Skip to content
Skills Library
Programming · Review & audit

code-review

/code-review

Sandwich-structured code review for PRs, MRs, diffs, or pasted code. Triggers on: "review this", "check my PR/MR", "what do you think of this code", "is this OK to merge", or any paste of code/diff where the user wants feedback. Produces motivating reviews that clearly separate blockers from nitpicks. Always use this skill — even for quick reviews. The structure matters.

Repository
ai-skills ↗
Licence
MIT
Last repository change
25.10.2026

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 25.10.2026, 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

Sandwich-structured code review for PRs, MRs, diffs, or pasted code. Triggers on: "review this", "check my PR/MR", "what do you think of this code", "is this OK to merge", or any paste of code/diff where the user wants feedback. Produces motivating reviews that clearly separate blockers from nitpicks. Always use this skill — even for quick reviews. The structure matters.

Triggers from the description

review thischeck my PR/MRwhat do you think of this codeis this OK to merge
Original author description

Sandwich-structured code review for PRs, MRs, diffs, or pasted code. Triggers on: "review this", "check my PR/MR", "what do you think of this code", "is this OK to merge", or any paste of code/diff where the user wants feedback. Produces motivating reviews that clearly separate blockers from nitpicks. Always use this skill — even for quick reviews. The structure matters.

How it works

  1. The Sandwich Method (always follow this order)
  2. Tone Guidelines
  3. Example Output Structure
  4. Edge Cases
Original SKILL.md headings · 80 lines, 443 words
SKILL.md preview
---
name: code-review
description: >
  Sandwich-structured code review for PRs, MRs, diffs, or pasted code.
  Triggers on: "review this", "check my PR/MR", "what do you think of this code",
  "is this OK to merge", or any paste of code/diff where the user wants feedback.
  Produces motivating reviews that clearly separate blockers from nitpicks.
  Always use this skill — even for quick reviews. The structure matters.
---

# Code Review Skill

Goal: leave the author feeling **capable and motivated**, not defensive.
The review should make them think "yes, I'm on the right track, let me fix that one thing."

---

## The Sandwich Method (always follow this order)

### Top Slice — Overall

- Open with genuine recognition of what's good
- Name the design pattern or approach and why it's solid
- One short paragraph, no hedging, no "but..."
- Example: *"Separating analytics into its own component via CustomEvents is a clean SRP refactor — event-driven decoupling between components is well-designed here."*

### Filling — Bugs & Notes

#### Bug / Blocker (must fix before merge)

- State the bug clearly and directly
- Show the broken code, explain WHY it's wrong
- Provide the fix — exact code, not vague direction
- One blocker per section. If there are multiple, list them all here.

#### Minor Notes (optional, low pressure)

- Numbered list
- Each note: what it is + why it matters (or why it's just a preference)
- Explicitly label style preferences vs. real issues: *"Style preference, not a bug — current approach works."*
- Include positive observations too (e.g., "No double-fire risk — verified both paths are cleanly separated.")

### Bottom Slice — Verdict

- Clear, confident closing statement
- Name the blocker(s) and say everything else is solid
- Example: *"Bug with `id` is the only blocker. The rest is clean and well thought-out."*
- Optional: one motivating sentence — not sycophantic, just human

---

## Tone Guidelines

- **Direct, not harsh.** Say "this is wrong" not "you might want to consider..."
- **Specific, not vague.** Always show code. Never say "the naming could be better" without showing the fix.
- **Proportional.** A 5-line nit doesn't get 3 paragraphs.
- **Honest about preferences.** If it's a style preference, say so. Don't dress up opinions as bugs.
- **Push, don't crush.** The goal is the author merging better code AND feeling good about it.

---

## Example Output Structure

```
## Overall
[positive opening paragraph about the approach]

## Bug
[blocker description]
[broken code snippet]
[fix snippet]

## Minor Notes
1. [note with label: bug / style preference / positive observation]
2. ...

## Verdict
[confident closing + blocker summary]
```

---

## Edge Cases

- **No bugs found?** Still follow the sandwich. The filling becomes only minor notes.
- **Multiple blockers?** List all under "Bug / Blocker". Don't bury them in minor notes.
- **Tiny snippet / quick question?** Keep the structure but compress it — 3 short paragraphs is fine.
- **Architecture review (no diff)?** Same structure applies — "blockers" become design risks.

Versions

RepositoryScoreLicence
This page · freema/ai-skills100MIT
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 099a1d4cb0a5 (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

  • 1004r-code-review
    Perform structured code reviews using the 4R framework (Risk, Readability, Reliability, Resilience). Use this skill whenever the user asks to review code, audit a PR, check a diff, analyze a file for quality issues, or says anything like "review this", "check this code", "is…
  • 100pr-review
    Team baseline for PR and code review — produces scope, blockers, nits, and strengths. Auto-triggers when you say review this PR, check this diff, review these changes, pre-review before I share, what do you think of this PR, or review the diff on this branch. Defers to any other…
  • 100code-review-checklist
    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.
  • 91review
    Use when the user wants a code review of EXISTING pull/merge requests: \"review this PR/MR\", \"code review <link>\", \"check the api + web MRs for ABC-123\", a bare link with \"thoughts?\". Also to address feedback on your OWN PR: \"fix the comments on this MR\", \"address the…
  • 90check-my-prs
    Check your open MRs for feedback from reviewers. Shows MRs needing response, awaiting review, pipeline failed, needs rebase, and approved. Use when you want to see PR status, any MR feedback, or before creating more MRs.
  • 90reviews
    Review a pull request or code change for code health. Use when a user asks to "code review", "review this PR", or "review this change".

Feedback and reports

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