Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 80 149 files from 1 774 authors, of which 62 489 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Optimizing test suite execution speed with parallelization, test splitting, caching, selective test execution, and test impact analysis.
Comprehensive TestCafe end-to-end testing skill for writing reliable browser automation tests in JavaScript and TypeScript without WebDriver dependencies, featuring smart assertions, automatic waiting, and parallel execution.
Docker-based integration testing with Testcontainers for databases, message queues, cloud services, and custom containers with lifecycle management.
Teaches the agent to speed up Node integration tests with Testcontainers reuse — withReuse(true), TESTCONTAINERS_REUSE_ENABLE, the .testcontainers.properties opt-in, stable hashing for Postgres/MySQL/Kafka, and Ryuk/CI caveats.
Safe testing-in-production strategies including feature flags, shadow traffic, canary releases, dark launches, and observability-driven development.
Advanced Java testing with TestNG covering data providers, parallel execution, test groups, XML suite configuration, listeners, soft assertions, and dependency management.
Organize testing in TestRail, suite and section architecture, writing maintainable cases, test runs and plans, milestone reporting, and TestRail API automation to push automated results into one quality view.
End-to-end test automation using testRigor's plain English syntax for writing maintainable tests without coding, covering cross-browser testing, mobile testing, API validation, and integrations with CI/CD pipelines.
Find timezone-related bugs in date handling, scheduling, and display logic by testing across multiple timezones and edge cases like DST transitions.
End-to-end type-safe API testing with tRPC covering router testing, middleware testing, subscription testing, and client-server integration testing patterns
Testing patterns for Turborepo and pnpm monorepos covering workspace dependency testing, affected package detection, parallel test execution, and shared test utilities
Generate high-signal unit tests for existing code, behavior-first case selection, boundary and error paths, mocking discipline, mutation-tested quality, and framework-idiomatic output for Vitest, Jest, and pytest.
Identify and log user experience friction points including excessive clicks, confusing navigation, slow interactions, and workflow bottlenecks through automated heuristic analysis
Testing patterns for Vercel Edge Functions, middleware, and serverless functions covering local testing, edge runtime simulation, and deployment verification.
Enforces rigorous verification evidence before any claims of task completion, preventing false positives, untested deployments, and premature celebration with a structured gate function.
Browser automation for AI agents. Navigate pages, fill forms, click elements, take screenshots, and manage tabs — all through simple CLI commands. 2.6k+ GitHub stars.
Natural language test automation methodology where tests are written as plain English instructions, leveraging AI agents to interpret intent, generate executable tests, and maintain test suites without traditional code-based selectors or assertions.
Visual regression testing skill using Playwright, covering screenshot comparison, visual diff thresholds, responsive testing, baseline management, and CI integration.
Teaches the agent to migrate a Jest suite to Vitest — vi.mock and the globals shim, vitest.config workspaces/projects, coverage, browser mode, and Vitest v4 breaking changes.
Write fast unit and integration tests with Vitest — vitest.config.ts setup, vi.fn and vi.mock module mocking, fake timers, snapshots, V8 coverage with thresholds, workspaces for monorepos, and in-source testing.
Modern JavaScript and TypeScript testing with Vitest, covering unit testing, integration testing, mocking, snapshots, browser mode, and Vite integration.
Testing voice-activated applications including speech recognition accuracy, intent detection, dialog flow testing, and multi-language support.
Vue.js component testing using Vue Test Utils with mount/shallow mount, event simulation, Vuex/Pinia store testing, and composition API testing.
Test Vue 3 components with Vue Test Utils and Vitest — mount vs shallowMount, finding and triggering DOM, asserting props and emitted events, awaiting async updates, and mocking Pinia stores and Vue Router.
Testing WebAssembly modules including compilation verification, memory management, interop testing, and performance benchmarking of WASM components.
Automated WCAG 2.2 AA/AAA compliance testing with axe-core, Pa11y, and manual testing patterns for keyboard navigation, screen readers, and color contrast.
Testing and monitoring Core Web Vitals (LCP, FID, CLS, INP, TTFB) to ensure web performance meets Google search ranking thresholds.
Anthropic's official web application testing skill using native Python Playwright scripts with helper utilities for server lifecycle management, browser automation, and comprehensive E2E testing workflows.
Build WebdriverIO E2E suites — wdio.conf.ts setup, $ and $$ selectors, auto-wait and waitUntil, Mocha framework structure, page objects, parallel capabilities, and services for visual testing and Appium mobile.
Comprehensive WebDriverIO (WDIO) test automation skill for generating reliable end-to-end browser tests in JavaScript and TypeScript with Page Object Model, custom commands, and advanced synchronization strategies.
Testing webhook implementations including delivery verification, retry logic, signature validation, idempotency, and failure handling patterns.
Test WebSocket connections for reliability including reconnection logic, message ordering, heartbeat mechanisms, and connection state management under adverse conditions
WebSocket testing including connection lifecycle, reconnection logic, message ordering, backpressure handling, and binary frame testing.
API simulation and service virtualization with WireMock for HTTP stubbing, request matching, stateful behavior, and fault injection testing.
iOS UI testing with XCUITest framework covering element queries, gesture simulation, accessibility testing, and Xcode test plan configuration.
