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 578 of 1,823
- View details
qcsd-refinement-swarmSkillDev tools
Lets your agent run sprint refinement sessions, generate BDD scenarios, and validate requirements using SFDIPOT factors.
Ready to connect★ 480
- View details
qe-a11y-allySkillWeb & browsing
Lets your agent audit web pages for accessibility problems using multiple testing tools and get fix suggestions.
Ready to connect★ 480
- View details
qe-accessibility-testingSkillMedia
Lets your agent check web apps for accessibility problems like missing labels and screen reader issues.
Ready to connect★ 480
- View details
qe-agentic-jujutsuSkillAI & models
Lets your agent manage version control with quantum-resistant security and coordinate changes across multiple agents.
Ready to connect★ 480
- View details
qe-agentic-quality-engineeringSkillAI & models
Lets your agent run quality engineering tasks like testing and review using a set of guided QE agent skills.
Ready to connect★ 480
- View details
qe-api-testing-patternsSkillDev tools
Teaches your agent how to test APIs, including contract, REST, GraphQL, and integration testing patterns.
Ready to connect★ 480
- View details
qe-aqe-v2-v3-migrationSkillDev tools
Lets your agent migrate Agentic QE projects from v2 to v3 without losing data.
Ready to connect★ 480
- View details
qe-brutal-honesty-reviewSkillDev tools
Gives your agent brutally honest technical criticism of code, tests, and decisions.
Ready to connect★ 480
- View details
qe-bug-reporting-excellenceSkillFiles & storage
Helps your agent write clear, complete bug reports that developers can act on quickly.
Ready to connect★ 480
- View details
qe-chaos-resilienceSkillDev tools
Lets your agent inject controlled failures like network partitions and process kills to test how well systems recover.
Ready to connect★ 480
- View details
qe-code-intelligenceSkillSearch
Lets your agent search and map large codebases, tracing call chains and dependencies to explain unfamiliar code.
Ready to connect★ 480
- View details
qe-code-review-qualitySkillDev tools
Lets your agent review code for quality, testability, and maintainability and give structured feedback.
Ready to connect★ 480
- View details
qe-compatibility-testingSkillWeb & browsing
Lets your agent test web apps across browsers, devices, and platforms to catch compatibility issues.
Ready to connect★ 480
- View details
qe-compliance-testingSkillDev tools
Lets your agent check software against regulations like GDPR, HIPAA, and PCI-DSS to prepare for audits.
Ready to connect★ 480
- View details
qe-consultancy-practicesSkillDev tools
Lets your agent apply software quality consultancy practices when advising clients or setting up workflows.
Ready to connect★ 480
- View details
qe-context-driven-testingSkillDev tools
Guides your agent to pick testing approaches that fit your project's context instead of defaulting to universal rules.
Ready to connect★ 480
- View details
qe-contract-testingSkillDev tools
Lets your agent run contract tests that check APIs like REST and GraphQL against agreed schemas.
Ready to connect★ 480
- View details
qe-courtSkillDev tools
Lets your agent get a code change reviewed by multiple independent AI reviewers before approving it.
Ready to connect★ 480
- View details
qe-coverage-analysisSkillDev tools
Lets your agent analyze test coverage reports to find untested lines, branches, and functions worth covering first.
Ready to connect★ 480
- View details
qe-defect-intelligenceSkillMonitoring & ops
Lets your agent predict which code areas are likely to have bugs using complexity metrics and past defect patterns.
Ready to connect★ 480
- View details
qe-iterative-loopSkillDev tools
Lets your agent fix failing tests and raise code coverage by running edit-and-test cycles until checks pass.
Ready to connect★ 480
- View details
qe-learning-optimizationSkillAI & models
Lets your agent improve its testing accuracy over time by learning from past results and tuning its settings.
Ready to connect★ 480
- View details
qe-quality-assessmentSkillCloud & infra
Lets your agent score code quality using complexity, lint, code smell, and test health checks.
Ready to connect★ 480
- View details
qe-requirements-validationSkillDev tools
Lets your agent check acceptance criteria for testability, trace requirements to tests, and generate BDD scenarios.
Ready to connect★ 480
- View details
qe-test-executionSkillWeb & browsing
Lets your agent run test suites in parallel with retries and live reports across Jest, Vitest, and Playwright.
Ready to connect★ 480
- View details
qe-test-generationSkillDev tools
Generates durable tests like invariants, contracts, and property-based tests, plus unit, integration, and e2e coverage.
Ready to connect★ 480
- View details
qe-visual-accessibilitySkillDev tools
Lets your agent capture page screenshots, compare them for visual changes, and run accessibility checks.
Ready to connect★ 480
- View details
quality-metricsSkillMonitoring & ops
Lets your agent track software quality metrics like defect rates, test effectiveness, and delivery speed.
Ready to connect★ 480
- View details
ReasoningBank IntelligenceSkillAI & models
Lets your agent learn from past tasks and improve its strategies over time.
Ready to connect★ 480
- View details
regression-testingSkillDev tools
Lets your agent pick which tests to rerun after code changes and manage regression suites for faster feedback.
Ready to connect★ 480
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.