Skip to content
Agentmart
Submit a tool

review

Review code or a PR diff for correctness, design, smells, and missing tests.

Skill by timander

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/timander-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review code or a PR diff for correctness, design, smells, and missing tests. Use when the user asks for a code review or PR walkthrough.

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/review

Tools it pre-approves 1

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • shell

What's inside

Skill name
review
Description
Review code or a PR diff for correctness, design, smells, and missing tests. Use when the user asks for a code review or PR walkthrough.
License
MIT
Allowed tools
shell
Instructions
28 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Review

Apply this checklist to either a code block or a PR diff. Items marked **(PR)** are additional when reviewing a pull request.

## Checklist

1. **Intent**: state in one sentence what the code (or PR) is trying to do. **(PR)** Restate the problem the PR claims to solve.
2. **Does it do what it claims?** Gaps, off-by-one, half-finished branches, dead paths.
3. **Quality Spectrum rating** (convoluted → elegant). Name the level honestly.
4. **Smells**: name them (Fowler, *Refactoring* Ch. 3). Don't gesture — name. **(PR)** Note smells *introduced* by the diff and missed opportunities in adjacent code.
5. **Refactorings**: suggest specific named moves (Extract Method, Replace Conditional with Polymorphism, etc.) with one-line rationale.
6. **SOLID violations** where they actually exist; don't manufacture them.
7. **Tests**: missing coverage, untested edge cases, vanity tests. **(PR)** Are the new behaviors tested? Are the tests load-bearing or theatre?
8. **Future-cost**: anything that will make the code harder to change later.
9. **Cite principles** with attribution when you invoke them ("Item 18, *Effective Java*"; "Ch. 3, *Refactoring*").
10. **(PR) Acknowledge what's done well** — briefly. The author doesn't need a parade.

Prioritize: correctness > clarity > simplicity > performance.

## Output Discipline

- One section per finding. Lead with severity: `blocker` / `should-fix` / `nit`.
- File:line references for every concrete finding.
- Say what you'd change and why. No "consider possibly maybe."

For multi-expert perspectives on the same code, use the `expert-panel` skill.

From timander/copilot-instructions-starter-kit, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 12, 2026 (4 months ago)
Last release
Jun 12, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from timander

Cite this page

review skill. Agent Mart. https://agentmart.dev/skills/timander-review (last updated 2026-10-24)