Skills requesting-code-review
📝

requesting-code-review

Safe ⚙️ External commands

Request AI Code Review

Also available from: davila7,DMJGilbert,DYAI2025,Cygnusfear,obra,Cycleaddict,CodingCossack

Developers often miss issues in their own code because they are too close to the implementation. This skill dispatches an AI subagent to review code changes against requirements, checking quality, architecture, testing, and production readiness before merging.

Supports: Claude Codex Code(CC)
🥉 74 Bronze
1

Download the skill ZIP

2

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

3

Toggle on and start using

Test it

Using "requesting-code-review". Request code review for my authentication module changes

Expected outcome:

### Strengths
- Clean separation of concerns with auth service (auth.ts:1-50)
- Proper password hashing using bcrypt (hash.ts:15)
- Good test coverage for edge cases

### Issues

#### Important
1. **Missing token expiration check**
- File: auth.ts:45
- Issue: Tokens never expire, creating security risk
- Fix: Add expiration timestamp to JWT payload

#### Minor
1. **Inconsistent error messages**
- File: auth.ts:30-35

### Assessment
**Ready to merge: With fixes**

**Reasoning:** Core authentication logic is solid. Important issue with token expiration must be addressed before production use.

Using "requesting-code-review". Review my database migration changes

Expected outcome:

### Strengths
- Proper foreign key constraints (migrations/002.sql:20)
- Good rollback strategy

### Issues

#### Critical
1. **No backup before destructive operation**
- File: migrations/003.sql:15
- Issue: DROP TABLE without backup strategy
- Fix: Add data migration script or backup step

### Assessment
**Ready to merge: With fixes**

**Reasoning:** Critical data safety issue must be resolved.

Security Audit

Safe
v1 • 2/24/2026

All 27 static findings are false positives. The skill uses legitimate git commands (git diff, git rev-parse) for code review - these are standard development operations. The detected 'weak cryptographic algorithm' patterns match the word 'security' in documentation headings, not actual crypto code. The 'system reconnaissance' matches are generic text. This is a safe code review workflow skill with no command injection risk - git commands use hardcoded arguments with template variable placeholders.

2
Files scanned
253
Lines analyzed
1
findings
1
Total audits

Risk Factors

⚙️ External commands (5)
code-reviewer.md:25-28 code-reviewer.md:112 SKILL.md:27-41 SKILL.md:51 SKILL.md:56-57

Detected Patterns

Git Command Execution (False Positive)Security Keyword Match (False Positive)Generic Text Pattern Match (False Positive)
Audited by: claude

Quality Score

38
Architecture
100
Maintainability
87
Content
50
Community
100
Security
91
Spec Compliance

What You Can Build

Pre-merge code review

Use before merging feature branches to catch issues early. The subagent reviews all changes against requirements and provides a clear ready/not-ready verdict.

Subagent task verification

After each subagent completes a task in agent-driven development, dispatch the code reviewer to verify the work before proceeding to the next task.

Stuck on a problem

When stuck on a complex bug or feature, request a code review to get a fresh perspective from the AI subagent on potential issues or better approaches.

Try These Prompts

Basic code review request 
Request code review for the changes I just made. Use the requesting-code-review skill with: WHAT_WAS_IMPLEMENTED: [describe what you built], PLAN_OR_REQUIREMENTS: [link to plan or describe requirements], BASE_SHA: [starting commit], HEAD_SHA: [ending commit], DESCRIPTION: [brief summary]
Full feature review 
Please review my latest feature implementation using the requesting-code-review skill. Compare against the requirements in docs/plans/[feature-name].md. Include architecture assessment and testing coverage evaluation.
Post-subagent task review 
Run the code-reviewer subagent to verify the task just completed. Check against the original task requirements and report any Critical or Important issues that need fixing before proceeding.
Pre-refactoring baseline 
Request a code review of the current state of [component/module] before I refactor it. This will serve as a baseline to ensure the refactoring does not introduce regressions.

Best Practices

  • Provide clear requirements or plan reference when requesting review - the subagent compares implementation against these
  • Review after each significant task in agent-driven development to catch issues before they compound
  • Fix Critical and Important issues before proceeding; address Minor issues in follow-up work

Avoid

  • Skipping review because the change seems simple - even small changes can have subtle bugs
  • Ignoring Critical issues or proceeding with unfixed Important issues
  • Requesting review without providing clear requirements or plan for the subagent to compare against

Frequently Asked Questions

How does this skill differ from using Claude directly?
This skill dispatches a specialized code-reviewer subagent with a structured review template. It provides consistent, comprehensive reviews with severity categorization and production readiness assessment.
Can I use this for any programming language?
Yes. The review checklist covers general code quality, architecture, and testing principles that apply across languages. The subagent adapts its feedback based on the code it reviews.
What if I do not have a formal requirements document?
Provide any existing documentation, ticket description, or even a clear summary of what the feature should do. The more context you give, the better the review.
Does this replace human code review?
No. This is an AI-assisted review that catches many issues early. Human review remains valuable for context, team conventions, and domain-specific knowledge.
How do I get the BASE_SHA and HEAD_SHA?
Use git commands: BASE_SHA=$(git rev-parse HEAD~1) or a specific commit, HEAD_SHA=$(git rev-parse HEAD) for latest. Or use origin/main for comparing against main branch.
Can I customize the review criteria?
The code-reviewer.md template can be modified to add team-specific checks, language-specific guidelines, or additional review criteria.

Developer Details

Author

ZhanlinCui

License

MIT

Repository

https://github.com/ZhanlinCui/Ultimate-Agent-Skills-Collection/tree/main/requesting-code-review

Ref

main

File structure

📄 code-reviewer.md

📄 SKILL.md