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
55,436 results · page 831 of 1,848
- View details
ai-feature-testingSkillDev tools
Lets your agent test an AI-powered feature for correct behavior, safety, and limits on user impact.
Ready to connect★ 221
- View details
ai-generated-test-reviewSkillDev tools
Lets your agent review AI-generated tests for weak assertions, missing risks, and unsafe behavior.
Ready to connect★ 221
- View details
ai-safety-testingSkillDev tools
Lets your agent analyze and improve AI safety plans, covering abuse cases, refusals, privacy, and escalation with evidence-based findings.
Ready to connect★ 221
- View details
api-design-quality-reviewSkillMedia
Lets your agent review an API design or contract for gaps in errors, auth, and compatibility before building it.
Ready to connect★ 221
- View details
api-error-contract-testingSkillDev tools
Lets your agent review API error responses for consistency with defined error contracts and record traceable findings.
Ready to connect★ 221
- View details
api-idempotency-testingSkillDev tools
Lets your agent design traceable test candidates for API retry and duplicate-request behavior from your existing evidence.
Ready to connect★ 221
- View details
api-negative-testingSkillMedia
Lets your agent design API failure and rejection test scenarios from contracts and error evidence, without running the tests.
Ready to connect★ 221
- View details
api-pagination-testingSkillMedia
Helps your agent design test scenarios for API pagination, like checking pages don't skip or repeat items.
Ready to connect★ 221
- View details
api-rate-limit-testingSkillMedia
Helps your agent design API rate-limit test scenarios from quota, burst, and recovery evidence without running tests.
Ready to connect★ 221
- View details
api-schema-validationSkillDev tools
Lets your agent compare API schemas against sourced request, response, and version evidence to produce traceable validation findings.
Ready to connect★ 221
- View details
api-test-brunoSkillDev tools
Lets your agent parse API definitions and generate Bruno test collections for regression testing.
Ready to connect★ 221
- View details
api-test-postmanSkillMedia
Lets your agent design Postman collections, environments, test scripts, and Newman-ready API regression plans.
Ready to connect★ 221
- View details
api-test-pytestSkillDev tools
Lets your agent turn API definitions into Pytest test code for API automation.
Ready to connect★ 221
- View details
api-test-restassureSkillDev tools
Lets your agent turn API definitions into Rest Assured Java test classes.
Ready to connect★ 221
- View details
api-test-supertestSkillDev tools
Lets your agent turn API definitions into runnable Supertest test scripts for Node.js.
Ready to connect★ 221
- View details
api-version-compatibility-testingSkillDev tools
Lets your agent analyze API version compatibility risks from old clients, server changes, and deprecation evidence.
Ready to connect★ 221
- View details
ascii-videoSkillMedia
Lets your agent convert video or audio files into colored ASCII-art MP4 or GIF animations.
Ready to connect★ 221
- View details
audiocraftSkillMedia
PyTorch library for audio generation including text-to-music (MusicGen)
Ready to connect★ 221
- View details
authentication-testingSkillSecurity
Lets your agent analyze authentication flows and produce evidence-based security test plans without touching real systems.
Ready to connect★ 221
- View details
authorization-testingSkillDev tools
Lets your agent analyze permission rules and prepare authorization test plans without touching real systems.
Ready to connect★ 221
- View details
automation-roi-analysisSkillDev tools
Lets your agent analyze automation ideas for costs, benefits, payback time, and evidence gaps before you invest.
Ready to connect★ 221
- View details
automation-testingSkillMedia
Lets your agent design automation testing plans using patterns like POM, data-driven testing, and BDD.
Ready to connect★ 221
- View details
boundary-value-testingSkillMedia
Lets your agent pick boundary and near-boundary test values from constraints like limits, lengths, and time rules.
Ready to connect★ 221
- View details
bug-reportingSkillDev tools
Lets your agent write clear, reproducible bug reports with steps, environment details, and evidence.
Ready to connect★ 221
- View details
business-rule-extractionSkillMedia
Lets your agent pull traceable, atomic business rules out of requirements, policies, and contracts into numbered entries with sources.
Ready to connect★ 221
- View details
capacity-planning-analysisSkillDev tools
Lets your agent analyze capacity demand, headroom, constraints, and planning assumptions for your systems.
Ready to connect★ 221
- View details
change-impact-analysisSkillDev tools
Lets your agent analyze how a code, config, or requirement change affects the scope of quality testing.
Ready to connect★ 221
- View details
chaos-testingSkillDev tools
Helps your agent draft chaos-testing plans, modeling fault-injection scenarios, blast radius, and safety guardrails from evidence.
Ready to connect★ 221
- View details
ci-fix-and-verifySkillDev tools
Lets your agent fix failing CI checks on a pull request by repeatedly pushing fixes until all checks pass.
Ready to connect★ 221
- View details
ci-test-optimizationSkillDev tools
Lets your agent analyze a CI test pipeline and produce prioritized improvement steps for flaky tests, slow feedback, caching, and sharding.
Ready to connect★ 221
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.
55,005 of the 55,436 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.