Skip to content
Skills Library
Programming · Review & audit

code-review

/code-review

Use when reviewing a pull request, diff, or branch. Produces severity-ranked findings covering correctness, security, performance, and maintainability, with concrete fixes rather than opinions. Trigger on "review this pr", "look over my diff before i push", "is this branch ready to merge", "anything wrong with this change". Do not use for a vulnerability-focused audit — see the security-review skill; for feature release readiness, see the qa-review skill.

Licence
MIT
Last repository change
24.10.2026

Assessment and security

100/ 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.
Content35 / 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 24.10.2026, 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

Use when reviewing a pull request, diff, or branch. Produces severity-ranked findings covering correctness, security, performance, and maintainability, with concrete fixes rather than opinions. Trigger on "review this pr", "look over my diff before i push", "is this branch ready to merge", "anything wrong with this change". Do not use for a vulnerability-focused audit — see the security-review skill; for feature release readiness, see the qa-review skill.

Triggers from the description

review this prlook over my diff before i pushis this branch ready to mergeanything wrong with this change
Original author description

Use when reviewing a pull request, diff, or branch. Produces severity-ranked findings covering correctness, security, performance, and maintainability, with concrete fixes rather than opinions. Trigger on "review this pr", "look over my diff before i push", "is this branch ready to merge", "anything wrong with this change". Do not use for a vulnerability-focused audit — see the security-review skill; for feature release readiness, see the qa-review skill.

How it works

  1. Purpose
  2. When to Use
  3. Capabilities
  4. Inputs
  5. Outputs
  6. Workflow
  7. Best Practices
  8. Examples
  9. Notes
Original SKILL.md headings · 73 lines, 609 words
SKILL.md preview
---
name: code-review
description: Use when reviewing a pull request, diff, or branch. Produces severity-ranked findings covering correctness, security, performance, and maintainability, with concrete fixes rather than opinions. Trigger on "review this pr", "look over my diff before i push", "is this branch ready to merge", "anything wrong with this change". Do not use for a vulnerability-focused audit — see the security-review skill; for feature release readiness, see the qa-review skill.
metadata:
  category: development
  version: 1.0.0
  tags: [code-review, pull-request, quality, security]
---

# Code Review

## Purpose

Review changes the way a senior engineer does: correctness first, then security, then performance, then design, then style. Every finding carries a severity, a reason, and a fix.

## When to Use

- Reviewing a pull request or a local diff before pushing.
- Auditing a branch before merge to a protected branch.
- Reviewing someone else's code in an unfamiliar area of the codebase.

## Capabilities

- Correctness analysis: edge cases, off-by-one, null and error paths, concurrency.
- Security review: injection, authorization gaps, secret exposure, unsafe deserialization.
- Performance review: N+1 queries, unbounded allocations, blocking calls on hot paths.
- Design review: coupling, layering violations, missing abstractions, premature ones.
- Test review: whether the tests would actually fail if the code were wrong.

## Inputs

- A diff, PR number, or branch reference.
- The surrounding code, not just the changed lines.
- The intent of the change: linked issue, PR description, or a one-line summary.

## Outputs

A review with findings grouped by severity:

- **Blocking** — Correctness, security, or data-loss defects. Must be fixed before merge.
- **Should fix** — Design or performance problems that will cost more later than now.
- **Consider** — Improvements that are genuinely optional.

Each finding states the file and line, what is wrong, why it matters, and a suggested fix.

## Workflow

1. **Understand the intent** — Read the PR description and the issue. A change that does something other than what it claims is the first finding.
2. **Read the diff in context** — Open the surrounding functions. Most defects live in the interaction between changed and unchanged code.
3. **Trace the failure paths** — For each new branch: what happens when the input is empty, null, malformed, or hostile? What happens when the network call fails?
4. **Check the boundaries** — Anything crossing a trust boundary (HTTP, queue, file, DB) must be validated on the way in and encoded on the way out.
5. **Assess the tests** — Would the new tests fail if the implementation were subtly wrong? If not, they are coverage, not verification.
6. **Rank and report** — Sort findings by severity. Lead with the ones that block.

## Best Practices

- Review the code, not the author. Write "this returns before closing the file", not "you forgot to close the file".
- Do not report style issues that a formatter should own. Fix the formatter config instead.
- One blocking finding stated clearly beats twenty nitpicks that bury it.
- If the design is wrong, say so early and stop line-by-line reviewing. Detailed feedback on code that should be deleted wastes everyone's time.
- Approve when the change is better than what exists. Perfection is not the bar; regression is.
- Quote the exact line. A finding without a location is not actionable.

## Examples

**A well-formed finding:**

> **Blocking — `api/orders.py:88`**
> `total` is computed from `request.json["items"]` without validating quantities, so a negative quantity produces a negative total and a credit to the customer's card.
> Validate `quantity >= 1` in the request schema, and assert `total > 0` before charging.

**A finding that is not actionable:**

> ~~"The order logic feels a bit fragile."~~

## Notes

- Automated tools should catch formatting, unused imports, and obvious lint violations before a human reads the diff. If they are reaching review, fix the pipeline, not the PR.
- Large PRs receive worse reviews. If a diff exceeds roughly 400 lines, reviewing it as one unit is unreliable — ask for it to be split.
- A review that finds nothing is a valid outcome, but say what you checked.

Versions

RepositoryScoreLicence
This page · nimadorostkar/Claude-Skills-collection100MIT
microsoft/aspire100MIT
kdlbs/kandev100AGPL-3.0
dotnet/runtime100MIT
drosam/agents100MIT
ggml-org/llama.cpp100MIT
ShamelesAbyss/Nyx100Apache-2.0
dzhng/jevgrep100MIT
iuliandita/skills100MIT

Database snapshot: 13.11.2026 · package version fa628bcc4054 (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

  • 100pr-review
    Reviews a pull request or diff for correctness first, then for how easily a human can understand, trust and change it: clear abstractions, data-driven design, honest names, local reasoning, and tests at the right boundary. Produces verified, ranked findings with concrete fixes.…
  • 100code-review-workflow
    Review a change in a fixed order — context, correctness, security, then style — and write feedback that is actionable and ranked by severity. Use when the user asks for a code review, wants a pull request or diff reviewed before merge, asks whether a change is safe to ship, or…
  • 100code-reviewer
    Reviews a code diff or pull request for correctness bugs, security vulnerabilities, and quality/maintainability problems, producing severity-ranked findings with file/line references and concrete fix suggestions. Use this skill when the user asks to "review this PR", "review my…
  • 100pr-review
    Focused pull request review practices with severity-ranked, file-and-line-cited findings across four angles: security, performance, tests, and architecture. Use when asked to review a pull request, review a diff or set of changes, review \"this PR,\" or provide a code review before merge.
  • 100awesome-code-review
    Reviews a diff, patch or pull request for correctness, security and team standards, with severity-ranked findings. Use when asked to review a change or PR, or before merging.
  • 100code-review-pro
    Performs a deep code review of files, modules, a diff, or a branch - finding security vulnerabilities (mapped to OWASP Top 10:2025), correctness bugs, performance problems, and maintainability issues - and returns severity-ranked findings with evidence and concrete fixes. Use…

Feedback and reports

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