Anthropic · install guide
Claude apps (claude.ai) skills. Where they live and how to install them.
Where Claude apps (claude.ai) loads skills
- Docs
- support.claude.com
- Website
- claude.ai
- Custom skills need code execution and file creation turned on (Settings > Capabilities; on Team and Enterprise, Organization settings > Plugins & skills > Policy tab).
- The Help Center lists Free, Pro, Max, Team and Enterprise plans; Anthropic's API docs list Pro, Max, Team and Enterprise. Check your plan in Customize > Skills.
- Anthropic's pre-built pptx, xlsx, docx and pdf skills are active when you create documents; example skills can be toggled on in Customize > Skills.
- Uploaded skills are personal. Team and Enterprise owners can provision skills for everyone, and members can share with colleagues or groups when owners allow it.
- Anthropic's docs say a skill name cannot contain the reserved words 'anthropic' or 'claude'.
- The Help Center upload guide calls the file skill.md and cites a 64-character name and 200-character description; the open standard and API docs use SKILL.md with a 1,024-character description. Follow the open standard and read the upload error if it complains.
- Skills you enable here also load in Claude Code when you sign in with the same account (Claude Code 2.1.273 or later). They do not sync to the API.
How to install a skill
zip -r {skill}.zip {skill}/Then open Customize > Skills, click +, choose + Create skill > Upload a skill, and pick the ZIP. The ZIP must contain the skill folder as its root, not loose files.
zip -r mcp-builder.zip mcp-builder/Example with MCP Server Builder.
git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && cp -r skills-src/{path} {skill} && zip -r {skill}.zip {skill} && rm -rf skills-srcBuilds the same ZIP from a skill that lives in a GitHub repo, ready to upload in Customize > Skills.
git clone --depth 1 https://github.com/anthropics/skills.git skills-src && cp -r skills-src/skills/mcp-builder mcp-builder && zip -r mcp-builder.zip mcp-builder && rm -rf skills-srcExample with MCP Server Builder.
Guide
How to add agent skills to Claude (claude.ai)
What skills are in the Claude apps
In claude.ai, a skill is a packaged folder of instructions, optional scripts and reference files that Claude uses when a task matches. Anthropic provides pre-built skills for Excel, Word, PowerPoint and PDF work. When code execution and file creation are on, Claude uses them automatically while you create documents. You can also upload your own custom skills.
There is no skills folder on your computer for claude.ai. You upload a ZIP file in the web or desktop app instead. Custom skills are tied to your account: skills you upload are not visible to colleagues until you share them, and they do not sync to the Claude API.
Requirements
- Code execution and file creation must be enabled. On Free, Pro and Max plans that is in Settings > Capabilities. On Team and Enterprise plans an owner enables it in Organization settings > Plugins & skills, on the Policy tab.
- Anthropic's Help Center says skills are available on the Free, Pro, Max, Team and Enterprise plans. Its API documentation lists Pro, Max, Team and Enterprise, so check Customize > Skills on your own plan.
- On Team and Enterprise, an owner can turn off user-created skills, in which case you can use provisioned skills but not upload your own.
Install a skill
The examples use frontend-design from anthropics/skills, located at skills/frontend-design.
Option 1: zip a skill folder you already have
The ZIP must contain the skill folder as its root, not loose files:
zip -r frontend-design.zip frontend-design/
The folder name should match the skill's name, and the folder must contain SKILL.md.
Option 2: build the ZIP from a GitHub repository
git clone --depth 1 https://github.com/anthropics/skills.git skills-src
cp -r skills-src/skills/frontend-design frontend-design
zip -r frontend-design.zip frontend-design
rm -rf skills-src
Then upload it
- Open Customize > Skills.
- Click the + button, then + Create skill.
- Choose Upload a skill and select the ZIP.
- Your skill appears in the list with a toggle. Turn it on.
Pre-built example skills are also listed on the same page, where you can switch them on without uploading anything.
Check that it loaded
Open Customize > Skills and confirm the skill is listed and switched on. Then try a prompt that matches its description and look at Claude's reasoning to see whether it loaded the skill. Disabled skills are not available to Claude. On Team and Enterprise plans, your list is grouped into sections such as personal skills and organization skills.
Share, update and remove
- Update: the Help Center does not describe replacing an upload in place, so delete the old copy and upload the new ZIP.
- Remove: open Customize > Skills, click the skill, switch it off, then use the ... button next to the toggle and choose Delete. To bring it back, upload the file again.
- Share: on Team and Enterprise, owners must first allow sharing. Then you can share a skill with colleagues or groups, or publish it to the organization's library. Shared skills are view-only for recipients, and owners can also provision skills for everyone.
- Claude Code: skills you enable here also download into Claude Code when you sign in with the same account (Claude Code 2.1.273 or later).
Troubleshooting
- Upload fails: the Help Center lists a ZIP over the size limit, a folder name that does not match the skill name, a missing skill file, and invalid characters in the name or description.
