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
55,435 results · page 835 of 1,848
- View details
stable-diffusionSkillMedia
State-of-the-art text-to-image generation with Stable Diffusion models
Ready to connect★ 221
- View details
state-transition-testingSkillMedia
Lets your agent derive state transition test candidates from states, events, guards, and actions.
Ready to connect★ 221
- View details
task-note-management-mcpSkillDocs & knowledge
Lets your agent manage SiYuan tasks, project boards, habit check-ins, and focus-time stats.
Ready to connect★ 221
- View details
technical-design-quality-reviewSkillDocs & knowledge
Lets your agent review a technical design or architecture doc and report gaps, risks, and missing evidence before coding starts.
Ready to connect★ 221
- View details
test-case-reviewerSkillDev tools
Lets your agent review test cases for completeness, clarity, and missing scenarios.
Ready to connect★ 221
- View details
test-case-reviewer-plusSkillDev tools
Lets your agent produce structured review findings for test cases from your requirements and strategy docs.
Ready to connect★ 221
- View details
test-case-writingSkillMedia
Guides your agent to write thorough test cases covering normal, exception, and boundary scenarios.
Ready to connect★ 221
- View details
test-code-reviewSkillDev tools
Lets your agent review test code for assertion, isolation, determinism, fixture, and maintainability issues.
Ready to connect★ 221
- View details
test-data-generationSkillMedia
Lets your agent design safe, representative test data based on constraints you provide.
Ready to connect★ 221
- View details
test-data-requirement-analysisSkillMedia
Lets your agent analyze what test data a scenario needs and flag gaps before any test data is created.
Ready to connect★ 221
- View details
test-effectiveness-analysisSkillDev tools
Lets your agent analyze how well tests catch real defects, including missed bugs and false alarms.
Ready to connect★ 221
- View details
test-maintenance-cost-analysisSkillDev tools
Lets your agent analyze test suites for change frequency, repair effort, flakiness cost, ownership, and maintainability.
Ready to connect★ 221
- View details
test-report-reviewSkillDev tools
Lets your agent review test reports for evidence consistency before human approval.
Ready to connect★ 221
- View details
test-runtime-optimizationSkillDev tools
Lets your agent speed up slow test suites using profiling, parallelism, and baseline evidence.
Ready to connect★ 221
- View details
test-scope-analysisSkillDev tools
Lets your agent define test scope boundaries, deciding what testing to include, exclude, deepen, or expand before execution.
Ready to connect★ 221
- View details
test-strategySkillDev tools
Lets your agent draft a test strategy covering scope, methods, resources, risks, and quality gates.
Ready to connect★ 221
- View details
test-strategy-plusSkillDev tools
Lets your agent produce a structured test strategy from your requirement, analysis, tech, and plan documents.
Ready to connect★ 221
- View details
test-strategy-reviewSkillDev tools
Lets your agent review a proposed test strategy with evidence before you approve it.
Ready to connect★ 221
- View details
test-suite-health-analysisSkillDev tools
Lets your agent assess test-suite health from duration, flakiness, duplication, quarantine, and maintenance evidence.
Ready to connect★ 221
- View details
testability-analysisSkillMedia
Lets your agent assess whether a requirement or design can be tested reliably and efficiently.
Ready to connect★ 221
- View details
testcase-writer-plusSkillDev tools
Lets your agent write test cases from your requirements and analysis documents.
Ready to connect★ 221
- View details
testing-bottleneck-analysisSkillDev tools
Helps your agent identify and explain constraints and delays in a testing workflow.
Ready to connect★ 221
- View details
threat-modelingSkillSecurity
Lets your agent run threat-modeling analysis and prepare for security validation.
Ready to connect★ 221
- View details
timeout-testingSkillDev tools
Lets your agent run evidence-bounded timeout-testing analysis and prepare validation reports.
Ready to connect★ 221
- View details
trl-fine-tuningSkillAI & models
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction
Ready to connect★ 221
- View details
tufte-data-vizSkillDev tools
Helps your agent create and style clean, minimal charts, graphs, and dashboards in popular charting libraries.
Ready to connect★ 221
- View details
ui-test-cypressSkillSearch
Helps your agent plan Cypress end-to-end and component tests with commands, fixtures, network stubbing, and CI reporting.
Ready to connect★ 221
- View details
ui-test-playwrightSkillWeb & browsing
Helps your agent write Playwright test suites with fixtures, screenshots, API and UI coverage, and CI reporting.
Ready to connect★ 221
- View details
ui-test-puppeteerSkillWeb & browsing
Lets your agent write Puppeteer scripts to test web pages, take screenshots, generate PDFs, and intercept network traffic.
Ready to connect★ 221
- View details
ui-test-selector-reviewSkillDev tools
Lets your agent review UI test selectors for stability, semantics, and maintainability using source code evidence.
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.
55,004 of the 55,435 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.