Yefclub
UserTurn Claude Code into a specialist in PR review, project-state analysis, and security review — a parallel subagent swarm on the strongest model.
Categories
Indexed Skills (7)
project-state
Produce a health snapshot of a repository — open/blocked PRs, CI status, issue backlog, stale branches, dependency and security posture, and architecture hotspots. Use when the user asks about the state of the project, repo health, what's blocked, or where the risk is.
review-pr-stack
Review a sequence or stack of dependent pull requests in order, each against its own base. Use when the user asks to review multiple related PRs, a stacked-diff chain, or a sequence of PRs together.
review-pr
Review a single pull request end to end with a parallel subagent swarm, then produce a verdict and optional inline comments. Use when the user asks to review, check, or audit a specific PR or the current branch's changes.
security-audit
Audit tenant isolation, server authorization, IDOR, exposed secrets and XSS with explicit coverage, a Portuguese PDF and local GitHub issue drafts. Use for full five-category audits or security reports with PDF delivery.
security-review
Run a deep, security-only review of a diff or an entire codebase using the OWASP 2025 taxonomy, with adversarial false-positive filtering. Use when the user asks for a security review, security audit, vulnerability scan, or "is this safe".
verify-closure
Verify that a prior audit/issue's findings were actually closed by the PRs that claim to fix them — per-finding verdict (FIXED/PARTIAL/NOT_FIXED/REGRESSED) plus a hunt for regressions the fixes introduced. Use when the user asks "did these PRs close the issue", "verify the audit was addressed", or reviews follow-up/merged fix PRs.
start
Explain Agent Review Kit workflows and route an unclear review request to PR review, security audit, repository health or fix verification.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.