Skip to content
Skills Library
Programming · Review & audit

code-review

/code-review

Performs a quick, lightweight review of a small diff or single file, giving concise feedback on correctness, readability, tests, and obvious risks. Use when the user asks for a fast sanity-check review of a small change. For test-automation suites, architectural refactors, security-sensitive paths, or multi-file reviews, use the code-review-advanced skill instead.

Licence
MIT
Last repository change
26.08.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.08.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Performs a quick, lightweight review of a small diff or single file, giving concise feedback on correctness, readability, tests, and obvious risks. Use when the user asks for a fast sanity-check review of a small change. For test-automation suites, architectural refactors, security-sensitive paths, or multi-file reviews, use the code-review-advanced skill instead.

Arguments

/code-review The diff, file, or snippet to review, plus the goal of the change
Original author description

Performs a quick, lightweight review of a small diff or single file, giving concise feedback on correctness, readability, tests, and obvious risks. Use when the user asks for a fast sanity-check review of a small change. For test-automation suites, architectural refactors, security-sensitive paths, or multi-file reviews, use the code-review-advanced skill instead.

How it works

  1. When to Use
  2. Skill Behavior
  3. Quick Review Checklist
  4. Output Style
  5. Related Skills
  6. Definition of Done
Original SKILL.md headings · 84 lines, 483 words
SKILL.md preview
---
name: code-review
description: 'Performs a quick, lightweight review of a small diff or single file, giving concise feedback on correctness, readability, tests, and obvious risks. Use when the user asks for a fast sanity-check review of a small change. For test-automation suites, architectural refactors, security-sensitive paths, or multi-file reviews, use the code-review-advanced skill instead.'
argument-hint: 'The diff, file, or snippet to review, plus the goal of the change'
user-invocable: true
---

# Quick Code Review

This skill applies a consistent, lightweight assessment to a small code change. It focuses on key principles of code quality:

- Safety (avoid incorrect assumptions; call out uncertain areas)
- Clarity (structuring comments in positive and actionable form)
- Coverage (address correctness, tests, security, performance, readability)

## When to Use

1. The user asks for a quick review of a small diff, single file, or snippet.
2. A change needs a fast sanity check before a fuller review.
3. You need a compact checklist for a routine, low-risk change.

For large or multi-file pull requests, legacy audits, test-automation suites, or high-risk paths (auth, payments, data flows), use `code-review-advanced` instead.

## Skill Behavior

- Start with a summary: what is changing, why, and whether the implementation is aligned with goals.
- Categorize findings:
  - ✅ Strengths / wins
  - ⚠️ Concerns / risks
  - 🛠️ Suggestions / improvements
- Provide `short-term` fix guidance plus `long-term` design thoughts.
- Flag any missing tests, docs, or standards violations.
- Respect context: mention the module/file/function names (not generic: "the code").

## Quick Review Checklist

1. **Correctness**
   - Does the code do what the ticket/PR describes?
   - Are edge cases handled (null, errors, concurrency, format)?
   - Any regression risk from changed behavior?

2. **Maintainability**
   - Is the implementation easy to read and reason about?
   - Are abstractions and naming appropriate?
   - Any repeated logic that should be refactored?

3. **Testing**
   - Are unit and integration tests present and relevant?
   - Do tests cover both normal and boundary cases?
   - Are tests deterministic and fast?

4. **Security & Privacy**
   - Are user inputs validated/escaped and untrusted data treated carefully?
   - Any secrets in code, logs, or config?
   - Does the change introduce new permissions, cross-origin, or auth gaps?

5. **Performance**
   - Any obvious O(N^2) loops or hot-path allocations?
   - Are caching and batching used when appropriate?
   - For network I/O, is retry/backoff and timeout handling present?

6. **Style/Convention**
   - Follow team linting rules and style guide (naming, indent, line length).
   - Approve clean diff with minimal noise in formatting.

7. **Documentation**
   - Public APIs should be documented.
   - Migration notes, config docs, and README changes included if needed.

## Output Style

- Keep each comment concise (1-2 sentences plus the issue).
- Use bullet points for multiple issues.
- Use neutral, teammate-first language (`Consider`, `Could`, `Would` instead of `You`).
- Include a final recommendation state: `approve`, `request changes`, or `comment`.

## Related Skills

- `code-review-advanced` - evidence-driven, severity-ranked review for complex, risky, or multi-file changes
- `tech-debt-analysis` - when recurring review findings suggest a broader debt assessment

## Definition of Done

This skill is complete when:

- the change is summarized with intent and alignment stated
- findings are categorized (strengths, concerns, suggestions) with concrete file/function references
- missing tests or docs are flagged
- a final recommendation (`approve`, `request changes`, or `comment`) is given

Versions

RepositoryScoreLicence
This page · jaktestowac/awesome-copilot-for-testers90MIT
microsoft/aspire100MIT
kdlbs/kandev100AGPL-3.0
dotnet/runtime100MIT
drosam/agents100MIT
ggml-org/llama.cpp100MIT
ShamelesAbyss/Nyx100Apache-2.0
dzhng/jevgrep100MIT
iuliandita/skills100MIT

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 0162c9aff2e0 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100code-review-advanced
    Performs evidence-driven code review for pull requests, legacy modules, and quality-critical changes. Use when reviewing complex or multi-file changes, test automation suites, architectural refactors, or hot paths that need analysis of correctness, maintainability, security,…
  • 100review-code
    Multi-dimensional code review with structured reports. Analyzes correctness, readability, performance, security, testing, and architecture. Triggers on "review code", "code review", "审查代码", "代码审查".
  • 100review
    Use when source code needs a quality / security / correctness pass — pre-merge review, post-implementation sanity check, or focused look at a small file set — over a small file set the worker reads together
  • 90Code Review
    Use when reviewing a diff, pull request, or patch - correctness and edge cases, security, API and data model changes, test quality, performance, error handling, and readability. Also covers writing review comments that are actionable and prioritised, giving an approval,…
  • 90wasp-review
    Review code changes for correctness, clarity, and potential issues. Use when the user asks for a review, code review, PR review, or wants feedback on a diff or file.
  • 90code-review-and-quality
    Conducts multi-axis code review across correctness, readability, architecture, security, and performance. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Triggers on "review my PR", "review this diff", "code review", "review…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.