Forge Review

Cross-Platform AI Agent Skill This skill works with any AI agent platform that supports the skills.sh standard.

Code Quality Review

Deep code quality review focusing on architecture, design patterns, readability, maintainability, and refactoring opportunities. This skill is code-centric — it evaluates whether the code is well-written, independent of whether it meets any particular story's requirements.

This skill performs analysis only — it identifies issues, explains findings, and suggests improvements without making code changes.

Anti-Hallucination Guidelines

CRITICAL: Code reviews must be grounded in actual code read during this session:

1. Read before reporting — Never cite a finding in code you have not read
2. Exact references — Every finding must include file:line and a short code excerpt
3. No assumed violations — Verify the pattern exists before reporting it
4. Context sensitivity — Understand project conventions before flagging style differences
5. Proportional severity — Match severity to actual impact, not theoretical worst case