Codex
Codex skills are built for OpenAI's coding-agent workflow across the terminal, repository context, and tool-driven implementation tasks. Expect software engineering, debugging, refactoring, and research helpers that pair well with an agent editing files and running commands.
Skills compatible with Codex
last30days
Deep research across 10+ social platforms and prediction markets, synthesized into cited reports on what people are discussing right now.
marketing-automation
23 specialized marketing sub-skills for generating CRO, copywriting, SEO, analytics, and growth deliverables with clear KPI alignment.
n8n-mcp-tools-expert
Comprehensive guide for building n8n workflows using MCP tools with node discovery, validation, and workflow management.
openclaw-control-center
Skill by ara.so — Daily 2026 Skills collection
ralphmode
Configure Claude Code, Codex CLI, and Gemini CLI for reduced-approval Ralph automation while enforcing project boundaries and secret denylists.
ultracite
Zero-config linting and formatting for JavaScript/TypeScript with pluggable linter backends.
uncodixfy
Clean, human-designed UI patterns that reject generic AI aesthetics in favor of Linear, Raycast, and Stripe.
video
Source details, install context, and public review data are available on the full page.
video-editing
AI-assisted editing for real footage. Not generation from prompts. Editing existing video fast.
video-production
Programmable video production with Remotion, scene planning, asset orchestration, and validation gates for brand-consistent automated content.
agent-eval
A lightweight CLI tool for comparing coding agents head-to-head on reproducible tasks. Every "which coding agent is best?" comparison runs on vibes — this tool systematizes it.
agentic-actions-auditor
Static security analysis for GitHub Actions workflows invoking AI coding agents.
agents
Build voice AI agents with natural conversations, multiple LLM providers, custom tools, and web embedding.
ai-regression-testing
Testing patterns specifically designed for AI-assisted development, where the same model writes code and reviews it — creating systematic blind spots that only automated tests can catch.
baoyu-image-cards
Break down complex content into eye-catching image card series with multiple style options.
blueprint
Turn a one-line objective into a step-by-step construction plan that any coding agent can execute cold.
daily-ai-news
Aggregates latest AI news from multiple sources with categorized summaries and direct article links.
dmux-workflows
Orchestrate parallel AI agent sessions using dmux, a tmux pane manager for agent harnesses.
documentation-lookup
When the user asks about libraries, frameworks, or APIs, fetch current documentation via the Context7 MCP (tools resolve-library-id and query-docs ) instead of relying on training data.
elite-longterm-memory
Six-layer memory architecture combining WAL protocol, vector search, git-based knowledge graphs, and cloud backup.
eraser-diagrams
Generate professional architecture diagrams from code, files, or natural language descriptions.
everything-claude-code-conventions
Generated from affaan-m/everything-claude-code on 2026-03-20
figma
Fetch design context, screenshots, and assets from Figma, then translate designs into production code.
openai-whisper
Local speech-to-text transcription using OpenAI's Whisper CLI without API keys.