Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Create a dedicated worktree for a GitHub PR (use `wf` for openai/openai workforests, `wt` for all other repos), check out the PR locally, run `codex review` plus a PAL `mcp__pal__precommit` review against the PR base, then merge both into one actionable review summary.
Use this skill to inspect what a Rails page currently displays, extract HTML content, or verify rendering WITHOUT starting a dev server. Useful for understanding page output before making changes, debugging views, searching for content, or testing that pages work correctly. Provides scripts/render.rb for quick page inspection and HTML extraction.
Verify that results, builds, and experiments can be reproduced consistently with documented steps and deterministic inputs.
Final code/plan review using Codex CLI. Use as the last review step after sonnet.
Performs comprehensive code review on git diffs and generates review.md with quality scores, critical issues, performance concerns, and potential bugs. Use when user requests to review changes, check code quality, analyze diffs, or validate LLM-generated code
Verify that review feedback was addressed in a revision
Deterministic debugging with rr record-replay. Use when debugging crashes, ASAN faults, or when reverse execution is needed. Provides reverse-next, reverse-step, reverse-continue commands and crash trace extraction.
Executes comprehensive test suite across unit, integration, E2E, database, protocols, and intelligence algorithms
Comprehensive code analysis, quality assessment, and issue diagnosis. Use when analyzing code quality, security vulnerabilities, performance bottlenecks, architecture reviews, or troubleshooting bugs and build failures.