Teach agents to manage Jira test cases and executions with Xray and Zephyr, including issue modeling, JQL, and CI result publishing through REST APIs.
Cross-site scripting vulnerability testing covering reflected, stored, and DOM-based XSS with sanitization validation and CSP bypass detection.
Comprehensive xUnit.net testing skill for writing reliable unit, integration, and acceptance tests in C# with [Fact], [Theory], fixtures, dependency injection, and parallel execution strategies.
Writing and testing YARA rules for malware detection, threat hunting, and file classification with rule validation and false-positive rate testing.
Automated web application security scanning using OWASP ZAP for finding XSS, SQL injection, CSRF, and other OWASP Top 10 vulnerabilities.
Comprehensive testing patterns for Zod schemas covering validation testing, transform testing, error message verification, and integration with API endpoints and forms
Expert guidance for working with Dagster and the dg CLI. ALWAYS use before doing any task that requires knowledge specific to Dagster, or that references assets, materialization, components, data tools or data pipelines. Common tasks may include creating a new project, adding new definitions, understanding the current project structure, answering general questions about the codebase (finding asset, schedule, sensor, component or job definitions), debugging issues, or providing deep information about a specific Dagster concept.
Opinionated production Python standards with automatic version detection (3.10-3.13). Use when writing, reviewing, or refactoring Python in repos that want modern type syntax, explicit condition checks where practical, pathlib operations, interface guidance, and pragmatic production patterns.
Use when users want XiaoBei skill / xiaobei-skill / 小北在读研 style academic image-to-VBA reconstruction: convert academic figures, scientific diagrams, slides, screenshots, or other images into VBA, Office drawing code, PowerPoint/Excel/Word shapes, editable shape reconstruction, 1:1 recreation, pixel-like approximation, or hybrid editable Office shape reconstruction.
Use for 小北在读研 / XiaoBei academic paper-to-PPT workflows: generate thesis-defense or project-report decks from uploaded papers, literature, reports, technical documents, and optional PPTX visual templates. Produces a source-grounded outline, an imagegen visual scheme, one complete bitmap per slide, an imagegen provenance manifest, and an image-only PPTX. Do not use when the user needs editable slide text or native editable charts.
Guidance for creating, managing and executing workflow automations that chain multiple tools and agents together. Use when the user asks about building, listing, running or composing workflows and automated task pipelines.
Authors Agent Skills v1.0 packages (SKILL.md plus references/scripts), runs package_skill to produce a standards-compliant zip, and uses install_skill to add skills from HTTPS, registry, workspace, or an uploaded archive. Use when the user wants to turn documentation, workflows, or code into a portable skill, export a skill zip, or install a skill from a link or file without leaving the chat.
> Generate printable attendance / 签到表 spreadsheets from name lists. Use when the user asks for 签到表, attendance sheet, meeting sign-in table, or similar printable roster tables (not full payroll attendance scoring unless asked).
> Review procurement contracts and purchase packages against uploaded compliance rules (招标/采购制度). Use for 采购审核, contract compliance checklists, or procurement statistics rollups.
> Audit travel / 差旅报销 claims against uploaded policy handbooks and rate tables (lodging caps, transport, per diem). Use for 差旅费审核, travel expense review, or lodging over-limit checks.
Guidance for analyzing structured data, generating statistics and producing data-driven insights. Use when the user asks to analyze data, compute statistics, find patterns, or generate analytical reports.
Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.
产品经理竞品分析报告生成器。当用户提到竞品分析、竞品调研、竞品对比、竞争对手分析、市场竞争分析、行业竞品研究时触发。也适用于用户要求对比多个产品/平台/公司的功能、商业模式、市场定位等场景。即使用户只是说'帮我分析一下XX和YY'或'XX有哪些竞争对手'，只要涉及产品/公司间的对比分析，都应该使用这个 skill。支持任意行业，支持快速分析和深度分析两种模式。
协助产品经理生成专业的产品需求文档(PRD)，通过交互式问答收集信息，进行竞品研究，迭代优化各模块内容，最终输出结构化的PRD文档。
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Best practices for Remotion - Video creation in React
> Extracts durable insights from temp/ files to SoT during EPIC Phase E. Triggers at EPIC completion or explicit `/ghm-harvest` invocation. Outputs new SoT entries and archive manifest.
> Install the PRD-Driven Context Engineering methodology into a fresh OR existing repository — the subscription-native alternative to forking the whole repo. Runs an interactive wizard that seeds the framework (.claude/ hooks, skills, agents, rules, scripts) without clobbering product content. Triggers on "install the methodology", "adopt this into my repo", "self-install", "set up PRD lifecycle here", "onboard existing project". Outputs an installed framework + a verification report.
> Synchronizes README.md Command Center with current project state. Triggers on gate changes, EPIC status changes, or explicit `/ghm-status-sync` invocation. Outputs updated README.md dashboard with current lifecycle stage, blockers, and metrics.
> Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py). Returns a graduated PASS / WARN / BLOCK verdict with top blockers and their causal chain. Triggers before advancing from v0.X to v0.Y or explicit `/ghm-gate-check`.
Claude Skills — questions
Answers built from the skills we actually parsed.