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 1037 of 1,814
- View details
forwardSkillDev tools
Lets your agent hand off the current session to the next one when you say forward, handoff, or wrap up.
Ready to connect★ 122
- View details
fragmentsSkillDev tools
Lets your agent define reusable widget groups once and place them on multiple pages instead of rebuilding them each time.
Ready to connect★ 122
- View details
fyiSkillDocs & knowledge
Lets your agent save notes and information for later when you say things like "fyi" or "remember this".
Ready to connect★ 122
- View details
game-modeSkillAI & models
Lets your agent track your feature usage, earn levels, and view stats in a gamified mode.
Ready to connect★ 122
- View details
generate-domain-modelSkillCommerce & finance
Lets your agent generate a Mendix domain model — a Claude skill that builds entities, attributes and associations and validates them.
Ready to connect★ 122
- View details
graph-analysisSkillDocs & knowledge
Lets your agent use a graph claude skill to map dependencies and see what a code change would break.
Ready to connect★ 122
- View details
hypothesisSkillMonitoring & ops
Lets your agent write property-based Python tests that auto-generate edge cases and shrink failures to minimal examples.
Ready to connect★ 122
- View details
incubateSkillAI & models
Lets your agent clone or create GitHub repos and set up development worktrees for coding work.
Ready to connect★ 122
- View details
intranet-penetration-testingSkillAI & models
Teaches your agent how to run intranet penetration tests, from credential theft and reconnaissance to privilege escalation and lateral movement.
Ready to connect★ 122
- View details
introspectSkillAI & models
Lets your agent audit your project's development setup and find gaps to improve it.
Ready to connect★ 122
- View details
java-actionsSkillDev tools
Lets your agent write custom Java actions for Mendix and call them from microflows.
Ready to connect★ 122
- View details
java-dependenciesSkillDev tools
Lets your agent add, update, remove and audit a Mendix module's Java dependencies in Studio Pro settings.
Ready to connect★ 122
- View details
javascript-actionsSkillWeb & browsing
Lets your agent create and run JavaScript actions that execute in the browser, using DOM, fetch, or geolocation.
Ready to connect★ 122
- View details
jndi-injectionSkillDev tools
Guides your agent through finding and testing JNDI injection flaws in Java apps like Log4j2 or Spring.
Ready to connect★ 122
- View details
json-structures-and-mappingsSkillAI & models
Lets your agent create and manage JSON structures and import/export mappings for a domain model.
Ready to connect★ 122
- View details
jwt-oauth-token-attacksSkillSecurity
Gives your agent a playbook for testing JWT and OAuth tokens for weaknesses like bad signing and claim abuse.
Ready to connect★ 122
- View details
ldap-injection-testingSkillSecurity
Lets your agent test LDAP directories for injection flaws like filter manipulation and authentication bypass.
Ready to connect★ 122
- View details
level-upSkillAI & models
Lets your agent view your feature roadmap and suggest what to try next.
Ready to connect★ 122
- View details
liquid-glass-widgetsSkillDev tools
Gives your agent guidance for writing and reviewing Flutter liquid-glass widget code, setup, and transitions.
Ready to connect★ 122
- View details
live-edit-with-studio-proSkillAI & models
Lets your agent switch the Mendix model while Studio Pro has the project open, with edits appearing live.
Ready to connect★ 122
- View details
log4shell-exploitationSkillSecurity
Lets your agent understand and test Log4Shell JNDI exploitation techniques and bypasses against Log4j2 systems.
Ready to connect★ 122
- View details
macos-desktop-qaSkillDev tools
Lets your agent launch, inspect, and test the Sesori macOS desktop app like a QA tester.
Ready to connect★ 122
- View details
makefileSkillDev tools
Lets your agent create or update a project's Makefile with standard targets like build, test, and lint.
Ready to connect★ 118
- View details
manage-navigationSkillDev tools
Lets your agent inspect and change an app's navigation, including menus, home pages, and role-based routing.
Ready to connect★ 122
- View details
manage-securitySkillSecurity
Lets your agent configure Mendix app security: user roles, access rules, project security level, demo users and guest access.
Ready to connect★ 122
- View details
master-detail-pagesSkillDev tools
Lets your agent build master-detail screens with a selectable list beside a detail form in MDL.
Ready to connect★ 122
- View details
mdl-entitiesSkillAI & models
Gives your agent a syntax reference for Mendix domain model entities, attributes and associations so spellings are exact.
Ready to connect★ 122
- View details
mendix-bulk-oql-dmlSkillDev tools
Lets your agent run bulk insert, update and delete statements on Mendix data instead of looping over records one by one.
Ready to connect★ 122
- View details
mendix-odata-pushdownSkillDatabases & data
Lets your agent push OData filters, sorting and paging into a Mendix resource's SQL so queries run against the database.
Ready to connect★ 122
- View details
mendix-vega-chartsSkillAI & models
Lets your agent add Vega-Lite charts to a Mendix app, feeding chart data as rows instead of building chart payloads.
Ready to connect★ 122
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.