Skip to content
Agentmart
Submit a tool

review

Perform a structured evidence-based code review with severity ratings.

Skill by jjongguet

IndexedMIT★ 99
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/jjongguet-review-54fcc7

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

Perform a structured evidence-based code review with severity ratings.

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

What's inside

Skill name
review
Description
Perform a structured evidence-based code review with severity ratings.
License
MIT
Instructions
46 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

<Purpose>
Review evaluates correctness, security, maintainability, and test confidence before merge.
</Purpose>

<Use_When>
- User asks for PR review, code audit, or change assessment
- You need release-readiness confidence and concrete findings
</Use_When>

<Execution_Policy>
- Prioritize defects over style opinions
- Every finding must include evidence (file and behavior impact)
- Rank findings by severity: critical/high/medium/low
- Include missing tests and verification gaps
</Execution_Policy>

<Checklist>
1. Correctness: edge cases, state transitions, null/undefined handling
2. Security: injection vectors, authz/authn gaps, secret handling
3. Reliability: retries/timeouts, error propagation, race conditions
4. Maintainability: coupling, duplication, naming clarity, complexity
5. Test Adequacy: missing coverage, flaky risk, weak assertions
</Checklist>

<Output_Format>
## Review Summary

### Critical
- [ ] <issue + evidence>

### High
- [ ] <issue + evidence>

### Medium
- [ ] <issue + evidence>

### Low / Suggestions
- [ ] <suggestion>

### Verification Gaps
- [ ] <missing test or validation>
</Output_Format>

Task: {{ARGUMENTS}}

From jjongguet/oh-my-product, MIT.

More from jjongguet/oh-my-product

Signals

Stars
99
Forks
22
Open issues
1
Last commit (this folder)
Apr 5, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from jjongguet

Cite this page

review skill. Agent Mart. https://agentmart.dev/skills/jjongguet-review-54fcc7 (last updated 2026-10-24)