`git diff BASE..HEAD`) - Any known concerns or trade-offs - Test results (proof they pass) ### Step 3: Act on Feedback | Severity | Action | |----------|--------| | **Critical** | Fix immediately before proceeding | | **Important** | Fix before merging/completing | | **Minor** | Note for follow-up, don't block | | **Suggestion** | Consider, decide, document decision | ### Step 4: Re-Review if Needed If critical or important items were fixed: - Re-run tests (verification-before-completion) - Re-request review on the fixes only - Don't re-review the entire changeset ## Two-Stage Review Order When both spec compliance and code quality reviews are needed: ``` 1. SPEC COMPLIANCE FIRST → "Did we build what was requested?" 2. CODE QUALITY SECOND → "Is it well-built?" (only after spec compliance passes) ``` **NEVER reverse this order.** Code quality is meaningless if you built the wrong thing. ## Rationalization Table | Excuse | Reality | |--------|---------| | "Changes are too small for review" | Small changes still break things. Review catches what you missed. | | "I already reviewed my own code" | Self-review has blind spots. Fresh eyes catch issues you can't. | | "Review will slow us down" | Bugs slow us down more. Review is investment in quality. | | "The tests pass, so it's fine" | Tests verify behavior, not quality. Review catches design issues. |
Related Skills
Using Archon — The Gatekeeper
> **Type:** Meta-process (always active)
reviewer
Use when reviewing implementation output against a specification for compliance. Generates a comprehensive HTML/CSS report comparing code to spec requirements. Triggers on tasks involving spec compliance review, implementation verification, quality auditing, or when user asks to "review against spec" or "verify implementation".
Receiving Code Review — The Response Protocol
> **Type:** Rigid
pr-quality-agent
Self-reviewing PR quality agent that audits, rewrites, and iteratively improves GitHub PR bodies to production-grade quality. Use when crafting, reviewing, or upgrading PR descriptions for open-source projects. Triggers on "review my PR", "improve PR body", "PR quality", "make this PR perfect", "audit PR", or any PR body creation/upgrade task.
design-review
Design critique and review methodology including heuristic evaluation, consistency checking, accessibility compliance, and visual quality assessment. Use when reviewing design artifacts, evaluating UI quality, or auditing design compliance.
Content Quality Gate
> Automated content validation combining fast rule-based checks with optional AI-powered analysis.
Archon Adversarial Review
> Spawn an independent Opus sub-agent to stress-test Archon's architecture, hooks, synapses, and framework evolution decisions against its own design principles.
YAML Prompt Library
> Store reusable AI prompts as YAML files with structured messages, variables, and test data for version-controlled prompt engineering.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Writing Plans — TDD-Sized Task Breakdown
> **Type:** Rigid process (follow structure exactly)
wireframing
Wireframing patterns including layout grids, content blocks, responsive breakpoints, and page layout patterns for landing pages, dashboards, and forms. Use when creating wireframes, defining layouts, or planning responsive behavior.
windows-registry-editor
Expert Windows Registry editor and optimizer via PowerShell. Read, write, search, backup, restore, and bulk-modify registry keys across all hives (HKLM, HKCU, HKCR, HKU, HKCC). Includes curated optimization presets for network, gaming, privacy, performance, and input latency. Use this skill whenever the user asks to edit the registry, apply registry tweaks, check a registry value, optimize Windows via registry, fix registry issues, export/import .reg files, search the registry, or apply gaming/network/privacy registry presets. Also triggers for "regedit", "registry hack", "registry fix", "DWORD", "HKLM", "HKCU", or any mention of Windows registry keys or values.