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 592 of 1,823

  • rpiSkillDev tools

    Lets your agent apply an outcome-to-judgment workflow when explicitly selected for coding tasks.

    Ready to connect★ 441

    github.com/boshu2/agentops441 stars

    View details
  • sbhSkillFiles & storage

    Lets your agent check disk space usage and, if authorized, run a storage recovery action.

    Ready to connect★ 441

    github.com/boshu2/agentops441 stars

    View details
  • skill-evalSkillProductivity

    Lets your agent measure whether a given skill actually helps a task, or should be revised or removed.

    Ready to connect★ 441

    github.com/boshu2/agentops441 stars

    View details
  • using-flywheelSkillDev tools

    Lets your agent run a structured coding workflow loop that repeats until tasks converge and are accepted.

    Ready to connect★ 441

    github.com/boshu2/agentops441 stars

    View details
  • using-gcSkillDev tools

    Lets your agent operate Gas City workflows, managing runs through its controller and stored run state.

    Ready to connect★ 441

    github.com/boshu2/agentops441 stars

    View details
  • 001-commands-inventorySkillDocs & knowledge

    Lets your agent generate a checklist file cataloging the command files bundled for Java projects.

    Ready to connect★ 440

    github.com/jabrena/cursor-rules-java403 stars

    View details
  • 002-agents-inventorySkillDocs & knowledge

    Lets your agent generate an agents inventory checklist document in your project from a fixed template.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 003-skills-inventorySkillDocs & knowledge

    Lets your agent generate a checklist document of Java system prompts from a skills.xml file.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 004-commands-installationSkillAI & models

    Lets your agent copy ready-made command files into editor command folders like .github/commands or .claude/commands.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 005-agents-installationSkillAI & models

    Lets your agent install ready-made agent definition files into folders for GitHub, Claude, Cursor, or Codex.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 012-agile-epicSkillDocs & knowledge

    Lets your agent draft agile epics with business value, success criteria, and user story breakdowns.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 013-agile-featureSkillFiles & storage

    Lets your agent split an epic into agile feature files with scope and acceptance criteria.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 014-agile-user-storySkillDev tools

    Guides your agent to write agile user stories, including splitting feature requirements into separate stories.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 021-problem-framingSkillDev tools

    Lets your agent frame a problem clearly by writing out the issue, current and desired states, stakeholders, and success criteria.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 022-root-cause-analysisSkillDev tools

    Lets your agent investigate a problem's root cause using Five Whys, Fishbone diagrams, and constraint analysis.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 023-assumption-analysisSkillMedia

    Lets your agent list a problem's hidden assumptions, unknowns, and how to test them before planning work.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 024-context-mappingSkillMedia

    Helps your agent map a problem's surrounding systems, integrations, ownership, and dependencies before design work.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 025-quality-attribute-discoverySkillMedia

    Lets your agent identify and prioritize a system's quality attributes (non-functional requirements) before design work begins.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 030-architecture-adr-generalSkillDocs & knowledge

    Lets your agent write architecture decision records for Java projects by asking questions step by step.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 031-architecture-adr-functional-requirementsSkillDocs & knowledge

    Lets your agent guide you through writing architecture decision records for CLI or HTTP API requirements.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 032-architecture-adr-non-functional-requirementsSkillDocs & knowledge

    Walks your agent through questions to write architecture decision records for requirements like performance and security.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 033-architecture-diagramsSkillCloud & infra

    Lets your agent generate UML, C4, ER, and other architecture diagrams from a Java project.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 041-planning-plan-modeSkillDev tools

    Lets your agent create and refine a structured Java implementation plan from issues and design docs.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 042-planning-openspecSkillMedia

    Lets your agent create and update OpenSpec planning artifacts from issues, plans, and design docs.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 043-planning-github-issuesSkillSecurity

    Guides your agent through setting up the GitHub CLI and running an operator-only issue inventory workflow.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 044-planning-jiraSkillSecurity

    Guides your agent through setting up and authenticating the Jira CLI and running a maintainer-reviewed issue inventory workflow.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 045-planning-azure-devopsSkillCloud & infra

    Lets your agent find Azure DevOps work items and create or update them.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 051-design-two-steps-methodsSkillMedia

    Guides your agent to refactor code first, then make a risky change safely in two separate steps.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 052-design-hamburger-methodSkillMedia

    Lets your agent split a large feature, story, or plan into small vertical slices of shippable work.

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 053-design-simple-rulesSkillMedia

    Lets your agent review Java code against Kent Beck's four simple design rules like passing tests and clear intent.

    Ready to connect★ 440

    github.com/jabrena/plinth440 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.

54,249 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.

See how to connect your AI