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 1040 of 1,814
- View details
validation-microflowsSkillCommunication
Lets your agent add input validation to form pages, checking fields and showing feedback messages to users.
Ready to connect★ 122
- 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★ 122
- View details
vibeSkillFiles & storage
Guides your agent to make small, quick code changes like bug fixes, typo corrections, or minor tweaks.
Ready to connect★ 118
- View details
vulnerability-assessmentSkillSecurity
Gives your agent expert guidance on finding, scoring, and prioritizing security vulnerabilities using CVSS, EPSS, and scanners.
Ready to connect★ 122
- View details
web-cache-deceptionSkillSecurity
Guides your agent through testing whether caches leak one user's private pages to others.
Ready to connect★ 122
- View details
websocket-securitySkillCommunication
Teaches your agent how to test WebSocket connections for security flaws like cross-site WebSocket hijacking.
Ready to connect★ 122
- View details
where-we-areSkillDev tools
Lets your agent give a quick mid-session recap of the current topic, timeline, and pending items.
Ready to connect★ 122
- View details
who-are-youSkillAI & models
Lets your agent report its current AI identity, model info, and session stats when asked who it is.
Ready to connect★ 122
- View details
write-layoutsSkillDev tools
Lets your agent write Claude skill layouts for Mendix pages: frames, nav trees and placeholders.
Ready to connect★ 122
- View details
write-lint-rulesSkillAI & models
Lets your agent write claude skill lint rules in Starlark that enforce your project's conventions automatically.
Ready to connect★ 122
- View details
write-microflowsSkillDev tools
Helps your agent write a Claude skill covering Mendix microflow syntax, activities, control flow, and common errors.
Ready to connect★ 122
- View details
write-nanoflowsSkillDev tools
Lets your agent write Claude skill files covering Mendix nanoflow syntax in MDL, explain validation errors, and pick nanoflow vs microflow.
Ready to connect★ 122
- 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★ 122
- View details
write-rulesSkillDev tools
Lets your agent write claude skill files for Mendix rules, deciding when logic belongs in a rule versus a microflow.
Ready to connect★ 122
- View details
write-workflowsSkillProductivity
Lets your agent write claude skill files for Mendix workflows with tasks, decisions, timers and parallel branches.
Ready to connect★ 122
- View details
xpath-constraintsSkillDev tools
Lets your agent write and debug XPath WHERE clauses for Mendix data retrieval, including association paths and functions.
Ready to connect★ 122
- View details
xpath-injection-testingSkillSecurity
Gives your agent expert knowledge for finding and fixing XPath and XQuery injection vulnerabilities.
Ready to connect★ 122
- View details
xss-cross-site-scriptingSkillMedia
Guides your agent through finding and fixing cross-site scripting (XSS) flaws in web code.
Ready to connect★ 122
- View details
xxe-xml-external-entitySkillFiles & storage
Guides your agent through finding and fixing XML external entity (XXE) vulnerabilities in files and parsers.
Ready to connect★ 122
- View details
accountable-engineeringSkillSecurity
Makes your agent pause and ask you to approve big decisions like architecture, security, or rollout plans.
Ready to connect★ 121
- View details
agents-md-managerSkillFiles & storage
Lets your agent create, update, and check AGENTS.md project context files, including audits across multiple projects.
Ready to connect★ 121
- View details
ai-slop-removerSkillDev tools
Lets your agent find and remove AI-generated code patterns that don't match your codebase's style.
Ready to connect★ 121
- View details
arvancloud-apiSkillFiles & storage
Lets your agent manage ArvanCloud services like DNS records, cloud servers, object storage, CDN, and security settings.
Ready to connect★ 121
- View details
bot-statusSkillDatabases & data
Lets your agent run a health check on the Aivena bot and report the status of all its subsystems.
Ready to connect★ 121
- View details
capability-experimentsSkillAI & models
Lets your agent build interactive reports and experiments that explore what AI models can do.
Ready to connect★ 121
- View details
cmuxSkillWeb & browsing
Lets your agent use the cmux claude skill to split terminal panes, run parallel processes, and preview web pages.
Ready to connect★ 121
- View details
codebase-docsSkillDocs & knowledge
Lets your agent generate and update markdown documentation for your codebase in a docs folder.
Ready to connect★ 121
- View details
codemapSkillDocs & knowledge
Lets your agent map a codebase into seven structured architecture documents.
Ready to connect★ 121
- View details
comfyui-node-updateSkillFiles & storage
Lets your agent document ComfyUI nodes with a ComfyUI Claude skill that writes per-node JSON descriptions.
Ready to connect★ 121
- View details
commit-atomicSkillDev tools
Lets your agent split staged changes into separate, clearly labeled git commits.
Ready to connect★ 121
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.