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 576 of 1,823
- View details
combinatorial-synthesisSkillDev tools
Lets your agent generate new ideas by synthesizing combinations of its creative outputs.
Ready to connect★ 481
- View details
comparative-feasibility-rankingSkillDev tools
Lets your agent compare several candidate options and rank them by feasibility across multiple criteria.
Ready to connect★ 481
- View details
comparative-formulationSkillDev tools
Lets your agent build systematic comparison questions for research analysis.
Ready to connect★ 481
- View details
comparison-designSkillMedia
Lets your agent design fair comparison experiments against baselines and competing methods.
Ready to connect★ 481
- View details
comparison-executorSkillDev tools
Lets your agent compare two candidates side by side and output a judgment of which is better.
Ready to connect★ 481
- View details
competing-hypothesis-constructionSkillDev tools
Guides your agent to build several competing explanations for the same observation instead of settling on one.
Ready to connect★ 481
- View details
competing-hypothesis-generationSkillDev tools
Lets your agent generate several distinct possible explanations for the same observed phenomenon.
Ready to connect★ 481
- View details
competing-hypothesis-matrixSkillDev tools
Lets your agent generate and compare competing hypotheses when analyzing a problem.
Ready to connect★ 481
- View details
repo-dependency-graphSkillDocs & knowledge
Lets your agent map a repo's skill dependencies and render them as an interactive offline HTML graph.
Ready to connect★ 481
- View details
a11y-allySkillWeb & browsing
Lets your agent run website accessibility audits and get suggested fixes for WCAG issues.
Ready to connect★ 480
- View details
agentic-quality-engineeringSkillAI & models
Guides your agent in orchestrating quality-engineering agents and applying PACTS principles to testing work.
Ready to connect★ 480
- View details
api-callerSkillDev tools
Lets your agent send GET, POST, PUT, and DELETE requests to any REST API with custom headers and JSON bodies.
Ready to connect★ 480
- View details
api-testing-patternsSkillDev tools
Gives your agent patterns for testing APIs, including contract, REST, GraphQL, and integration testing.
Ready to connect★ 480
- View details
aqe-plan-qualitySkillProductivity
Lets your agent create risk-based quality and test plans for feature changes.
Ready to connect★ 480
- View details
aqe-plan-workSkillDev tools
Lets your agent turn requirements into phased, dependency-aware work plans with critical paths and acceptance gates.
Ready to connect★ 480
- View details
aqe-researchSkillAI & models
Lets your agent run evidence-first research on repositories, comparing changes and tracing dependencies.
Ready to connect★ 480
- View details
aqe-review-qualitySkillSecurity
Lets your agent review code changes and issue an evidence-backed verdict on quality, regression risk, and release readiness.
Ready to connect★ 480
- View details
aqe-rufloSkillDocs & knowledge
Adds Ruflo development-time orchestration—swarms, persistent memory, and routing—to agentic QE workflows.
Ready to connect★ 480
- View details
aqe-test-changeSkillMedia
Lets your agent design, run, and verify tests for changes in the Agentic QE codebase.
Ready to connect★ 480
- View details
bug-reporting-excellenceSkillFiles & storage
Helps your agent write clear, high-quality bug reports that developers can act on quickly.
Ready to connect★ 480
- View details
chaos-engineering-resilienceSkillDev tools
Guides your agent in testing system resilience by injecting controlled failures and validating recovery.
Ready to connect★ 480
- View details
cicd-pipeline-qe-orchestratorSkillDev tools
Lets your agent plan test strategies and quality gates across CI/CD pipeline phases.
Ready to connect★ 480
- View details
code-review-qualitySkillDev tools
Lets your agent review code for quality, testability, and maintainability with structured feedback.
Ready to connect★ 480
- View details
compatibility-testingSkillWeb & browsing
Lets your agent test how a website works across different browsers, devices, and platforms.
Ready to connect★ 480
- View details
compliance-testingSkillDev tools
Lets your agent check your project for compliance with regulations like GDPR, HIPAA, and PCI-DSS.
Ready to connect★ 480
- View details
consultancy-practicesSkillDev tools
Lets your agent apply software quality consultancy practices when advising clients or setting up workflows.
Ready to connect★ 480
- View details
context-driven-testingSkillDev tools
Lets your agent choose testing approaches based on your project's context instead of fixed best practices.
Ready to connect★ 480
- View details
coverage-drop-investigatorSkillFiles & storage
Lets your agent find which code changes caused a drop in test coverage and suggest tests to add.
Ready to connect★ 480
- View details
coverage-guardSkillDev tools
Lets your agent watch code coverage and warn you when changes drop it below a set threshold.
Ready to connect★ 480
- View details
create-custom-graderSkillProductivity
Lets your agent turn an existing rubric, benchmark, or verifier into a custom evaluation for grading tasks.
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.