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

70,730 results · page 1489 of 2,358

  • run-localSkillCloud & infra

    Lets your agent run claude skill loops that keep a Mendix app hot so model changes go live in about a second.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • runtime-admin-apiSkillDev tools

    Lets your agent query a running Mendix app's admin API directly, including OQL queries and runtime info.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • scheduled-events-and-queuesSkillProductivity

    Run a microflow on a schedule by setting up Mendix scheduled events and task queues.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • skill-testSkillDev tools

    Checks whether your agent's skill system is set up and running properly.

    Ready to connect★ 125

    github.com/andrefetch/postal128 stars

    View details
  • story-douban-long-writeSkillDev tools

    Lets your agent organize a long original novel's theme, plot, and synopsis into inputs for a novel-writing pipeline.

    Ready to connect★ 128

    github.com/xiaoyangy/novel-studio99 stars

    View details
  • strict-enforcementSkillDev tools

    Lets your agent verify code quality and issue pass/fail verdicts based on real evidence, not just passing tests.

    Ready to connect★ 128

    github.com/povvo/claudikins-kernel128 stars

    View details
  • study-workflowSkillMedia

    Generates a publication-quality research workflow diagram as a PNG via gpt-image-2 (OpenAI image API).

    Ready to connect★ 128

    github.com/ai4scientist/nano-scientist128 stars

    View details
  • system-moduleSkillFiles & storage

    Lets your agent look up how to link records to users, handle file uploads, and use workflow entities.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • test-microflowsSkillFiles & storage

    Lets your agent write and run tests for Mendix microflow logic using the mxcli test command.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • testing-dbt-modelsSkillFiles & storage

    Lets your agent add data quality tests to dbt models and debug failing ones.

    Ready to connect★ 127

    github.com/altimateai/data-engineering-skills128 stars

    View details
  • theme-stylingSkillMedia

    Guides your agent through writing and debugging Mendix app styling with SCSS, themes, and mxcli theme commands.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • translationsSkillFiles & storage

    Lets your agent translate a Mendix app's interface strings by exporting them per language and writing translations back.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • upgrade-mendix-versionSkillWeb & browsing

    Lets your agent upgrade a Mendix project to a newer version from the command line, without opening Studio Pro.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • validation-microflowsSkillCommunication

    Guides your agent to write Mendix input-validation flows that check form fields and show error messages.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • verify-with-oqlSkillWeb & browsing

    Lets your agent check that data changes in a running app happened as expected by querying its database.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • write-layoutsSkillDev tools

    Lets your agent create and change page layouts, including topbars, sidebars, navigation trees and placeholders.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • write-lint-rulesSkillAI & models

    Teaches your agent to write Claude Skill-based Starlark lint rules that mxcli runs next to its built-in checks.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • write-microflowsSkillDev tools

    Teaches your agent to write Mendix microflows in MDL syntax, working like a write claude skill reference.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • write-nanoflowsSkillDev tools

    Write Claude skill content that guides building correct Mendix nanoflows in MDL syntax.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • write-oql-queriesSkillDatabases & data

    Lets your agent write OQL for Mendix VIEW entities using this Claude skill covering joins, aggregates, and valid syntax.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • write-rulesSkillDev tools

    Shows your agent how to write Claude skill-style Mendix rules that return true/false answers for decisions.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • write-workflowsSkillProductivity

    Lets your agent write Mendix workflow files with tasks, decisions, timers and parallel branches.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • xpath-constraintsSkillDev tools

    Gives your agent correct XPath query syntax for filtering Mendix data in retrieves, pages, and access rules.

    Ready to connect★ 128

    github.com/mendixlabs/mxcli122 stars

    View details
  • amazon-returns-recoverySkillMedia

    Lets your agent audit Amazon charges to recover restocking fees, denied refunds, and forgotten subscriptions.

    Ready to connect★ 127

    github.com/jasoncolapietro/suede-creator-skills127 stars

    View details
  • axhub-annotation-standaloneSkillDocs & knowledge

    Guides your agent to add annotation markers, notes, and directories to standalone web pages or React apps.

    Ready to connect★ 127

    github.com/lintendo/axhub-skills127 stars

    View details
  • axhub-commentarySkillDocs & knowledge

    Lets your agent read page comments, apply the requested changes, and mark comments done in Axhub projects.

    Ready to connect★ 127

    github.com/lintendo/axhub-skills127 stars

    View details
  • axhub-prototype-contextSkillAI & models

    Lets your agent read a prototype's product requirements, page structure, and annotations so it can review or build on it.

    Ready to connect★ 127

    github.com/lintendo/axhub-skills127 stars

    View details
  • build-design-systemSkillWeb & browsing

    Lets your agent extract a website's colors, fonts and styles into a design spec and Tailwind theme files.

    Ready to connect★ 127

    github.com/lintendo/axhub-skills127 stars

    View details
  • china-customer-researchSkillDev tools

    Lets your agent run customer and user research across China, overseas, and cross-market contexts using real evidence.

    Ready to connect★ 127

    github.com/lintendo/axhub-skills127 stars

    View details
  • clone-pageSkillWeb & browsing

    Lets your agent capture a webpage and rebuild it as a complete HTML/CSS copy.

    Ready to connect★ 127

    github.com/lintendo/axhub-skills127 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.

68,599 of the 70,730 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