Official

Official skills

First-party skills straight from the source. Published and maintained by Anthropic and OpenAI, mirrored here with the full document and one-click install.

These are the skills the model builders ship themselves. Anthropic's document suite — pptx, docx, xlsx, pdf — and design skills like canvas-design and frontend-design are the reference implementations everyone else forks; OpenAI's set leans into Figma, deployment and repo workflows. Because they come straight from the source, they track the upstream repo, not a third-party re-upload that quietly goes stale.

Every official skill here carries its full SKILL.md and its auxiliary scripts, packaged exactly as the repo publishes them, and installs onto any of your agents in one click. When a skill needs a helper script to do its job — the way pptx leans on a Python thumbnail generator — that script comes with it, so it works the moment it lands.

Star counts are the real GitHub numbers; install counts are omitted rather than invented, because a first-party skill's authority comes from who published it, not from a usage number we could only estimate.

Anthropic official skills

View all Anthropic

Generate p5.js algorithmic art from a written philosophy, with seeded reproducibility and interactive parameter controls.

by Anthropic175.2k stars

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting

by Anthropic175.2k stars

Write a design philosophy as a .md file, then render it as a .pdf or .png artwork.

by Anthropic175.2k stars

Co-author documents through a guided three-stage workflow from context gathering to reader testing.

by Anthropic175.2k stars

docx

Official

Create, edit, read, and analyze .docx/.dotx files through scripted XML and docx-js workflows.

by Anthropic175.2k stars

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defau

by Anthropic175.2k stars

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal com

by Anthropic175.2k stars

mcp-builder

Official

Step-by-step guide for building MCP servers that connect LLMs to external services via Python or TypeScript.

by Anthropic175.2k stars

pdf

Official

Read, split, merge, rotate, watermark, OCR, and create PDFs with pypdf, pdfplumber, reportlab, qpdf, and pdftk.

by Anthropic175.2k stars

OpenAI official skills

View all OpenAI

aspnet-core

Official

Pick the right ASP.NET Core app model and structure Program.cs, middleware, and services to match current Microsoft guidance.

by OpenAI26.4k stars

chatgpt-apps

Official

Scaffold ChatGPT Apps SDK projects from docs to MCP server and widget code in one workflow.

by OpenAI26.4k stars

cli-creator

Official

Scaffold a durable, composable CLI that future Codex threads can invoke from any directory.

by OpenAI26.4k stars

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

by OpenAI26.4k stars

define-goal

Official

Turn fuzzy intent into a measurable goal with explicit verification before any work begins.

by OpenAI26.4k stars

figma

Official

Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, d

by OpenAI26.4k stars

Connects Figma design components to their matching code components through Figma's Code Connect mapping workflow.

by OpenAI26.4k stars

Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma. Handles plan resolution via whoami if needed.

by OpenAI26.4k stars