Summary
This is a serious code review automation that runs five parallel specialized agents against your PR: one checks CLAUDE.md compliance, another scans for bugs in the diff, one digs through git history for context, one reviews past PR feedback on those files, and the last verifies code comment adherence. Each finding gets a confidence score from a separate agent, anything below 80 is dropped, then it posts a GitHub comment with links to specific line ranges. The workflow is designed to avoid false positives that waste your time, like pre-existing issues, linter catches, or nitpicks a senior engineer wouldn't flag. It's overkill for trivial PRs but legitimately useful when you want thorough review coverage without manually coordinating multiple perspectives.
Install to Claude Code
npx -y skills add feiskyer/claude-code-settings --skill github-review-pr --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 →
