Automated summary
Reviews a pull request diff and produces a severity-ordered review covering correctness, security, maintainability, and tests.
Strengths
- Enforces a fixed output template with Critical/Suggestion/Nice-to-have levels and precise issue locations
- Includes a focused security pass (injection, XSS/CSRF, authz, SSRF, secrets in logs, CORS)
- Aligns findings with repo guidance files such as STYLE.md, SECURITY.md, and CONTRIBUTING.md
- Ends with a clear decision: approve, request changes, or needs follow-up
Limitations
- Cannot run tests or browse the repo; it relies entirely on the diff the user pastes in
- Suggested test commands are guesses when the tooling isn't visible in the diff
- No described integration with GitHub/GitLab APIs to post review comments
Use it when you want a rigorous, prioritized review of a patch, diff, or PR description before merging.
Avoid it for full architecture rewrites or design reviews, since it only analyzes a change set.
Security analysis
SafeThis skill only provides code-review instructions and does not declare or request tools, execute commands, access networks, handle secrets, or perform destructive actions. It asks the model to review supplied diffs and reference local documentation for standards, which is low-risk editorial behavior.
No concerns found
How this analysis is madeExamples
Here's the diff for our checkout service refactor — please review it for correctness, security, and missing tests. We're aiming for ready-to-merge. [paste diff]Review this PR that adds user input handling to our Express API. Focus on injection, XSS, and authorization mistakes, and tell me if you'd approve or request changes.Early review please — repo is a Go service, nothing needs to be polished yet. Here's the patch that adds a new caching layer; flag critical issues and test gaps.name: code-review description: Reviews pull request diffs for correctness, security, maintainability, and test coverage. Use when the user asks for a code review of a change set, patch, or PR description.
Code Review
Instructions
When reviewing a diff/PR, follow this flow:
-
Clarify context (if missing)
- Ask for the repo name, language/framework, and what “done” means (e.g., “ready to merge” vs “early review”).
- If the user did not provide a diff, ask them to paste the relevant patch or describe the files/behavior changed.
-
Summarize the change
- Provide a 2–5 sentence summary of what changed and the most important impact.
-
Identify issues with severity
- Report issues in this order: Critical, Suggestion, Nice-to-have.
- For each issue, include:
severity,area(correctness/security/performance/maintainability/tests/style),location(file path and the changed symbol/section when possible), andwhy it matters. - Prefer specific, actionable fixes over general guidance.
-
Security review
- Check for common risks relevant to the language/framework: injection (SQL/NoSQL/command), XSS/CSRF, authz/authn mistakes, unsafe deserialization, SSRF, secrets in logs, and overly-permissive CORS.
- If user input handling exists, validate, sanitize/escape appropriately, and enforce allow-lists where possible.
-
Correctness & robustness
- Look for broken invariants, edge cases, race conditions, timezone/locale bugs, error handling, and inconsistent data types.
- Verify new/modified code paths are exercised by the change.
-
Maintainability
- Check naming, complexity, duplication, API boundaries, and whether abstractions match existing patterns.
- Flag “spaghetti logic” or overly broad functions/modules.
-
Tests & quality gate
- Identify missing/weak tests that would have caught the issues you found.
- If the repo has test tooling detectable from the diff (e.g.,
jest,vitest,pytest,go test,npm test), suggest the most likely command(s) to run. - If you cannot infer a command reliably, list what to test instead (unit/integration/E2E) without guessing exact commands.
-
Close-out recommendation
- End with a short decision suggestion: “Approve”, “Request changes”, or “Needs follow-up” based on Critical items.
Output Template
Use this structure by default:
Summary
- ...
Critical
- [file/path] <what> — <why> — Fix: <specific change>
Suggestion
- [file/path] <what> — <why> — Fix: <specific change>
Nice-to-have
- [file/path] <what> — <why> — Improvement: <specific change>
Test plan (what to run / what to add)
- ...
Recommendation
- Approve / Request changes / Needs follow-up
Standards
- If the repo contains a style guide or security guidelines (commonly
docs/STYLE.md,STYLE_GUIDE.md,SECURITY.md, orCONTRIBUTING.md), align findings and fix suggestions to those documents.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/code-review-mrwakfz9/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/code-review-mrwakfz9' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/code-review-mrwakfz9/download' --output '.skill-downloads/code-review-mrwakfz9/SKILL.md.part' && mv '.skill-downloads/code-review-mrwakfz9/SKILL.md.part' '.skill-downloads/code-review-mrwakfz9/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/code-review-mrwakfz9/SKILL.md' && test -s '.skill-downloads/code-review-mrwakfz9/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/code-review' && cp -R '.skill-downloads/code-review-mrwakfz9' '.claude/skills/code-review'Cursor
test -f '.skill-downloads/code-review-mrwakfz9/SKILL.md' && test -s '.skill-downloads/code-review-mrwakfz9/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/code-review' && cp -R '.skill-downloads/code-review-mrwakfz9' '.cursor/skills/code-review'Codex
test -f '.skill-downloads/code-review-mrwakfz9/SKILL.md' && test -s '.skill-downloads/code-review-mrwakfz9/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/code-review' && cp -R '.skill-downloads/code-review-mrwakfz9' '.agents/skills/code-review'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/code-review-mrwakfz9'openskills read 'code-review-mrwakfz9'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/code-review-mrwakfz9/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.