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

58,489 results · page 454 of 1,950

  • ruanzhuSkillFiles & storage

    Lets your agent generate software copyright source code documentation as a DOCX file.

    Ready to connect★ 1k

    github.com/doccker/cc-use-exp1k stars

    View details
  • rust-devSkillDev tools

    Gives your agent a rust claude skill with Axum + Tokio guidelines, error handling, async pitfalls and testing standards.

    Ready to connect★ 1k

    github.com/doccker/cc-use-exp1k stars

    View details
  • size-checkSkillFiles & storage

    Lets your agent review changed code for reuse, quality, and efficiency, fix issues, and check file size limits.

    Ready to connect★ 1k

    github.com/doccker/cc-use-exp1k stars

    View details
  • storage-url-safetySkillFiles & storage

    Guides your agent in choosing safe file storage URLs so links don't expire or break when using services like S3.

    Ready to connect★ 1k

    github.com/doccker/cc-use-exp1k stars

    View details
  • streaming-export-safetySkillFiles & storage

    Helps your agent write code that exports large files without running out of memory or leaving temp files behind.

    Ready to connect★ 1k

    github.com/doccker/cc-use-exp1k stars

    View details
  • time-zone-safetySkillDatabases & data

    Flags code that uses current-time calls or compares across timezones so your agent can fix timezone bugs before they cause wrong statistics.

    Ready to connect★ 1k

    github.com/doccker/cc-use-exp1k stars

    View details
  • kotlin-tooling-agp9-migrationSkillAI & models

    Using the kotlin Claude skill, migrates KMP projects to Android Gradle Plugin 9, fixing builds that break after upgrade.

    Ready to connect★ 1k

    github.com/kotlin/kotlin-agent-skills1k stars

    View details
  • agentic-test-creationSkillWeb & browsing

    Guides your agent to write Playwright e2e tests from a user story or bug report, discovering existing page objects and fixtures first.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • assertionsSkillDev tools

    Guides your agent to write correct expect() assertions in Playwright end-to-end tests, using custom matchers and translation checks.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • basic-syntaxSkillMedia

    Gives your agent the coding style rules for Trezor Suite so it writes consistent TypeScript and React code.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • commentsSkillDev tools

    Gives your agent conventions for writing clear, minimal code comments when working on Trezor Suite code.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • common-issuesSkillDev tools

    Lets your agent look up fixes for known Trezor Suite build, test, and environment problems.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • common-tasksSkillProductivity

    Lets your agent manage dependencies, create packages, and troubleshoot builds in the Trezor Suite codebase.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • defensive-programmingSkillDev tools

    Guides your agent to write safer TypeScript with exhaustive checks, Result-style error handling, and non-mutating array methods.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • dependency-injectionSkillDev tools

    Teaches your agent the repo's dependency injection conventions so it writes services, factories, and composition roots that match the codebase.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • development-commandsSkillDev tools

    Lets your agent run, build, lint, and test code in the Trezor Suite monorepo using the right yarn commands.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • git-and-commit-guidelinesSkillDev tools

    Gives your agent a git claude skill so it writes Conventional Commits and follows pull request best practices.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • idb-migrationsSkillFiles & storage

    Guides your agent in writing IndexedDB storage migrations for Trezor Suite data between app versions.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • locatorsSkillDev tools

    Gives your agent a set of rules for finding page elements reliably when writing end-to-end tests.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • packagesSkillDev tools

    Teaches your agent how to create and structure packages in the Trezor Suite monorepo.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • page-objectsSkillDev tools

    Guides your agent in writing page object classes for end-to-end UI tests, with naming rules and patterns.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • performance-complexitySkillDev tools

    Teaches your agent to write faster loops, sorts and reduces when processing accounts, tokens, transactions or UTXOs.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • performance-domSkillWeb & browsing

    Gives your agent coding guidance for measuring, scrolling, and animating DOM elements without causing layout thrash.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • performance-react-hooksSkillMedia

    Guides your agent to write efficient React hooks and memoization so components avoid unnecessary re-renders.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • performance-schedulingSkillDatabases & data

    Lets your agent defer non-essential app tasks like analytics or prefetching until the browser is idle.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • publish-configSkillDev tools

    Lets your agent set publishConfig fields when you publish claude skill packages to npm.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • retriesSkillWeb & browsing

    Helps your agent fix flaky end-to-end tests by waiting and retrying properly instead of using fixed delays.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • security-headersSkillSecurity

    Guides the agent to apply security rules like security claude skill checks, avoiding unsafe JS eval in generated code.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • setup-requirementsSkillDev tools

    Guides your agent through setting up the Trezor Suite dev environment with Node.js, Yarn, Git LFS, and submodules.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k stars

    View details
  • skills-and-code-style-contributionSkillDev tools

    Lets your agent propose code style changes to Trezor Suite via issues and pull requests.

    Ready to connect★ 1k

    github.com/trezor/trezor-suite1k 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.

58,489 of the 58,489 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.

See how to connect your AI