Skills DirectoryCodex Skills
Codex-friendly skills turn repeatable development practices into reusable agent workflows. Use them to standardize debugging, testing, refactoring, docs, and review across projects.
Indexed skills
36634
Search focus
Codex skill
Security context
Scanned
Top matching skills
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
Vector-powered CLI for semantic file search with a Claude/Codex skill
You are operating in **codex exec** - a non-interactive automation mode for hands-off task execution.
Repository orientation and which Codex skills to use for each area (go-lcpd, protocol spec, docs, openai-serve, ExecPlans).
**Overview:** This guide outlines best practices for using Firebase on Apple platforms with Swift and on web/Node platforms with TypeScript. It covers how to set up the SDKs, organize code, handle data efficiently, and ensure security across all supported Firebase services and platforms.
Example skill demonstrating the full skill directory structure with scripts, references, assets, and examples. Use when learning how to structure Codex skills.
Keep documentation in sync with code changes across README, docs sites, API docs, runbooks, and configuration. Use when the user asks to update docs, ensure docs match behavior, or prepare docs for a release/PR.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
OpenAI Codex CLI configuration guide for Claude. Use when users ask about: codex config, ~/.codex/config.toml, codex sandbox policies, codex approval modes, creating codex skills, codex mcp servers, codex model settings, local LLM providers, or integrating tools with Codex.
Leverage OpenAI Codex/GPT models for autonomous code implementation. Triggers: "codex", "use gpt", "gpt-5", "gpt-5.2", "let openai", "full-auto", "用codex", "让gpt实现".
Codex CLI用のスキル作成ガイド。YAML frontmatter、ディレクトリ構造、ベストプラクティスを解説。Use when creating new Codex skills, updating existing skills, or learning about Codex skill development.
Use when the user suspects a Codex skill is not triggering, wants to validate SKILL.md frontmatter (name/description), check description quality for discovery, or needs a plugin-dev-like validation step for skill packaging.
Portable coding-agent patterns
The most useful Codex skill patterns are not model-specific. They define how to gather context, make small edits, run verification, summarize changes, and stop before risky operations.
Best workflows to standardize
Testing, bug reproduction, code review, migration planning, documentation, and release checklists are all strong candidates for skill-style workflows.
Safety for autonomous coding
Skills that guide autonomous coding should include verification steps, rollback boundaries, and explicit human approval gates for secrets, production deploys, and destructive changes.
Why security-scanned skills matter
Skills can influence agent behavior, suggest commands, include helper files, or touch code and data. Skills Directory adds security context so you can inspect risk before installing a workflow from a public repo.
See the security modelFrequently asked questions
Do SKILL.md files work directly with Codex?
Codex may not load Claude skills natively in the same way, but SKILL.md files can still be adapted into agent instructions, project rules, or reusable prompts.
What makes a skill Codex-friendly?
Clear task triggers, verification commands, small-step workflows, and minimal Claude-specific assumptions make a skill easier to adapt to Codex.
Should Codex skills include approval gates?
Yes. Any workflow that might deploy, delete data, modify secrets, or rewrite large areas should require explicit human approval.