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
54,680 results · page 632 of 1,823
- View details
components-buildSkillMonitoring & ops
Lets your agent build and review accessible, composable React UI components following a set specification.
Ready to connect★ 391
- View details
control-uiSkillWeb & browsing
Lets your agent drive and inspect a local browser or Electron app UI to take screenshots and reproduce bugs.
Ready to connect★ 391
- View details
cyclomatic-complexitySkillDev tools
Lets your agent refactor code to reduce cyclomatic complexity so it stays readable and maintainable.
Ready to connect★ 391
- View details
design-system-patternsSkillMonitoring & ops
Guides your agent in building design systems with tokens, theming, and component architecture patterns.
Ready to connect★ 391
- View details
domain-modelSkillMonitoring & ops
Lets your agent build domain models, glossaries, and shared terminology for a project.
Ready to connect★ 391
- View details
emil-design-engineeringSkillMonitoring & ops
Lets your agent apply design engineering principles when building or reviewing web interfaces.
Ready to connect★ 391
- View details
github-actions-templatesSkillCloud & infra
Lets your agent create GitHub Actions workflow files for automated testing, building, and deploying your apps.
Ready to connect★ 391
- View details
grill-for-unknownsSkillMonitoring & ops
Lets your agent surface hidden assumptions and blindspots before implementation.
Ready to connect★ 391
- View details
ideagramSkillDev tools
Lets your agent find a matching illustration from the unDraw library and recolor it to your brand color.
Ready to connect★ 385
- View details
idempotency-handlingSkillMonitoring & ops
Guides your agent to add idempotency keys so retried operations don't cause duplicate effects.
Ready to connect★ 391
- View details
improve-animationsSkillMonitoring & ops
Lets your agent review a codebase's animations and produce a prioritized audit with implementation plans.
Ready to connect★ 391
- View details
inngest-agentsSkillMonitoring & ops
Helps your agent build and run durable AI workflows with steps, retries, human approval, and crash-safe execution.
Ready to connect★ 391
- View details
inngest-apiSkillMonitoring & ops
Lets your agent inspect and manage Inngest accounts, keys, webhooks, function runs, and traces via its API.
Ready to connect★ 391
- View details
inngest-brownfield-auditSkillMonitoring & ops
Lets your agent scan an existing TypeScript or JavaScript codebase to find where background jobs and durability are needed.
Ready to connect★ 391
- View details
inngest-durable-functionsSkillMonitoring & ops
Lets your agent build background jobs that retry on failure, run on schedules, react to events, and survive crashes.
Ready to connect★ 391
- View details
inngest-eventsSkillMonitoring & ops
Lets your agent design event-driven workflows with fan-out, dedupe, and at-least-once delivery from sources like webhooks.
Ready to connect★ 391
- View details
inngest-flow-controlSkillMonitoring & ops
Lets your agent handle rate limits, batch events, debounce duplicates, and control concurrency when running workflows.
Ready to connect★ 391
- View details
inngest-middlewareSkillMonitoring & ops
Lets your agent add shared features like logging, error tracking, and encryption to background job functions.
Ready to connect★ 391
- View details
inngest-realtimeSkillWeb & browsing
Lets your agent stream live workflow updates to a web UI as steps complete, like order statuses or AI output.
Ready to connect★ 391
- View details
inngest-setupSkillMonitoring & ops
Guides your agent through setting up background jobs, retries, and scheduled tasks in a TypeScript project.
Ready to connect★ 391
- View details
inngest-stepsSkillMonitoring & ops
Lets your agent add delays, waits for approvals, and poll external services that survive crashes and restarts.
Ready to connect★ 391
- View details
inngest-v3-v4-migrationSkillMonitoring & ops
Guides your agent through upgrading a TypeScript codebase from Inngest SDK v3 to v4, including fixing mixed API usage.
Ready to connect★ 391
- View details
interface-designSkillMonitoring & ops
Helps your agent design and build interfaces like dashboards, admin panels, and interactive apps.
Ready to connect★ 391
- View details
lint-and-validateSkillMonitoring & ops
Lets your agent automatically check code for syntax errors and style problems after edits.
Ready to connect★ 391
- View details
moai-library-shadcnSkillMonitoring & ops
Lets your agent build and customize UI components using the shadcn/Base UI system with a fixed style.
Ready to connect★ 391
- View details
motionSkillMonitoring & ops
Helps your agent write smooth, accessible React animations using motion/react with gestures and layout transitions.
Ready to connect★ 391
- View details
nextjs-app-routerSkillMonitoring & ops
Lets your agent build Next.js apps with correct routing, component boundaries, and data fetching.
Ready to connect★ 391
- View details
nextjs-supabase-authSkillDatabases & data
Lets your agent add Supabase login and protected pages to a Next.js app with middleware and auth callbacks.
Ready to connect★ 391
- View details
nlmSkillFiles & storage
Lets your agent create and manage Google NotebookLM notebooks, add sources, chat with them, and generate reports or slides.
Ready to connect★ 391
- View details
npm-deps-cleanupSkillMonitoring & ops
Lets your agent audit and trim unused JavaScript package dependencies across npm, pnpm, Yarn, and Bun projects.
Ready to connect★ 391
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.
54,249 of the 54,680 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 gateway 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.