Escape generic AI-generated UIs. Forces a bold, distinctive design direction before any code is written.
By agent
Top Skills for Codex CLI
OpenAI's coding agent CLI. Adopted the SKILL.md spec verbatim in Dec 2025.
About Codex CLI
Codex CLI is OpenAI's coding agent CLI — terminal-first like Claude Code — and it adopted the SKILL.md spec verbatim in December 2025. Skills on Codex CLI load the same way Anthropic Skills do, with the same frontmatter schema, but run against an OpenAI model (GPT-5 family) instead of Claude.
The install model mirrors Claude Code: Skills live as folders under `~/.codex/skills/` (user-wide) or `.codex/skills/` (project-scoped). Many Claude-targeted Skills run cleanly on Codex with no changes; some need minor adjustments where they assume Claude-specific tool names or system-prompt conventions. The CLI also supports Workflows for multi-agent orchestration similar to Claude Code's.
Codex CLI is the right Skill target for teams already standardized on OpenAI infrastructure who want SKILL.md-driven workflows. Composite scoring weights cross-agent verification — Skills tested in both Codex and Claude Code rank above single-target Skills.
Verified for this agent
Best Skills for Codex
Every skill below is verified to work with Codex CLI. Ranked by composite score.
1,234+ skills in one bundle. Single install across AI coding assistants.
Firebase-authored. Init, configure, and one-step deploy to Firebase Hosting / App Hosting.
Programmatic video done right. Idiomatic Remotion patterns auto-activate when detected.
Resend's deliverability playbook: SPF/DKIM/DMARC, spam avoidance, bounce handling, and CAN-SPAM/GDPR/CASL compliance.
Build cross-client HTML emails as React components, with a visual editor and Resend-ready rendering.
Resend's own API skill: send transactional and batch email, handle inbound webhooks, and manage domains, templates, and keys.
Give an agent a webhook-driven inbox with the sender-allowlist and content-filtering patterns that block prompt injection from inbound email.
Structured multi-step development. Brainstorm → spec → plan → build → review → merge — TDD baked in.
Paddle's own integration playbook: ten skills for Checkout, webhooks, pricing pages, and subscription lifecycle on the merchant-of-record platform.
Open-source marketing stack for AI coding agents. SEO, content, email, ads, analytics in one bundle.
Twilio's official Developer Kit: 55 skills across SMS, WhatsApp, Voice, Verify, SendGrid, and compliance — plus the Twilio MCP. Public beta.
Full-stack WorkOS implementation with auth provider migration paths.
Drop-in WorkOS widgets with backend token wiring across every major framework.
Pre-handoff a11y audit that catches what design QA misses.
1,000+ SaaS integrations as one skill. OAuth lifecycle, scoped credentials, structured actions.
ADR authoring + design review. Trade-offs, consequences, alternatives.
Disciplined debugging loop. Reproduce, isolate, diagnose, fix.
The pre-ship checklist that catches the embarrassing stuff.
Technical writing that engineers will actually read and update.
Incident triage + comms + blameless postmortem in one harness.
System design from requirements. APIs, data, boundaries, scale.
Honest tech-debt audit with a prioritized cleanup backlog.
Layered test plan sized to the change's risk profile.
Self-contained HTML artifacts with React + shadcn/ui — no build step, just paste and run.
Extract, fill, merge. PDF manipulation with bundled scripts so Claude does not waste tokens generating them.
Supabase done right. RLS policies, edge functions, realtime, auth — in idiomatic patterns.
Tailwind that scales. Token mapping, responsive variants, dark mode, plugins.
Stripe done right. Checkout, subscriptions, webhooks, idempotency, metered billing.
Shopify Storefront API: cart, checkout, metafields, customer accounts, Hydrogen patterns.
Sentry the right way. Source maps, releases, breadcrumbs, performance, structured tags.
100+ accessibility and UX rules from Vercel, applied as a structural audit on your UI code.
57 React/Next.js performance rules, applied as a structural review on your code.
Security audits run by a real security firm. CodeQL + Semgrep + audit workflows.
Web scraping, search, and browser automation built to be agent-friendly.
Web search + 36 authoritative data sources. SEC, PubMed, ChEMBL, FRED — agent-grade research.
Next.js App Router by the book. Server components, streaming, parallel routes.
20 SEO + GEO skills in one bundle. Keyword research, audits, rank tracking, AI search optimization.
232+ skills across engineering, marketing, product, compliance, advisory.
TDD with red/green/refactor as a concrete TypeScript walkthrough.
32+ marketing skills in one bundle. CRO, copywriting, SEO, analytics, email, growth.
Strip the AI tells. Multi-pass editing for content that reads opinionated, not generated.
Prisma migrations and queries by the book. Index-aware, migration-safe, type-correct.
Caching without the bugs. Invalidation, write-through, cache-aside, distributed locks.
C4, deployment, sequence-of-events architecture diagrams generated from natural-language descriptions.
CRO patterns from real teardowns. Hero copy, social proof, friction audits, test design.
Full email sequences with branching, exit conditions, and copy that does not read like an AI wrote it.
Dockerfiles done right. Multi-stage, cache-friendly, distroless, hardened.
GitHub Actions workflows with matrix, reusable jobs, OIDC, secrets done right.
Ethical scraping at scale. robots.txt respect, rate-limiting, structured extraction.
TypeScript strict mode by default. Discriminated unions, branded types, exhaustive switches.
Vitest patterns: snapshots, mocks, parallel runs, in-source tests, coverage.
Notion API: page/database CRUD, block hierarchies, rich text, schema sync.
FAQ
Frequently asked
How do I install a Skill on Codex CLI?
Drop the Skill folder under `~/.codex/skills/` for user-wide or `.codex/skills/` for project-scoped. Codex loads SKILL.md the same way Claude Code does.
Do Claude Skills work on Codex CLI?
Most do — the SKILL.md spec is the same. Skills that hardcode Claude-specific tool names or assume Claude system-prompt conventions may need minor adjustments.
Which model does Codex CLI use?
GPT-5 family by default. Skill performance varies between model tiers; the best Codex-targeted Skills are tuned for the specific model.
Does Codex CLI support Workflows?
Yes — Codex has a Workflow primitive for multi-agent orchestration similar to Claude Code's. Skills can be invoked from within Workflows.
Is Codex CLI free?
The CLI itself is free; usage is billed against your OpenAI API account.
Switch agent