- The ZIP has the wrong shape: if the files sit at the root of the archive rather than inside a folder, repackage it so the folder is the root.
- Name rules: Anthropic's documentation says a name cannot contain the reserved words
anthropicorclaude, and the API documentation limits names to lowercase letters, numbers and hyphens. - Limits disagree between pages: the Help Center's upload guide cites a 64-character name and a 200-character description and calls the file
skill.md, while the open standard and the API documentation useSKILL.mdand allow 1,024 characters. Keep the description short and useSKILL.md, as public skill repositories do, then read the error message if an upload is rejected. - Skills are greyed out or missing: check that code execution is enabled for you, or ask your organization owner on Team and Enterprise.
Safety
Skills can carry scripts, and in claude.ai they run in Claude's code execution environment. Network access there depends on your own and your organization's settings. Review SKILL.md and every bundled file before you upload a skill you did not write. Anthropic recommends using skills only from sources you trust. On Enterprise plans an organization can turn on skill scanning, which checks third-party skills for malicious content before they can run.
Top skills to try in Claude apps (claude.ai)
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation. | anthropics/ | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 2 | Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR. | anthropics/ | 180k | 48 repos | ~2k | Automated safety check: Pass | Proprietary | 2 days ago |
| 3 | Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file. | anthropics/ | 180k | 40 repos | ~769 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 4 | Builds animated HTML slide decks that run in the browser with no dependencies, or converts PowerPoint files to the web, starting from visual style previews. | zarazhangrui/ | 30k | 16 repos | ~7k | Automated safety check: Pass | MIT | 3 mo ago |
| 5 | Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code. | shareAI-lab/ | 78k | 6 repos | ~1.2k | Automated safety check: Pass | MIT | 9 days ago |
| 6 | Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources. | PleasePrompto/ | 7.8k | 13 repos | ~2.4k | Automated safety check: Notes | MIT | 27 days ago |
| 7 | Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it. | makeplane/ | 60k | 12 repos | ~657 | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 8 | Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree. | obra/ | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | today |
| 9 | Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart. | anthropics/ | 37k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | today |
| 10 | Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories. | browser-use/ | 28k | 6 repos | ~3k | Automated safety check: Pass | MIT | 4 days ago |
| 11 | Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions. | addyosmani/ | 102k | 6 repos | ~2k | Automated safety check: Pass | MIT | 3 days ago |
| 12 | Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking… | vercel-labs/ | 44k | 24 repos | ~864 | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. | rolling-scopes/ | 10k | 24 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | 3 days ago |
| 14 | A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions | farm-fe/ | 5.6k | 34 repos | ~1.4k | Automated safety check: Pass | MIT | 15 days ago |
| 15 | Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review. | obra/ | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | today |
| 16 | Explores a web app with the agent-browser CLI to find bugs and UX problems, then writes a report with screenshots, repro videos and step-by-step reproduction for each issue. | vercel-labs/ | 44k | 8 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 17 | Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters. | anthropics/ | 180k | 37 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 18 | Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. | spacering-net/ | 3.8k | 15 repos | ~3.6k | Automated safety check: Pass | MIT | today |
| 19 | 19.Matplotlib Low-level plotting library for full customization. An agent skill from zLanqing/codex-claude-academic-skills. | zLanqing/ | 4.6k | 17 repos | ~2.9k | Automated safety check: Pass | MIT | 4 mo ago |
| 20 | A skill your agent uses whenever the user mentions Horizon by name in a Laravel context. | coollabsio/ | 63k | 4 repos | ~898 | Automated safety check: Pass | MIT | today |
| 21 | Gives the agent Postgres rules to consult before writing or changing tables, queries, indexes, RLS policies or migrations, and when diagnosing slow queries. | supabase/ | 2.7k | 24 repos | ~808 | Automated safety check: Pass | MIT | 5 days ago |
| 22 | Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way. | openinterpreter/ | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | today |
| 23 | Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design. | anthropics/ | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | today |
| 24 | Create new skills, modify and improve existing skills, and measure skill performance. | Azure/ | 794 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
Questions, answered from the data.
How do I install a skill in Claude apps (claude.ai)?
Upload a ZIP: zip -r {skill}.zip {skill}/. ZIP from a repo: git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && cp -r skills-src/{path} {skill} && zip -r {skill}.zip {skill} && rm -rf skills-src. Replace the placeholders with the skill's GitHub owner, repository and name; every skill page here shows the filled-in command.
What are the best skills for Claude apps (claude.ai)?
Agent skills are portable SKILL.md folders, so the catalogue's top skills work in Claude apps (claude.ai) too. The highest-ranked right now are MCP Server Builder (anthropics/skills), PDF Processing (anthropics/skills) and Web Artifacts Builder (anthropics/skills).
Sources
- https://support.claude.com/en/articles/12512180-using-skills-in-claude
- https://support.claude.com/en/articles/12512198-how-to-create-custom-skills
- https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview
- https://github.com/anthropics/skills
Checked October 7, 2026