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. 86 961 files from 2 125 authors, of which 68 678 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.
Read and control SwitchBot devices: Bots, Locks, curtains, plugs, lights, AC, IR remotes, scenes. Trigger phrases: switchbot, switchbot lock, switchbot bot, switchbot curtain.
Read and write Tally: list forms, fetch a form, create and update forms, read submissions. Trigger phrases: tally, forms.
Fast, clean web research: search with an AI answer and cited sources. Trigger phrases: research this, web search, look up, tavily, find sources.
Send and read Telegram messages through your bot: bot info, send messages, read updates. Trigger phrases: telegram, telegram bot, send a telegram message.
Control Tesla vehicles through the official Tesla Fleet API: lock/unlock, remote start, charge control, preconditioning, honk, trunk. Trigger phrases: tesla car, tesla vehicle, lock my tesla, precondition tesla, tesla charge.
Monitor and control Tesla Powerwall and energy sites through the Tesla Fleet API: live power status, backup reserve, operation mode, storm watch. Trigger phrases: tesla powerwall, powerwall, tesla energy, backup reserve, storm watch.
Read TikTok via API v2: your profile and video list. Posting is approval-gated and not shipped. Trigger phrases: tiktok, my tiktok, tiktok profile, tiktok videos.
List tasks, create tasks, and complete them in Todoist. Trigger phrases: todoist, my tasks, add a task, todo list.
Read and write TickTick: list projects and tasks, create tasks, complete and delete tasks. Trigger phrases: ticktick, task list, my tasks.
Read and write trigger.dev: list runs, check run status, trigger tasks, cancel runs, list schedules. Trigger phrases: trigger.dev, background jobs.
Read and control Tuya / Smart Life devices: plugs, lights, thermostats, curtains, smart locks. Trigger phrases: tuya, smart life, tuya device, smart life plug.
Manage Transistor.fm podcast hosting, from episode drafts to audio uploads. Trigger phrases: transistor, transistor.fm, podcast hosting, publish episode.
Read and write Twitch via the Helix API: channel profile, follower stats, live stream status, past videos, channel title and game updates, clip creation. Trigger phrases: twitch, stream stats, stream followers, channel update.
Work with Typeform: list forms and responses, create forms, and (with confirmation) manage response webhooks. Trigger phrases: typeform, form responses, typeform webhook, typeform forms, create form.
Quote and dispatch same-day Uber Direct courier deliveries, and check their status. Trigger phrases: uber direct, same-day delivery, dispatch courier, delivery quote.
Read UniFi Protect cameras, pull snapshots, and adjust camera settings (PTZ, lights, chimes). Trigger phrases: unifi protect, unifi camera, protect snapshot, unifi doorbell.
Read and write Upstash: get, set, and delete Redis keys, run command pipelines. Trigger phrases: upstash, redis.
Search Unsplash for free stock photos, browse by photographer or topic, and download images with proper attribution credit. Trigger phrases: unsplash, stock photo, find an image, download unsplash image.
Remove video backgrounds with VEED's direct developer API: standard, fast and green-screen endpoints. Trigger phrases: veed, remove video background, background removal, transparent video.
Manage Vapi voice AI: assistants, phone numbers, calls. Outbound calls are high actuation and need exact-match confirmation; test numbers by default. Trigger phrases: vapi, voice assistant, outbound call, AI phone call.
Inspect Vercel projects and deployments: your account, project list, recent deploys. Trigger phrases: vercel, vercel project, vercel deployment.
Manage Webflow sites: list sites and CMS collections, read and edit CMS items, and publish. Trigger phrases: webflow, webflow cms, publish webflow site.
View Wise profiles and multi-currency balances. Read-only by design. Trigger phrases: wise, wise balance, transferwise.
Read and write X: post and delete tweets, search recent tweets, like tweets, send DMs. Trigger phrases: x, twitter, tweet.
Query Grok chat completions and list available Grok models through the xAI API. Trigger phrases: xai, grok, chat with grok, grok model.
Work with YouTube: read channels, videos, search, playlist items; upload videos and post comments (with confirmation). Trigger phrases: youtube, videos, upload video, youtube comment.
Read and write YNAB budgets: list budgets, accounts, balances, transactions, and categories; record transactions. Trigger phrases: ynab, budget, my budget, spending.
