Skip to content

OffchainLabs/arbitrum-docs / .agents/skills/review

review

Verified

Critical code review using hostile falsification. Delegates to qa. Triggers on "review this", "check my code", "critique", "is this good".

FileKindSize
SKILL.mdskill md789 B
---
name: review
description: Critical code review using hostile falsification. Delegates to qa. Triggers on "review this", "check my code", "critique", "is this good".
agent: qa
---

# Critical Review

Delegates to `qa` for hostile falsification review.

## Usage

Invoke with content to review:

- Code files or snippets
- Plans or specifications
- Architecture designs

## What Gets Reviewed

1. **Bugs & Security** - Logic errors, vulnerabilities
2. **Performance** - Bottlenecks, missing optimizations
3. **Edge Cases** - Unhandled scenarios
4. **Naming & Clarity** - Unclear identifiers
5. **Arbitrum-Specific** - SDK patterns, protocol compliance

## Output

```text
## Summary
[1-2 sentences]

## Issues
| Severity | Location | Issue | Fix |

## Rating: X/10

## Top 3 Actions
```
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall