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
55,286 results · page 828 of 1,843
- View details
agent-loop-testingSkillAI & models
Use this skill when you need evidence-bounded loop state, plan/action/observation cycles, stop conditions, budgets, repetition, and trace evidence; triggers include Agent 循环 and Agent loop.
Ready to connect★ 221
- View details
agent-memory-testingSkillDocs & knowledge
Use this skill when you need evidence-bounded memory write/read/update/delete, retention, contamination, isolation, provenance, and forgetting behavior; triggers include Agent 记忆 and Agent memory.
Ready to connect★ 221
- View details
agent-permission-testingSkillAI & models
Use this skill when you need evidence-bounded Agent identity, tool/resource scope, approval, denial, escalation, and side-effect boundaries; triggers include Agent 权限 and Agent permission.
Ready to connect★ 221
- View details
agent-tool-testingSkillAI & models
Use this skill when you need to test AI agent tool-call contracts, authorization, failures, and side-effect boundaries; triggers include agent tool testing.
Ready to connect★ 221
- View details
ai-agent-testingSkillAI & models
Use this skill when you need to test AI agent goals, state, planning, recovery, and safety boundaries; triggers include ai agent testing.
Ready to connect★ 221
- View details
ai-assisted-testingSkillDev tools
Use this skill when you need AI-assisted testing workflows such as test data generation, root-cause analysis, and prioritization; triggers include AI-assisted testing and AI for QA.
Ready to connect★ 221
- View details
ai-feature-testingSkillDev tools
Use this skill when you need to test an AI-enabled product feature for behavior, safety, and user-impact boundaries; triggers include AI feature testing.
Ready to connect★ 221
- View details
ai-generated-test-reviewSkillDev tools
Use this skill when reviewing AI-generated unit, functional, API, or end-to-end tests for false confidence, weak assertions, missing risks, or unsafe test behavior; triggers include AI-generated test review and functional test review.
Ready to connect★ 221
- View details
ai-safety-testingSkillDev tools
Use this skill when you need evidence-bounded safety policy, abuse categories, refusal/redirect behavior, privacy, escalation, and Human risk decisions; triggers include AI 安全 and AI safety.
Ready to connect★ 221
- View details
api-design-quality-reviewSkillMedia
Use this skill when an API, OpenAPI, or consumer contract needs a quality review before implementation or versioning; triggers include API design review, contract readiness review, and consumer compatibility audit.
Ready to connect★ 221
- View details
api-error-contract-testingSkillDev tools
Use this skill when you need to review API error shape, status, code, and disclosure behavior against sourced contracts; triggers include API 错误契约测试 and API error contract testing.
Ready to connect★ 221
- View details
api-idempotency-testingSkillDev tools
Use this skill when you need to assess API retry and duplicate-request behavior against sourced side-effect evidence; triggers include API 幂等性测试 and API idempotency testing.
Ready to connect★ 221
- View details
api-negative-testingSkillMedia
Use this skill when you need to design evidence-bounded API failure and rejection scenarios; triggers include API 负向测试 and API negative testing.
Ready to connect★ 221
- View details
api-pagination-testingSkillMedia
Use this skill when you need to design API pagination scenarios from ordered data and cursor or offset evidence; triggers include API 分页测试 and API pagination testing.
Ready to connect★ 221
- View details
api-rate-limit-testingSkillMedia
Use this skill when you need to design evidence-bounded API quota, burst, and recovery scenarios; triggers include API 限流测试 and API rate limit testing.
Ready to connect★ 221
- View details
api-schema-validationSkillDev tools
Use this skill when you need to compare API schemas with sourced request and response evidence; triggers include API Schema 校验 and API schema validation.
Ready to connect★ 221
- View details
api-test-brunoSkillDev tools
Use this skill when you need to parse multi-format API definitions and generate Bruno collections for executable regression; triggers include Bruno collections and Bruno API testing.
Ready to connect★ 221
- View details
api-test-postmanSkillMedia
Use this skill when you need to design Postman collections, environments, scripts, and Newman-ready API regression plans; triggers include Postman API testing, API testing, and api-test-postman.
Ready to connect★ 221
- View details
api-test-pytestSkillDev tools
Use this skill when you need to parse multi-format API definitions and generate Pytest API automation; triggers include Pytest API tests and API automation with Pytest.
Ready to connect★ 221
- View details
api-test-restassureSkillDev tools
Use this skill when you need to parse multi-format API definitions and generate Rest Assured Java test classes; triggers include Rest Assured, RestAssured, and Java API automation.
Ready to connect★ 221
- View details
api-test-supertestSkillDev tools
Use this skill when you need to parse multi-format API definitions and generate executable Supertest scripts; triggers include Supertest, Node.js API testing, and Supertest automation.
Ready to connect★ 221
- View details
api-version-compatibility-testingSkillDev tools
Use this skill when you need to assess API version compatibility from old-client, new-server, and deprecation evidence; triggers include API 版本兼容性测试 and API version compatibility testing.
Ready to connect★ 221
- View details
authentication-testingSkillSecurity
Use this skill when you need evidence-bounded authentication-testing analysis and validation preparation; triggers include 身份认证测试 and authentication-testing.
Ready to connect★ 221
- View details
authorization-testingSkillDev tools
Use this skill when you need evidence-bounded authorization-testing analysis and validation preparation; triggers include 授权测试 and authorization-testing.
Ready to connect★ 221
- View details
automation-roi-analysisSkillDev tools
Use this skill when you need evidence-bounded automation candidates, build/run/maintenance costs, benefit assumptions, time horizon, and sensitivity; triggers include 自动化投资回报 and automation ROI.
Ready to connect★ 221
- View details
automation-testingSkillMedia
Use this skill when you need to design automation testing approaches using patterns like POM, data-driven testing, or BDD; triggers include automation testing and test automation strategy.
Ready to connect★ 221
- View details
boundary-value-testingSkillMedia
Use this skill when you need to select boundary and near-boundary candidates from sourced value, length, time, and resource constraints; triggers include 边界值分析 and boundary value test design.
Ready to connect★ 221
- View details
bug-reportingSkillDev tools
Use this skill when you need to write clear, reproducible bug reports with steps, environment details, and evidence; triggers include bug reporting and defect reporting.
Ready to connect★ 221
- View details
business-rule-extractionSkillMedia
Use this skill when requirements, policies, contracts, or workflows need traceable business rules extracted before design or testing; triggers include business rule extraction, policy rule inventory, and atomic rule analysis.
Ready to connect★ 221
- View details
capacity-planning-analysisSkillDev tools
Use this skill when you need to assess capacity demand, headroom, constraints, and planning assumptions; triggers include capacity planning analysis.
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.
54,855 of the 55,286 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.