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

54,404 results · page 1055 of 1,814

  • ost-target-selectionSkillDev tools

    Lets your agent pick one target opportunity from a tree of options using weighted, evidence-based scoring.

    Ready to connect★ 115

    github.com/itseffi/agentic-os115 stars

    View details
  • playwright-mcp-skillSkillWeb & browsing

    Lets your agent use a Playwright skill to control a browser, navigating pages and interacting with sites.

    Ready to connect★ 115

    github.com/holon-run/uxc113 stars

    View details
  • power-mapSkillDev tools

    Lets your agent map stakeholders by power and interest to plan an engagement strategy.

    Ready to connect★ 115

    github.com/itseffi/agentic-os115 stars

    View details
  • prd-writingSkillDev tools

    Lets your agent write a PRD claude skill style document to plan high-risk, cross-team projects before coding starts.

    Ready to connect★ 115

    github.com/itseffi/agentic-os115 stars

    View details
  • problem-structuringSkillDev tools

    Lets your agent break complex problems into clear, actionable steps through structured reasoning.

    Ready to connect★ 115

    github.com/itseffi/agentic-os115 stars

    View details
  • program-intelSkillCommerce & finance

    Lets your agent summarize past disclosed bug reports for a bug bounty program to show recurring weak spots.

    Ready to connect★ 115

    github.com/bugbountywithmarco/bugbounty-disclosed-reports112 stars

    View details
  • qmd-mcp-skillSkillDocs & knowledge

    Lets your agent search a local QMD knowledge base using the qmd skill, with fast repeated queries.

    Ready to connect★ 115

    github.com/holon-run/uxc113 stars

    View details
  • recon-playbookSkillSecurity

    Lets your agent build a recon checklist or methodology for hunting a given vulnerability or tech stack.

    Ready to connect★ 115

    github.com/bugbountywithmarco/bugbounty-disclosed-reports112 stars

    View details
  • render-evidenceSkillMedia

    Lets your agent capture before/after rendered PNG screenshots as visual evidence for UI-affecting pull requests.

    Ready to connect★ 115

    github.com/yschimke/compose-ai-tools115 stars

    View details
  • report-searchSkillSearch

    Lets your agent search ~10k disclosed HackerOne bug bounty reports by vulnerability type, technique, program, or keyword.

    Ready to connect★ 115

    github.com/bugbountywithmarco/bugbounty-disclosed-reports112 stars

    View details
  • severitySkillSecurity

    Lets your agent rate how severe a security vulnerability is and explain its impact.

    Ready to connect★ 115

    github.com/bugbountywithmarco/bugbounty-disclosed-reports112 stars

    View details
  • signal-identificationSkillMedia

    Lets your agent design quick early signals to test whether an assumption is right.

    Ready to connect★ 115

    github.com/itseffi/agentic-os115 stars

    View details
  • slack-message-checkSkillCommunication

    Lets your agent check Slack for important messages and activity as part of daily planning, a Slack Claude skill.

    Ready to connect★ 115

    github.com/itseffi/agentic-os115 stars

    View details
  • slack-openapi-skillSkillCommunication

    Lets your agent use a Slack Claude skill to read and send Slack messages through the Slack Web API.

    Ready to connect★ 115

    github.com/holon-run/uxc113 stars

    View details
  • spec-writingSkillDev tools

    Lets your agent turn a PRD or requirements into a technical spec with scope, interfaces, and acceptance criteria.

    Ready to connect★ 115

    github.com/itseffi/agentic-os115 stars

    View details
  • stage-trace-testSkillCommunication

    Lets your agent fix failing simulation tests by reading trace diffs and updating expected traces.

    Ready to connect★ 115

    github.com/pragma-org/amaru114 stars

    View details
  • stakeholder-risk-reviewSkillDev tools

    Lets your agent review a feature plan or PRD for stakeholder pushback and political risks before wide sharing.

    Ready to connect★ 115

    github.com/itseffi/agentic-os115 stars

    View details
  • stewardSkillProductivity

    Guides your agent through getting a pull request to green, from fixing CI failures to handling review comments.

    Ready to connect★ 115

    github.com/yschimke/compose-ai-tools115 stars

    View details
  • structured-product-strategySkillDev tools

    Lets your agent draft a full product strategy covering objectives, users, vision, pillars, and roadmap.

    Ready to connect★ 115

    github.com/itseffi/agentic-os115 stars

    View details
  • sui-jsonrpc-skillSkillDev tools

    Lets your agent query the Sui blockchain over JSON-RPC for read-only data and subscribe to events.

    Ready to connect★ 115

    github.com/holon-run/uxc113 stars

    View details
  • sync-agentSkillAI & models

    Lets your agent audit and update AGENTS.md, Copilot instructions, and other agent config files to match your code.

    Ready to connect★ 115

    github.com/thun-res/vlink115 stars

    View details
  • sync-reviewSkillDocs & knowledge

    Lets your agent audit code, docs, build files, and workflows for missing or outdated content across a project.

    Ready to connect★ 115

    github.com/thun-res/vlink115 stars

    View details
  • tb-best-practicesSkillDev tools

    Gives your agent the best claude skill guidance for writing well-structured, professional-quality hardware testbenches.

    Ready to connect★ 115

    github.com/codejunkie99/gateflow-plugin110 stars

    View details
  • telegram-openapi-skillSkillCommunication

    Lets your agent send and manage Telegram bot messages, read updates, and handle webhooks.

    Ready to connect★ 115

    github.com/holon-run/uxc113 stars

    View details
  • thegraph-mcp-skillSkillCloud & infra

    Lets your agent find blockchain data subgraphs and run GraphQL queries against them.

    Ready to connect★ 115

    github.com/holon-run/uxc113 stars

    View details
  • thegraph-token-mcp-skillSkillDev tools

    Lets your agent look up crypto token data like prices, wallet balances, transfers, and holders.

    Ready to connect★ 115

    github.com/holon-run/uxc113 stars

    View details
  • tidyfactor-stylerSkillDev tools

    Lets your agent restyle and polish UI in existing codebases, including layout, typography, and color changes.

    Ready to connect★ 115

    github.com/tidyfactor/styler115 stars

    View details
  • upbit-openapi-skillSkillDocs & knowledge

    Lets your agent look up Upbit cryptocurrency exchange market data like prices and order books.

    Ready to connect★ 115

    github.com/holon-run/uxc113 stars

    View details
  • uxcSkillAI & models

    Lets your agent discover, inspect, and call remote APIs like OpenAPI, GraphQL, and gRPC through one command-line tool.

    Ready to connect★ 115

    github.com/holon-run/uxc113 stars

    View details
  • uxc-skill-creatorSkillDev tools

    Helps your agent create new skills that connect to remote tools using reusable templates and validation guidance.

    Ready to connect★ 115

    github.com/holon-run/uxc113 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.

53,973 of the 54,404 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