five-axis-code-review
Helps your agent review code thoroughly. It focuses on correctness, security, clarity, performance, and tests, offering useful suggestions to improve the code.
What it does
This tool reviews programming code to ensure it's correct, secure, readable, fast, and well-tested. It points out specific issues with suggestions on how to fix them.
When to use it
- ✓When you want someone to review a piece of code.
- ✓When submitting a small change (diff) to a project.
- ✓When asking to check a pull request.
Example of what to ask your AI
“Please review this code. Is it correct, secure, and readable?”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The tool analyzes code across five areas: correctness, security, readability, performance, and tests. For each problem found, it suggests a concrete solution, focusing on useful fixes rather than minor style tweaks.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill five-axis-code-reviewOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/five-axis-code-review/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Code Review Checklist
One review answers a single question: "Will this code become someone else's problem within three months?" Walk the five axes in order; each axis gets pass / fail / N-A, and every failure must come with a concrete fix.
When to Use
- Use when the user asks to review code, a diff, or a pull request.
- Use when a review should stay actionable and skip style nitpicks.
Workflow
- Check the scope first: look at the diff size. Over ~400 changed lines, ask for a split before reviewing — review quality on huge diffs always collapses.
- Check axis by axis (order = priority):
- Correctness: edge cases (null, empty, zero, negative, oversized), concurrency/timing assumptions, error handling (are exceptions swallowed?). The only axis that can block a merge.
- Security: is user input concatenated into SQL / shell commands / HTML; are secrets or tokens hard-coded; does logging leak sensitive data.
- Readability: do names say what things are; does each function do one thing; are magic numbers named. Flag only what you can't understand — not "I'd write it differently."
- Performance: repeated queries or recomputation inside loops; N+1 problems; avoidable large-object copies. No data-free performance speculation ("this might get slow" is not a comment).
- Test coverage: does new logic have tests; do edge cases have cases. All-green tests with the critical path uncovered still get sent back.
- Write the comments: fixed format —
[axis] file:line problem → suggested fix. Only actionable suggestions; "could be optimized" is not one. - Triage:
Must fix(correctness / security) vsShould fix(readability / performance / tests). "Should fix" doesn't block the merge, but say so explicitly.
Rules
- At most 10 comments per review. More than that means the code is too broken — send it back for a rewrite instead of grading 50 items.
- No style policing: indentation, quotes, semicolons — that's the linter's job, not a human's.
- Speak with the diff: every comment must cite a concrete line of code. A comment without a code reference is invalid.
Checklist (minimal executable version)
## Code review checklist
- [ ] Correctness: edge cases (null/0/negative/oversized) handled, exceptions not swallowed
- [ ] Correctness: concurrency/timing assumptions hold, no races
- [ ] Security: no SQL/shell/HTML injection points, no hard-coded secrets, no sensitive data in logs
- [ ] Readability: names are descriptive, functions have a single responsibility, no magic numbers
- [ ] Performance: no repeated queries/computation in loops, no N+1, no evidence-free performance worries
- [ ] Tests: new logic is covered, edge cases have cases
- [ ] Scope: diff ≤ ~400 lines, otherwise split first
Example review comments:
[Must fix][Correctness] order.py:87 empty order list triggers IndexError → guard for empty before taking [0]
[Should fix][Readability] order.py:92 magic number 86400 → name it SECONDS_PER_DAY
Limitations
- Covers five review axes, not every quality dimension. Domain-specific correctness (financial rounding, protocol conformance, accessibility conformance) still needs its own specialist review.
- The five axes are heuristics for a human reviewer. A clean pass on the checklist does not prove the change is correct, secure, or performant.
- Security review here is a reading checklist, not a scanner. Static analysis, dependency audit and secret scanning run as separate tools.
- The skill reviews diffs; it cannot establish that requirements were met, and an empty findings list only means no finding was evidenced in the reviewed scope.
Anti-patterns
- ❌ Drive-by LGTM: approving before reading the whole diff — the review is theater.
- ❌ Style police: 18 of 20 comments about quotes and line breaks while a null-pointer dereference slips through.
- ❌ Comments without code: "this logic looks off" — which logic? Which line? Unsaid means invalid.
- ❌ Performance speculation: "this loop might be slow at scale" — a performance comment without data is noise.
- ❌ Grading 50 items: when there are too many problems to list, the right move is "rewrite and resubmit", not playing teacher.
FAQ
What are style 'nitpicks'?
These are minor suggestions about the code's appearance, like spacing or semicolons, that don't affect how it works but can be annoying.
What does 'block a merge' mean?
It means a change cannot be added to the main project until the pointed-out issues are fixed.
Does the tool find all types of errors?
No, it focuses on five main areas. Very domain-specific errors (like exact financial calculations) or complex security issues might need additional expert review.
Details
Original description by the author
Five-axis code review checklist (correctness, security, readability, performance, test coverage) producing actionable comments instead of style nitpicks. Use when the user asks to review code, a diff, or a pull request.
Popularity
- GitHub stars
- 48k
- Ranking position
- #3013
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
cpp-testing
Makes your agent write and improve tests for C++ code. It helps set up testing tools and fix errors.
affaan-m/ECC
csharp-testing
Helps your agent create tests for C# and .NET code. It uses best practices to ensure tests are efficient and reliable.
affaan-m/ECC
django-tdd
Enables your agent to apply testing strategies for Django with pytest-django and TDD. It's useful for writing robust tests and ensuring code quality, especially for DRF APIs.
affaan-m/ECC