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

55,055 results · page 743 of 1,836

  • transactional-patternsSkillDatabases & data

    Gives your agent guidance for writing code with @Transactional and reliable multi-step database operations.

    Ready to connect★ 273

    github.com/rrezartprebreza/spring-boot-skills273 stars

    View details
  • webflux-reactive-patternsSkillDev tools

    Guides your agent in building reactive Spring Boot apps with WebFlux controllers, Reactor pipelines, and R2DBC persistence.

    Ready to connect★ 273

    github.com/rrezartprebreza/spring-boot-skills273 stars

    View details
  • sivtr-memorySkillDocs & knowledge

    Lets your agent recall past local work—decisions, debugging trails, and conversation history—before asking you to repeat context.

    Ready to connect★ 272

    github.com/ariestar/sivtr257 stars

    View details
  • zigSkillFiles & storage

    Gives your agent up-to-date Zig 0.15.x coding patterns for writing, reviewing, and debugging Zig code.

    Ready to connect★ 272

    github.com/simoarpe/ziggity260 stars

    View details
  • building-native-uiSkillAI & models

    Guides your agent to build mobile app interfaces with Expo Router, covering navigation, styling, animations, and native tabs.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • codely-doc-createSkillDocs & knowledge

    Lets your agent create new documentation pages from the current conversation context.

    Ready to connect★ 271

    github.com/codelytv/agent-harness271 stars

    View details
  • codely-git-conventional_commitSkillAI & models

    Lets your agent create git commits that follow your team's Conventional Commit message format.

    Ready to connect★ 271

    github.com/codelytv/agent-harness271 stars

    View details
  • codely-plan_phase-implementSkillAI & models

    Lets your agent implement one phase of a plan at a time, stopping for your review before continuing.

    Ready to connect★ 271

    github.com/codelytv/agent-harness271 stars

    View details
  • codely-plan_phase-implement-githubSkillAI & models

    Lets your agent implement one phase of a development plan stored as GitHub issues in your repo.

    Ready to connect★ 271

    github.com/codelytv/agent-harness271 stars

    View details
  • codely-plan-create-githubSkillProductivity

    Lets your agent turn a task into a GitHub plan issue with a checklist and linked child issues per phase.

    Ready to connect★ 271

    github.com/codelytv/agent-harness271 stars

    View details
  • codely-plan-create-subagentsSkillProductivity

    Lets your agent create a step-by-step plan for a task before starting work.

    Ready to connect★ 271

    github.com/codelytv/agent-harness271 stars

    View details
  • expo-api-routesSkillCloud & infra

    Guides your agent to build server-side API routes in an Expo Router app and deploy them to EAS Hosting.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • expo-cicd-workflowsSkillFiles & storage

    Helps your agent write and check EAS workflow YAML files that automate builds and deployments for Expo apps.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • expo-deploymentSkillCloud & infra

    Lets your agent build and publish an Expo app to the App Store, Play Store, or web hosting.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • expo-dev-clientSkillAI & models

    Lets your agent build custom Expo development clients and share them locally or via TestFlight.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • just-bashSkillFiles & storage

    Lets your agent run shell commands safely in an isolated sandbox without touching your real files.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • qa-device-managementSkillAI & models

    Lets your agent boot iOS Simulators and Android Emulators, launch apps, and capture screenshots for QA testing.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • qa-scrollSkillMedia

    Lets your agent run QA tests on scroll-based video feeds, checking autoplay, navigation, mute, and playback.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • qa-setupSkillWeb & browsing

    Checks your agent's QA testing tools are installed and installs any missing ones.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • qa-state-persistenceSkillAI & models

    Lets your agent test whether app state like likes, bookmarks, and cart items survives navigating away and back.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • qa-test-flowsSkillWeb & browsing

    Lets your agent run automated UI tests on web and native apps, taking screenshots and generating JSON reports.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • qa-webSkillWeb & browsing

    Lets your agent test web apps: filling forms, checking navigation, responsive layouts, cookies, and visual changes.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • slack-webSkillWeb & browsing

    Lets your agent read, send, and reply to Slack messages, search channels, and react using a browser.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • upgrading-expoSkillAI & models

    Lets your agent upgrade Expo SDK versions and fix dependency issues in React Native projects.

    Ready to connect★ 271

    github.com/ruizrica/agent-pi267 stars

    View details
  • adr-writerSkillDev tools

    Lets your agent write architecture decision records that document context, alternatives, and outcomes.

    Ready to connect★ 270

    github.com/govctl-org/govctl267 stars

    View details
  • decision-analysisSkillMedia

    Lets your agent stress-test important decisions with premortem and backcast reasoning and return a risk-calibrated recommendation.

    Ready to connect★ 270

    github.com/govctl-org/govctl267 stars

    View details
  • detachSkillDev tools

    Lets your agent safely remove the govctl integration from a project with a dry run, backup plan, and undoable edits.

    Ready to connect★ 270

    github.com/govctl-org/govctl267 stars

    View details
  • discussSkillMedia

    Lets your agent explore a governance design and draft RFC or ADR documents.

    Ready to connect★ 270

    github.com/govctl-org/govctl267 stars

    View details
  • govSkillDev tools

    Lets your agent run governed development tasks with traceable work items, RFC/ADR approval, and scoped verification.

    Ready to connect★ 270

    github.com/govctl-org/govctl267 stars

    View details
  • guard-writerSkillDev tools

    Lets your agent run reusable verification checks that confirm code changes are safe before they are applied.

    Ready to connect★ 270

    github.com/govctl-org/govctl267 stars

    View details

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.

54,624 of the 55,055 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.

See how to connect your AI