What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.

Find awesome Agent Skills

review-docs

Documentation review and fix workflow for MDX files

FranciscoMoretti

1,180111

ultracite

Skill: ultracite

FranciscoMoretti

1,180111

typescript

Skill: typescript

FranciscoMoretti

1,180111

trpc-patterns

Skill: trpc-patterns

FranciscoMoretti

1,180111

react

Skill: react

FranciscoMoretti

1,180111

chat-context

Skill: chat-context

FranciscoMoretti

1,180111

lazy-prefetch-pattern

Skill: lazy-prefetch-pattern

FranciscoMoretti

1,180111

general

General repo context and behavior guidelines

FranciscoMoretti

1,180111

write-api-route

Create or modify ryOS backend API routes under api/ using the shared apiHandler wrapper, request-auth, Redis, rate limiting, and CORS conventions. Use when adding an endpoint, writing a serverless/Bun API handler, wiring auth or rate limits, or working with anything under the api/ directory.

ryokun6

1,180178

write-tests

Write and run ryOS tests with Bun's native test runner (bun:test). Covers unit/wiring tests (no server) vs API integration tests (require the standalone API server), shared HTTP helpers, and the package.json suite commands. Use when adding tests, writing test coverage for a change, or running/triaging the test suite.

ryokun6

1,180178

ui-design-styling

Design and style ryOS UI using the current OS theme token system, Tailwind variants, shared primitives, Aqua Glass, dark mode, and accent conventions. Use when creating UI components, styling elements, working with themes, adding visual effects, or implementing retro OS aesthetics.

ryokun6

1,180178

localize

Localize ryOS apps and components by extracting hardcoded strings, replacing with translation keys, and syncing across languages. Use when localizing an app, adding i18n support, translating UI text, or working with translation files.

ryokun6

1,180178

desktop-release

Cut and publish ryOS Electron desktop releases on GitHub. Covers bumping package.json version, tagging v*, triggering Build Electron, and verifying the GitHub release. Use when the user asks to release the desktop app, bump the desktop version, trigger an Electron build, or publish macOS/Windows installers.

ryokun6

1,180178

create-store

Create or modify ryOS Zustand stores following repo conventions — persist middleware, partialize, versioned migrations, the debounced write-behind storage adapter for large slices, and cloud-sync deletion tombstones. Use when adding state management, creating a use*Store, persisting app state, or wiring a store into cloud sync.

ryokun6

1,180178

update-docs

Update ryOS documentation by analyzing the codebase and syncing docs with current implementation. Use when updating docs, syncing documentation, or when docs are outdated.

ryokun6

1,180178

create-ryos-app

Create new applications for ryOS following established patterns and conventions. Use when building a new app, adding an application to the desktop, creating app components, or scaffolding app structures.

ryokun6

1,180178

add-ai-chat-tool

Add or modify an AI chat tool ("Ask Ryo" capability) in ryOS. Covers the server-side tool definition (Zod schema + description + optional execute) and the client-side handler dispatch, plus the server-vs-client execution split. Use when giving the AI a new capability, adding a tool to the chat agent, or editing chat/tool schemas, descriptions, or handlers.

ryokun6

1,180178

xhs-publisher

小红书发布 skill - 通过 agent-browser (CDP) 自动发布小红书图文笔记，支持多图上传、标题正文填写、一键发布。使用场景：自动化发布图文笔记到小红书创作中心。

inclusionai

1,177121

html-to-image

HTML 转图片 skill - 将 HTML 文件或内容通过 agent-browser 渲染并截图为图片。适用于生成信息图、社交媒体配图、数据可视化截图等场景。

inclusionai

1,177121

text2agent

Creates new agents from user requirements by generating Python implementation and mcp_config.

inclusionai

1,177121

optimizer

Analyzes and automatically optimizes existing agents by improving system prompts and tool configuration.

inclusionai

1,177121

media_comprehension

An intelligent assistant specialized in handling media files (images/audio/video). **Only for media file analysis**, does not handle document types.\n\n✅ Media files that can be processed:\n- Images: .jpg, .jpeg, .png, .gif, .bmp, .webp, .svg\n- Audio: .mp3, .wav, .m4a, .flac, .aac, .ogg\n- Video: .mp4, .avi, .mov, .mkv, .webm, .flv\n\n❌ Files that cannot be processed (please do not trigger this skill):\n- Documents: .pdf, .doc, .docx, .txt, .md, .rtf\n- Spreadsheets: .xlsx, .xls, .csv, .tsv\n- Presentations: .pptx, .ppt, .key\n- Code: .py, .js, .ts, .java, .cpp, .go, .rs\n- Archives: .zip, .tar, .gz, .rar, .7z\n- Executables: .exe, .bin, .app, .dmg\n- Databases: .db, .sqlite, .sql\n- Configuration files: .json, .xml, .yaml, .yml, .toml, .ini\n- Web pages: .html, .htm, .css\n\n**Trigger conditions**: When the user explicitly requests to analyze image/audio/video content, or when the file extension belongs to the aforementioned media types.".

inclusionai

1,177121

embedded-video-pip-smooth-playback

inclusionai

1,177121

app_evaluator

A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).

inclusionai

1,177121

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

inclusionai

1,177121