Skills for Codex – install and usage guide

OpenAI's Codex CLI reads skills in the SKILL.md standard. Skill Library for AI Agents collects 4166 free skills; find the right task and paste one command to install.

3 steps to use skills with Codex

Find a skill for your task (e.g. “make slides”, “SEO writing”, “docker”).

Copy the install command and run it in your terminal – for example for the api-and-interface-design skill:

mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/api-and-interface-design-52d78.tgz | tar xz -C ~/.codex/skills

Restart Codex, then call $skill-name or just describe the task.

Frequently asked questions

What is a skill for Codex?

A skill is a folder with a SKILL.md file that teaches Codex how to do a specific kind of work (SEO writing, slides, code review…). Codex loads a skill only when needed, so it costs no context up front.

Where do Codex skills live?

The skills folder for Codex is ~/.codex/skills. Each skill is a subfolder containing SKILL.md.

How do I install a skill for Codex?

Run a command like: mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/<skill-id>.tgz | tar xz -C ~/.codex/skills. Every skill page on Skill Library for AI Agents has the command ready to copy. Then restart Codex.

Is it free?

Yes. Every skill on Skill Library for AI Agents is open source under the MIT or Apache 2.0 licence and ships with its original LICENSE file.

Featured skills

api-and-interface-design – Guides stable API and interface design. Use when designing APIs, module boundaries, or any public…
ab-testing – When the user wants to plan, design, or implement an A/B test or experiment, or build a growth…
13c-metabolic-flux – Estimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements…
adaptyv – Uses the Adaptyv Bio Foundry API and Python SDK to design protein characterization experiments…
00-andruia-consultant – Usar al iniciar o mejorar un proyecto de IA: diagnostica código y restricciones, propone skills…
007 – Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code…
10-andruia-skill-smith – Usar para crear o mejorar una skill de Andru.ia: define entradas y resultados, redacta SKILL.md…
20-andruia-niche-intelligence – Usar tras definir el sector de un proyecto: prepara un dossier en español con contexto, normas…
2d-games – 2D game development principles. Sprites, atlases, tilemaps, physics, cameras, and genre patterns…
2slides-ppt-generator – AI-powered presentation generation via the 2slides API — create slides from text, match a…
360-feedback-system – 360 feedback register: reviewer, subject, review cycle, visibility, due date and score, as CSV…
3d-games – 3D game development principles. Rendering, shaders, physics, cameras.
3d-ui – Web and App implementation guide for 3D UI. Trigger when user wants actual 3D objects, perspective…
accessibility-compliance – Implement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and…
ai-debt-detector – Use after generating code, after accepting AI suggestions, or when reviewing AI-written modules…
a11y-audit – Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance…
ab-test-setup – When the user wants to plan, design, or implement an A/B test or experiment. Also use when the…
access-lifecycle – Use when preparing or running a user access review, checking that leavers lost their access…
aspnet-core – Build, review, refactor, or architect ASP.NET Core web applications using current official…
baoyu-article-illustrator – Analyzes article structure, identifies positions requiring visual aids, generates illustrations…
brand-guidelines – Applies OpenAI's brand colors and typography to any artifact that should match the Codex/OpenAI…
401-403-bypass-techniques – Use when protected HTTP routes return 401 or 403.
api-noauth-hunt – Use when an API may expose data or privileged operations without authentication.
browser-testing-with-devtools – Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs…
ad-creative – When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary…
aeon – This skill should be used for time series machine learning tasks including classification…
alphagenome – Looks up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score…
3d-web-experience – Use when building or debugging web 3D scenes, product configurators or portfolios with Three.js…
a4a – Connect your AI agent to the A4A end-to-end encrypted agent-to-agent messaging network via local…
aas-compose-stack – Preserve the coding agent's explicit AAS skill selection as a validated stack and optional evidence.
1password – Set up op CLI, sign in, and read or inject secrets.
3-statement-model – Build integrated IS/BS/CF financial workbooks in Excel.
academy-guide – Stop and check this skill before finishing any reply to a question about how to use Claude or a…
antinet-doc-parse – 软件开发工程师与数据科学家在构建RAG系统时，当需处理PDF/Word/Excel等多格式复杂文档，用此技能可自动触发三级解析降级，一键输出高置信度结构化Markdown与元数据，免去繁琐清洗，直接…
deepcode-self-refer – Answers questions about Deep Code CLI itself — including features, configuration options, slash…
accelerate – Run PyTorch training across GPUs with minimal changes.
actual-setup – Set up Actual Computer (actual.inc) inference in Hermes.
algorithmic-art – Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration…
antinet-four-color-cards – 财务和投资分析师、律师助理与法律助手在撰写金融研报或分析法律文档时，必用此技能！基于解析文档一键生成事实蓝卡、解释绿卡、风险黄卡与行动红卡。自动完成深度剖析与风险排查，产出100%可溯源的结构化四色…
image-generator – Generate or edit images from text and local files, image URLs, or data URLs through image API. Use…
adversarial-ux-test – Roleplay a hostile user to find and triage UX pain points.
agent-merge-conflict-arbiter – Neutral arbiter for merge conflicts between two agents.
brand-guidelines – Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit…
antinet-provenance – 软件开发工程师与信息安全分析师在构建多智能体系统时，当需全链路可观测与安全审计，请用此技能。它自动收集操作日志，生成可追溯证据链与向量索引，开箱即用实现系统审计与精准回放，让Agent运行安全透明。
skill-digester – Reviews and improves another DeepCode skill's SKILL.md description field, and guides Agent Skill…
agentmail – Use when an agent needs AgentMail CLI email inboxes.
ai-presenter-video – Make a verified AI presenter video from script + image.
canvas-design – Create beautiful visual art in .png and .pdf documents using design philosophy. You should use…
antinet-security-scan – 信息安全分析师与软件开发工程师在搭建文档处理流水线时，当需要拦截违规文件或外部URL，请挂载此技能作为强制前置安检，自动输出 pass/reject 判定与详细合规扫描报告，一键守住零信任安全底线。
skill-writer – Guide users through creating, updating, debugging, and validating Agent Skills for AI agents. Use…
airtable – Airtable REST API via curl. Records CRUD, filters, upserts.
anatomy – Explain an idea as an interactive isometric machine figure.
claude-api – Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use…
contract-review – 律师助理与法律助手、项目管理专家在审核合同、排查条款风险时必备。自动执行基础、商业、法律三层审查，仅添加批注不改原文，一键生成带批注合同、审查摘要、综合意见及业务流程图，让合同风控与业务梳理更高效专…
video-generator – 使用AI大模型根据文字、首尾帧图片或图片/视频/音频参考素材生成带对白和环境音的视频。适用于文生视频、图生视频、首尾帧过渡和多模态参考视频生成，通过 Deep Code Plus…
antigravity-cli – Operate the Antigravity CLI (agy): plugins, auth, sandbox.
apple-notes – Manage Apple Notes via memo CLI: create, search, edit.
discernment-nudge – After you give a substantive answer or draft that the user may act on — advice or recommendations…
expert-prompt-migrator – 将任意专家/角色提示词规范化为可移植格式并迁移到任意 AI（DeepSeek、豆包、Kimi、Claude、Ollama 等）的实用工具。内置「清理平台语法 / 单专家单任务 /…
apple-reminders – Apple Reminders via remindctl: add, list, complete.

Browse all 4166 skills →