# Anthropic Skills By **anthropics** ยท Skills Anthropic's official skill library for Claude: modular SKILL.md bundles that add repeatable, domain-specific workflows across docs, dev, design, and enterprise tasks. - Source: https://github.com/anthropics/skills - Repository: https://github.com/anthropics/skills - Tags: open-source, claude, agent, anthropic, cli, document-processing, enterprise - Pricing: freemium - Upvotes: 0 ## Features - Dynamic skill loading: Claude picks up SKILL.md instructions automatically when relevant - Three-level progressive disclosure: metadata, instructions, and scripts load in stages - Pre-built document skills for PDF, Word, PowerPoint, and Excel (production-grade) - Creative skills: algorithmic art, canvas design, frontend design, theme factory - Development skills: MCP server builder, webapp testing, web artifacts builder, skill creator - Enterprise skills: brand guidelines, internal comms, doc coauthoring, Slack GIF creator - Custom skill authoring via a simple SKILL.md template with just name and description fields - Partner skill support (e.g. Notion Skills for Claude) --- ## Why it matters Skills turn Claude from a general assistant into a repeatable specialist. Instead of re-prompting the same workflows every session, a skill loads its instructions automatically when Claude decides they are relevant, per the platform docs. ## The big picture Anthropic's skills repository is the canonical reference implementation of the Agent Skills standard (documented separately at agentskills.io). The repo ships four major skill sets: document processing (PDF, Word, PowerPoint, Excel), development tools (MCP builder, webapp testing, web artifacts), creative tools (algorithmic art, canvas design, frontend design, theme factory), and enterprise workflows (brand guidelines, internal comms, doc coauthoring, Slack GIF creator). ## How it works Each skill is a self-contained folder with a single SKILL.md file. YAML frontmatter supplies a `name` and `description` Claude uses for discovery. The markdown body holds instructions, examples, and guidelines. Skills use a three-level progressive disclosure model: metadata loads always, instructions load when the skill is selected, and optional scripts or templates load only when the task calls for them. This keeps context usage low. ## Zoom in The document skills (docx, pdf, pptx, xlsx) are the same skills that power Claude.ai's built-in document creation features. They are source-available (not Apache 2.0) but included so developers can study a production-grade, actively deployed skill as a reference. Custom skills follow the same SKILL.md format and can be uploaded via the Claude API, Claude Code, or Claude.ai settings. ## Yes, but The repo README is explicit: these skills are for demonstration and educational purposes. Behavior you see in the repo may differ from what Claude produces in a live product. Test any custom skill thoroughly before using it in critical workflows. ## The bottom line If you need Claude to reliably follow a specialized workflow, brand standard, or multi-step process across many conversations, skills are the right abstraction. The Anthropic repo gives you working examples for every major category, a clean template to clone, and the spec to build against. ## FAQ ### What is Anthropic Skills? Anthropic Skills is Anthropic's official GitHub repository of modular, filesystem-based skill packages that extend Claude's behavior for specialized tasks. Each skill is a folder containing a SKILL.md file with YAML frontmatter (name and description) and markdown instructions that Claude loads dynamically. The repo covers document processing, creative tools, development utilities, and enterprise workflows, and also serves as the reference implementation of the open Agent Skills standard. ### How do I install and use skills from this repository? In Claude Code, run `/plugin marketplace add anthropics/skills` to register the repo, then browse and install either `document-skills` or `example-skills` from the `anthropic-agent-skills` marketplace entry. On Claude.ai, the example skills are already available to paid plan users with no setup needed. Via the Claude API, use the Skills API (see the Skills API Quickstart in the docs) to upload and use pre-built or custom skills. Once installed, you activate a skill simply by mentioning the relevant task in your message. ### Is this free and open source? Most skills in the repository are open source under the Apache 2.0 license. The exception is the document creation and editing skills (docx, pdf, pptx, xlsx), which are source-available but not open source. Anthropic included them as a reference for production-grade skill design. The repository itself is free to clone and use. ### What is Anthropic Skills best for? Skills are best suited for repeatable, domain-specific workflows you run across many Claude conversations: enforcing brand guidelines, processing documents at scale, automating multi-step development tasks, or packaging organizational knowledge so teams share a consistent Claude behavior. The platform docs describe skills as the alternative to prompts when you need load-on-demand expertise rather than one-off instructions. ### How do Anthropic Skills compare to regular system prompts? Skills and system prompts solve different problems. System prompts are conversation-level, one-off instructions that must be repeated every session. Skills are filesystem-based resources Claude loads on-demand using a three-level progressive disclosure model (metadata always, instructions when selected, scripts only when needed), which keeps context consumption low and eliminates repetition. Per the platform docs, skills are designed to compose, letting you combine multiple skills to build complex workflows. ### What are the limitations or risks of using these skills? The README is explicit: skills in this repository are provided for demonstration and educational purposes only, and behavior you get from Claude may differ from what the skill definitions show. Agent Skills are also not eligible for Zero Data Retention, meaning data is retained under Anthropic's standard retention policy. Always test custom skills thoroughly in your own environment before relying on them for critical or sensitive tasks. --- [View on Analog](https://analoghq.ai/anthropics/skills/anthropic-skills)