Codex

dmux-workflows is a guide for orchestrating parallel AI agent sessions with dmux in tmux panes. It helps split research, implementation, testing, and docs across Claude Code, Codex, OpenCode, and similar harnesses so you can manage multi-agent development with less context bottlenecking.

ai-regression-testing helps catch bugs AI-assisted development often misses, including incomplete fixes, stale assumptions, and regressions across sandbox and production paths. Use this ai-regression-testing skill for Regression Testing when an agent has changed API routes, backend logic, or bugfixes that need practical, repeatable checks. It is especially useful for DB-free sandbox-mode verification and review workflows that expose hidden branches.

agent-eval is a skill for benchmarking coding agents head-to-head on reproducible tasks, comparing pass rate, cost, time, and consistency. Use the agent-eval skill to evaluate Claude Code, Aider, Codex, or another agent in your own repo with clearer evidence than ad hoc prompting.

verification-before-completion is a final-check skill that blocks unsupported completion claims. Learn when to use it, how to install it from obra/superpowers, and how to match each status claim to fresh verification evidence.

using-superpowers is a session-start skill from obra/superpowers that forces skill lookup before any reply, helping agents discover and activate the right workflow first.

Install and use the test-driven-development skill to enforce strict TDD: write a failing test first, verify the failure, implement the minimum code, then refactor safely.

systematic-debugging is a root-cause-first debugging skill for bugs, flaky tests, build failures, and unexpected behavior. Learn the four-phase workflow, companion files, and when to use it before proposing fixes.

subagent-driven-development is a skill for executing implementation plans with a fresh subagent per task, then reviewing each result in two passes: spec compliance first, code quality second. It includes prompt templates for the implementer, spec reviewer, and code quality reviewer.

executing-plans helps agents follow a written implementation plan: review it first, execute tasks in order, run specified checks, stop on blockers, and hand off to a finishing workflow. Best for Project Management and other plan-led delivery.

dispatching-parallel-agents is an Agent Orchestration skill for splitting truly independent tasks across separate agents with isolated context and coordinated results.

webapp-testing is a skill for testing local web apps with Python Playwright. It helps agents start servers with scripts/with_server.py, inspect rendered UI, discover selectors, capture screenshots and console logs, and validate frontend behavior with a reconnaissance-first workflow.

quieter is a UI design refinement skill that reduces visual aggression in loud or overstimulating interfaces while preserving clarity, hierarchy, and brand intent. It works best after the parent $impeccable skill and helps teams diagnose intensity sources before making targeted changes.

notion-meeting-intelligence helps turn Notion context into meeting-ready agendas and pre-reads, with Codex research for decisions, status, planning, retros, and 1:1 prep. Best for the notion-meeting-intelligence for Meeting Prep workflow when you need grounded materials, clear timeboxes, and attendee-specific outputs.

The colorize skill helps UI teams add strategic color to gray or flat interfaces. Learn when to use it, what context it needs, and how it fits the impeccable workflow with $frontend-design and brand-aware color decisions.

arrange helps diagnose and improve UI layout, spacing, and visual hierarchy. Use this arrange skill to fix crowded screens, repetitive grids, and weak composition, with required setup through $frontend-design and optional $teach-impeccable context.

neat-freak is a knowledge cleanup skill for end-of-session handoffs. It reconciles project docs, agent memory, and code drift so CLAUDE.md, AGENTS.md, and docs/ stay accurate. Useful for technical writing, developers, and agent operators who need a cleaner, more reliable project knowledge base.

codex is a Claude Code skill that wraps the Codex CLI for code analysis, refactoring, and automated editing. It helps you run `codex exec` and `codex resume` with the right model, sandbox, resume flow, and quieter default output. Requires a working local Codex CLI install first.

subagent-driven-development helps you break implementation plans into independent tasks, dispatch a fresh subagent for each one, and review results between steps. It is built for agent orchestration when you need faster delivery with quality gates, especially for 3+ independent issues, bug fixes, feature slices, or repo cleanup.

cross-agent-delegation helps Claude Code route work across Kimi and Codex for agent orchestration. It supports automatic tool detection, Codex auto-review after tests, and bounded Kimi delegation based on complexity signals. Use this cross-agent-delegation skill when you want a practical guide to install, activate, and use hidden routing in multi-CLI workflows.

long-task-coordinator helps agents coordinate long-running or delegated work with a durable state file, recovery checks, explicit statuses, and a persist-before-report workflow for reliable resumability.

skills-cli helps users discover, install, and manage Agent Skills with current `bunx skills` or `npx skills` commands, including `--skill`, `skills-lock.json`, update, remove, restore, and sync workflows.

image-to-code is an image-to-code skill for Codex that turns visual references into real web pages. It starts with design image generation, then careful analysis, then implementation to match the layout, spacing, typography, and hero composition. Use it for landing pages, product pages, editorial layouts, portfolios, and redesigns that need strong visual fidelity.

codex-review is a GitHub skill for OpenAI Codex CLI code review with GPT-5.2-Codex. It helps teams catch bugs, security issues, and code quality problems with structured findings, GitHub-native review flows, and CI/CD-friendly usage.

code-review is a mandatory review workflow for code changes before commits and deploys. It helps teams run a structured /code-review step, choose an engine, and get actionable feedback instead of a generic pass. Ideal for pre-merge checks, release candidates, and high-stakes refactors.