Summary
This is a structured code review skill that runs through your git diff with a severity-based framework (P0 through P3) covering SOLID violations, security risks like injection and race conditions, and code quality issues like N+1 queries and error swallowing. It's review-first by design: you get a full report with inline comments and severity ratings, then you choose whether to fix everything, just the critical stuff, or nothing at all. The nice part is it loads specific checklists for security, SOLID, and removal candidates, so you're not just getting generic linter feedback. Good for catching the kind of stuff that slips through automated tools but would get flagged in a senior engineer review.
Install to Claude Code
npx -y skills add dtsola/xiaoyaosearch --skill code-review-expert --agent claude-codeInstalls into .claude/skills of the current project.
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Files
SKILL.md
Select a file.
Featured
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
