Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Filter by category
70,704 results · page 1643 of 2,357
- View details
surgeonSkillDev tools
Lets your agent refactor one module at a time using safe, incremental patterns like Strangler Fig.
Ready to connect★ 88
- View details
suspicious-login-triageSkillSecurity
Lets your agent investigate suspicious user login events and decide if they need action.
Ready to connect★ 88
- View details
tailwind-react-guidelinesSkillAI & models
Frontend React 19 + TypeScript + TailwindCSS v4 + shadcn/ui for Vite SPA. Components, React Query, forms (RHF + Zod), testing (Vitest + RTL + MSW), lazy loading, Suspense, Sonner. Use when creating components, pages, styling, data fetching, forms, tests, optimization.
Ready to connect★ 88
- View details
theory-ingestSkillDocs & knowledge
Lets your agent add a theoretical modeling paper to a research wiki as structured cards of assumptions, theorems, and testable corollaries.
Ready to connect★ 88
- View details
todo-listSkillProductivity
Personal to-do list (todolist) CRUD tool supporting multi-level nesting of projects/subtasks, automatic parent progress rollup, and soft-delete recycle bin. Whenever the user sends a command starting with "ta#" (e.g. ta#add a task, ta#see what's unfinished, ta#mark item 2 done, ta#delete item 3, ta#
Ready to connect★ 88
- View details
trend-scoutSkillMonitoring & ops
Lets your agent scan market trends and competitor activity across Product Hunt, GitHub, HackerNews, and social platforms.
Ready to connect★ 88
- View details
triage-alertsSkillMonitoring & ops
Lets your agent evaluate and categorize incoming security alerts to decide which need attention.
Ready to connect★ 88
- View details
url-get-gti-reportSkillSecurity
Lets your agent look up a URL's threat classification and category from Google Threat Intelligence.
Ready to connect★ 88
- View details
url-get-secops-threat-intelSkillSecurity
Lets your agent look up threat intelligence indicators in Google SecOps for a specific item.
Ready to connect★ 88
- View details
url-search-chronicleSkillSearch
Lets your agent search Chronicle proxy and web access logs for HTTP and HTTPS activity.
Ready to connect★ 88
- View details
user-lookup-entity-chronicleSkillDev tools
Lets your agent look up a user's details in Chronicle, such as department and manager.
Ready to connect★ 88
- View details
user-search-login-activity-chronicleSkillSearch
Lets your agent search Chronicle for a user's recent login and authentication activity.
Ready to connect★ 88
- View details
user-search-process-activity-chronicleSkillSearch
Lets your agent search Chronicle endpoint logs for process launches.
Ready to connect★ 88
- View details
ux-ui-guidelinesSkillSearch
UX/UI guidelines for React 19 + Tailwind v4. Design system (OKLCH colors), accessibility (WCAG 2.2, ARIA), responsive design (mobile-first, container queries), animations (Motion, View Transitions, prefers-reduced-motion), UI patterns (navigation, tables, search, onboarding), interface polish (conce
Ready to connect★ 88
- View details
variable-mapSkillDocs & knowledge
Lets your agent explain how an economics or management research variable is measured, calculated, and used in models.
Ready to connect★ 88
- View details
video-creatorSkillMedia
Lets your agent plan videos with a video claude skill that writes scripts, storyboards, and shot lists.
Ready to connect★ 88
- View details
xteink-displaySkillCommunication
Lets your agent send messages to an MQTT broker that shows up on an XTeInk e-ink display.
Ready to connect★ 88
- View details
zroastuj-mnieSkillAI & models
Grills the user about every aspect of a plan or project until fully understood, resolving every branch of the decision tree. Use when the user wants to stress-test a plan, asks for a "roast", "zroastuj", wants to talk the topic through, or says "podważ to" (challenge this).
Ready to connect★ 88
- View details
3d-model-generator-by-threejsSkillWeb & browsing
Lets your agent create 3D models from plain-language requests using Three.js, with previews and export files.
Ready to connect★ 82
- View details
acid-depth-posterSkillMedia
Lets your agent turn themes, articles, or titles into an experimental poster prompt with sharp foreground and blurred background layers.
Ready to connect★ 87
- View details
add-cucumber-testsSkillDatabases & data
Lets your agent add Claude skill-style Cucumber BDD tests (.feature files) generated from a functional specification.
Ready to connect★ 86
- View details
afu-llm-todoSkillDocs & knowledge
Lets your agent turn an Obsidian inbox into a wiki, then into weekly todo cards and a calendar.
Ready to connect★ 87
- View details
agent-rulesSkillFiles & storage
Lets your agent create and update AGENTS.md rule files that document how AI agents should work with a codebase.
Ready to connect★ 87
- View details
amq-remoteSkillCommunication
Lets your agent receive messages from you via the Buzz phone or desktop apps and reply within the same session.
Ready to connect★ 87
- View details
amq-specSkillCommunication
Lets your agent team up with another AI agent to research a design separately and agree on one shared specification.
Ready to connect★ 87
- View details
assholeSkillDev tools
Lets your agent critique your writing harshly, challenging every claim and poking holes in your logic.
Ready to connect★ 87
- View details
auto-paperSkillDev tools
Lets your agent use the auto-paper research workflow through its documented Harness aliases.
Ready to connect★ 87
- View details
auto-paper-argumentSkillDev tools
Lets your agent use the auto-paper-argument instructions to help build and check arguments in research papers.
Ready to connect★ 87
- View details
auto-paper-citationSkillDev tools
Lets your agent automatically add citations to papers using the auto-paper-citation harness instructions.
Ready to connect★ 87
- View details
auto-paper-dataSkillDev tools
Lets your agent follow the auto-paper-data instructions by routing through the visible Harness aliases.
Ready to connect★ 87
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
68,574 of the 70,704 skills listed here can be served through Ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your workspace and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.