Skip to content
Agentmart
Submit a tool

code-review

Reviews code changes for correctness, security, maintainability, and test coverage using a severity-tagged checklist.

Skill by openagentskills

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/openagentskills-code-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

Reviews code changes for correctness, security, maintainability, and test coverage using a severity-tagged checklist. Use when reviewing pull requests, diffs, patches, or when the user asks for a code review.

Use cases: testing, security

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/code-review

What's inside

Skill name
code-review
Description
Reviews code changes for correctness, security, maintainability, and test coverage using a severity-tagged checklist. Use when reviewing pull requests, diffs, patches, or when the user asks for a code review.
License
MIT
Instructions
53 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • reference.md
  • skill.manifest.yaml

SKILL.md (first lines)

# Code Review

## Quick start

1. Understand the change goal (read PR description or ask).
2. Read the diff in logical chunks (not only file order).
3. Apply the checklist below.
4. Report findings by severity with file/line references when possible.

## Review checklist

- [ ] **Correctness** — Logic handles happy path and edge cases
- [ ] **Security** — No injection, auth bypass, secret leakage, unsafe deserialization
- [ ] **API/contracts** — Public surfaces backward-compatible unless versioned
- [ ] **Performance** — No obvious N+1, unbounded memory, or hot-path regressions
- [ ] **Maintainability** — Clear names, focused functions, matches project style
- [ ] **Tests** — Behavior covered; tests assert outcomes not implementation details
- [ ] **Docs** — User-facing changes documented

## Output format

```markdown
## Summary
[1–2 sentences: overall recommendation]

## Findings

### Critical (must fix)
- `path:line` — Problem. Suggested fix.

### Suggestions
- `path:line` — Improvement.

### Nitpicks (optional)
- Minor style or clarity notes.

## Verdict
[Approve / Request changes / Comment only]
```

## Severity guide

| Level | When |
|-------|------|
| Critical | Bugs, security issues, data loss risk |
| Suggestion | Better design, clearer code, missing tests |
| Nitpick | Style not enforced by linter |

## Additional resources

- Extended standards: [reference.md](reference.md)

From openagentskills/betterskills, MIT.

More from openagentskills/betterskills

Signals

Stars
0
Forks
1
Open issues
25
Last commit (this folder)
Jun 1, 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 openagentskills

Cite this page

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