Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Comprehensive PR code review - checks diff, patterns, runs validation, comments on PR. Single-pass by default; pass --agents for a multi-agent specialist fan-out (comments, tests, errors, types, code, docs, simplify). Use when the user wants to review a pull request, wants a thorough/multi-agent review, or invokes the prp-review skill.
Debug MLX ports by comparing against a PyTorch/diffusers reference via exported tensors/images (export-then-compare).
Manually validate mflux CLIs by exercising the changed paths and reviewing output images/artifacts.
Run tests in mflux (fast/slow/full), preserve image outputs, and handle golden image diffs safely.
Review tutti git diffs for project structure, layering, module ownership, and duplicate event-center infrastructure by planning focused architecture review tasks, then having the main agent orchestrate sub-agents for only the changed areas.
Run UnrealCV closed-loop test workflow (build + launch + test)
caddy-security break-fix triage and support-report workflow. Use when diagnosing reported configuration, deployment, or runtime failures; analyzing Caddyfiles, Caddy logs, redirect loops, login failures, authorization denials, OAuth/OIDC/SAML/LDAP/local-user issues, module-version mismatches, or secret/runtime placeholder problems; preparing GitHub issue Markdown files for .github/ISSUE_TEMPLATE/break-fix.md under tmp/breakfix/; or identifying gaps in repository skills after troubleshooting.
Use when iterating on a fix after an adversarial code review (Codex, human reviewer) surfaces design-level findings — not typos, lint, or formatter work. Frames the review/fix loop as implement -> [review -> REFLECT -> reproducer -> fix -> verify -> handoff] where each round runs in a fresh agent to prevent context accumulation. Provides a four-item cheap-checks list (timeline draw, upstream contract read, full lifecycle trace, variant enumeration) that catches recurring failure classes. No git commits during the loop — all changes commit together after zero-finding termination. Trigger when a review pass surfaces 2+ findings on a single change, when sibling bugs of an "already-fixed" issue keep appearing across rounds, or when the user asks "why did I miss this?". Do NOT use for single-line fixes where the cause is obvious from the diff, or for initial implementation work (use CLAUDE.md rules).
综合代码审查 skill，覆盖安全、性能、代码质量和可维护性。Use when users ask to review code, analyze code quality, evaluate pull requests, or mention code review, security analysis, or performance optimization.