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.

Category: AI & models

8,700 results · page 2 of 290

  • google-agents-cli-adk-codeSkillAI & models

    Lets your coding assistant build, test, and deploy AI agents on Google Cloud using guided commands.

    Ready to connect★ 6k

    github.com/google/agents-cli195k installs

    View details
  • google-agents-cli-publishSkillAI & models

    Lets your agent create, test, and deploy AI agents on Google Cloud from the command line.

    Ready to connect★ 6k

    github.com/google/agents-cli195k installs

    View details
  • academy-guideSkillAI & models

    Lets your agent recommend matching Claude Academy courses, tutorials, and use cases when users ask how to use Claude.

    Ready to connect★ 176k

    github.com/anthropics/skills176k stars

    View details
  • Algorithmic ArtSkillAI & models

    Lets your agent create generative art by writing p5.js code with seeded randomness and interactive parameters.

    Ready to connect★ 176k

    github.com/anthropics/skills176k stars

    View details
  • convex-quickstartSkillAI & models

    Lets your agent build and manage Convex backend databases and functions.

    Ready to connect★ 56

    github.com/get-convex/agent-skills116k installs

    View details
  • caveman-discoverSkillAI & models

    Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

    Ready to connect★ 105k

    github.com/juliusbrussee/caveman46k installs

    View details
  • caveman-evidence-reviewSkillAI & models

    Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.

    Ready to connect★ 105k

    github.com/juliusbrussee/caveman46k installs

    View details
  • caveman-learnSkillAI & models

    🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

    Ready to connect★ 105k

    github.com/juliusbrussee/caveman47k installs

    View details
  • safe-refactorSkillAI & models

    🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

    Ready to connect★ 105k

    github.com/juliusbrussee/caveman47k installs

    View details
  • code-review-and-qualitySkillAI & models

    Lets your agent review code changes for correctness, readability, architecture, security, and performance before merging.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • code-simplificationSkillAI & models

    Lets your agent rewrite messy code to be clearer and easier to maintain without changing how it behaves.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • constraint-driven-developmentSkillAI & models

    Lets your agent set up a written quality bar for your project and stop code that weakens it.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • debugging-and-error-recoverySkillAI & models

    Guides your agent through a step-by-step process to find and fix the root cause of test failures and errors.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • doubt-driven-developmentSkillAI & models

    Makes your agent double-check its own important decisions by getting a separate adversarial review before finalizing them.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • git-workflow-and-versioningSkillAI & models

    Guides your agent to follow good git habits like clean commits, branching, pull requests, releases, and version bumps.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • idea-refineSkillAI & models

    Lets your agent turn a vague idea into a clear, structured plan through guided questioning, variation generation, and stress-testing.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • interview-meSkillAI & models

    Lets your agent interview you one question at a time to figure out what you actually want before building anything.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • test-driven-developmentSkillAI & models

    Guides your agent to write failing tests before writing code so changes and bug fixes are proven to work.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • using-agent-skillsSkillAI & models

    Helps your agent find and apply the right engineering workflow skill for whatever coding task it's working on.

    Ready to connect★ 94k

    github.com/addyosmani/agent-skills94k stars

    View details
  • mem-setupSkillAI & models

    Lets your agent set up and connect the claude-mem memory plugin using your sync credentials.

    Ready to connect★ 94k

    github.com/thedotmack/claude-mem94k stars

    View details
  • oh-my-issuesSkillAI & models

    Lets your agent group related GitHub issues by root cause into plan issues and link fix PRs.

    Ready to connect★ 94k

    github.com/thedotmack/claude-mem94k stars

    View details
  • openclawSkillAI & models

    Lets your agent remember what happened in past sessions by saving and reusing context automatically.

    Ready to connect★ 94k

    github.com/thedotmack/claude-mem94k stars

    View details
  • pathfinderSkillAI & models

    Lets your agent analyze a codebase, spot duplicated logic across features, and propose a unified architecture.

    Ready to connect★ 94k

    github.com/thedotmack/claude-mem94k stars

    View details
  • standupSkillAI & models

    Lets your agent review changes across git branches, worktrees, or PRs and produce one consolidation plan.

    Ready to connect★ 94k

    github.com/thedotmack/claude-mem94k stars

    View details
  • timeline-reportSkillAI & models

    Lets your agent generate a narrative report of a project's full development history.

    Ready to connect★ 94k

    github.com/thedotmack/claude-mem94k stars

    View details
  • version-bumpSkillAI & models

    Lets your agent bump plugin versions, update manifests, tag releases, and generate changelogs automatically.

    Ready to connect★ 94k

    github.com/thedotmack/claude-mem94k stars

    View details
  • what-theSkillAI & models

    Lets your agent turn technical topics into a plain-English breakdown of who, what, where, why, and when.

    Ready to connect★ 94k

    github.com/thedotmack/claude-mem94k stars

    View details
  • testing-heterogeneous-agentsSkillAI & models

    Manually runs the live LobeHub official-provider compatibility matrix across Claude Code, Codex, Grok Build, Kimi Code, Pi, and TRAE when explicitly invoked by the user.

    Ready to connect★ 82k

    github.com/lobehub/lobehub82k stars

    View details
  • twitter-algorithm-optimizerSkillAI & models

    Analyzes and rewrites your tweets to boost reach based on how Twitter's ranking system works.

    Ready to connect★ 75k

    github.com/composiohq/awesome-claude-skills75k stars

    View details
  • ast-grepSkillAI & models

    Lets your agent find and rewrite code by structure across 25 languages, like swapping console.log for logger.info repo-wide.

    Ready to connect★ 69k

    github.com/code-yeongyu/oh-my-openagent69k 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.

52,524 of the 52,958 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