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 579 of 1,823
- View details
risk-based-testingSkillDev tools
Helps your agent plan testing by ranking features by risk and focusing effort on the highest-risk areas.
Ready to connect★ 480
- View details
security-testingSkillDatabases & data
Lets your agent scan apps for security flaws like XSS, SQL injection, CSRF, and authentication problems.
Ready to connect★ 480
- View details
security-visual-testingSkillSecurity
Lets your agent test web pages for layout changes, exposed personal data, and accessibility issues.
Ready to connect★ 480
- View details
security-watchSkillSecurity
Scans your code for security issues like hardcoded secrets, eval(), and innerHTML as you write.
Ready to connect★ 480
- View details
sfdipot-product-factorsSkillDev tools
Lets your agent analyze requirements or user stories and generate prioritized test ideas across product quality factors.
Ready to connect★ 480
- View details
sherlock-reviewSkillDev tools
Lets your agent investigate code changes with evidence to verify what actually happened versus what was claimed.
Ready to connect★ 480
- View details
shift-left-testingSkillDev tools
Lets your agent plan and run testing earlier in development so defects are caught while cheap to fix.
Ready to connect★ 480
- View details
shift-right-testingSkillCloud & infra
Lets your agent test software in production with feature flags, canary releases, and chaos engineering.
Ready to connect★ 480
- View details
simpleSkillDocs & knowledge
Lets your agent turn short user notes into clear action items.
Ready to connect★ 480
- View details
six-thinking-hatsSkillDev tools
Lets your agent analyze software testing problems using the Six Thinking Hats method from six perspectives.
Ready to connect★ 480
- View details
skill-statsSkillDev tools
Lets your agent review how often skills are used, spot underused ones, and get recommendations.
Ready to connect★ 480
- View details
Swarm OrchestrationSkillProductivity
Lets your agent split big tasks across multiple coordinated agents that run in parallel.
Ready to connect★ 480
- View details
tdd-london-chicagoSkillDev tools
Guides your agent to practice test-driven development using London (mock-based) or Chicago (state-based) styles.
Ready to connect★ 480
- View details
test-automation-strategySkillMedia
Guides your agent in designing test automation plans with test pyramids, patterns, and CI/CD integration.
Ready to connect★ 480
- View details
test-data-managementSkillDev tools
Lets your agent generate and manage realistic test data while handling PII and GDPR/CCPA compliance.
Ready to connect★ 480
- View details
test-design-techniquesSkillMedia
Helps your agent design thorough test cases using techniques like boundary analysis, decision tables, and state testing.
Ready to connect★ 480
- View details
test-environment-managementSkillCloud & infra
Lets your agent set up and manage test environments using infrastructure code, Docker, Kubernetes, and cost optimization.
Ready to connect★ 480
- View details
test-failure-investigatorSkillDev tools
Lets your agent investigate a failing test and figure out whether it's flaky, an environment issue, or a real bug.
Ready to connect★ 480
- View details
test-idea-rewritingSkillMonitoring & ops
Lets your agent rewrite vague 'Verify X' test descriptions into clear, action-verb test steps.
Ready to connect★ 480
- View details
test-metrics-dashboardSkillMonitoring & ops
Lets your agent query test history and build dashboards showing flakiness rates, MTTR, and quality trends.
Ready to connect★ 480
- View details
test-reporting-analyticsSkillDatabases & data
Lets your agent build test quality reports, dashboards, trend analysis, and executive summaries from testing metrics.
Ready to connect★ 480
- View details
testability-scoringSkillWeb & browsing
Lets your agent score how testable a web application is across ten principles like observability and controllability.
Ready to connect★ 480
- View details
text-analyzerSkillFiles & storage
Lets your agent analyze text files and report word counts, frequent words, and readability statistics.
Ready to connect★ 480
- View details
validation-pipelineSkillDev tools
Lets your agent check requirements, code, or artifacts through multi-stage validation gates with scores and pass/fail reports.
Ready to connect★ 480
- View details
visual-testing-advancedSkillWeb & browsing
Lets your agent compare screenshots to spot visual changes and layout bugs in your web app.
Ready to connect★ 480
- View details
wms-testing-patternsSkillDev tools
Gives your agent testing patterns for warehouse management systems, covering inventory, pick/pack/ship, EDI, and barcode workflows.
Ready to connect★ 480
- View details
xp-practicesSkillFiles & storage
Gives your agent guidance on applying XP practices like pair programming, continuous integration, and sustainable pace.
Ready to connect★ 480
- View details
youtube-fetcherSkillDocs & knowledge
Lets your agent pull a YouTube video's transcript and save it as a Markdown note with captions and video details.
Ready to connect★ 478
- View details
ai-checkSkillDev tools
Lets your agent analyze text to check if it sounds AI-written and spot what gives it away.
Ready to connect★ 468
- View details
llmdocSkillWeb & browsing
Lets your agent explore a codebase and find concepts, contracts, and change impacts via indexed docs instead of crawling files.
Ready to connect★ 478
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.