Work with Zep's temporal memory: create users and threads, append messages, read distilled facts and history. Trigger phrases: zep, knowledge graph memory, conversation memory.
>- Adversarially review a diff, patch, or plan for memtier_benchmark using the real review standards of the project's senior maintainers (Yossi Gottlieb / yossigo, Oran Agra / oranagra, Paulo Sousa / paulorsousa). Use when asked to "adversarially review", "review like the maintainers", "find what a reviewer would block on", or before opening/merging a PR. Emits skeptical, evidence- backed findings; assumes a problem is real until it can be refuted.
Review code for quality, security, and best practices. Use when the user asks for code review, wants feedback on their code, mentions reviewing changes, or asks about code quality.
API design patterns and conventions for this project. Covers RESTful URL naming, response format standards, error handling, and authentication requirements. Use when writing or reviewing API endpoints, designing new APIs, or making decisions about request/response formats.
Generate API documentation from code. Use when the user wants to document APIs, create API reference, generate endpoint documentation, or needs help with OpenAPI/Swagger specs.
Analyze financial data, calculate financial ratios, and generate analysis reports. Use when the user asks about revenue, costs, profits, margins, ROI, financial metrics, or needs financial analysis of a company or project.
Analyze financial data, calculate financial ratios, and generate analysis reports. Use when the user asks about revenue, costs, profits, margins, ROI, financial metrics, or needs financial analysis of a company or project.
Generate an interactive tree visualization of your codebase. Use when exploring a new repo or understanding project structure.
Generate API endpoint code and documentation from specifications. Use when the user wants to create new API endpoints, generate route handlers, scaffold REST APIs, or produce OpenAPI/Swagger specs from code.
Generate API endpoint documentation from Express route files. Use when the user asks to generate, update, or review API docs for Express.js routes.
Perform a comprehensive code health check on a directory. Use when the user asks to analyze code quality, find issues, or get a health report.
Generate API documentation from a route manifest. Use when you have a list of discovered routes and need to produce markdown documentation.
Validate API documentation against quality standards. Use when you need to verify generated docs are complete and correct.
Scan Express.js source files to discover all API route definitions.
React 组件设计模式、Hooks 使用指南、性能优化技巧
Guide for optimizing MSBuild build parallelism and multi-project scheduling. USE FOR: builds not utilizing all CPU cores, speeding up multi-project solutions, evaluating graph build mode (/graph), build time not improving with -m flag, understanding project dependency topology. Note: /maxcpucount default is 1 (sequential) — always use -m for parallel builds. Covers /maxcpucount, graph build for better scheduling and isolation, BuildInParallel on MSBuild task, reducing unnecessary ProjectReferences, solution filters (.slnf) for building subsets. DO NOT USE FOR: single-project builds, incremental build issues (use incremental-build), compilation slowness within a project (use build-perf-diagnostics), non-MSBuild build systems.
>- Generates and writes new unit tests for any programming language — scaffolds .NET test projects, pytest suites, Vitest/Jest suites, Go test files, and JUnit suites, and configures coverage tooling (coverlet, pytest-cov, @vitest/coverage-v8) as part of test generation. Use when asked to generate tests, generate pytest tests, generate Vitest tests, write unit tests, add tests, improve coverage, comprehensive tests, or scaffold a new test project or suite for an app, service, library, REST API, blueprint, or package — including project-wide, multi-file test generation across services, repositories, routes, and modules. Supports C#/.NET, Python (pytest, Flask/Django), TypeScript/JavaScript (Vitest, Jest, Mocha), Go, Rust, Java (JUnit). Runs a research, planning, and implementation pipeline so tests compile and pass. existing coverage reports (use coverage-analysis or crap-score); MSTest modernization (use writing-mstest-tests).
Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath. USE FOR: builds failing with 'Cannot create a file when that file already exists', 'The process cannot access the file because it is being used by another process', intermittent build failures that succeed on retry, missing outputs in multi-project builds, multi-targeting builds where project.assets.json conflicts. Diagnoses when multiple projects or TFMs write to the same bin/obj directories due to shared OutputPath, missing AppendTargetFrameworkToOutputPath, or extra global properties like PublishReadyToRun creating redundant evaluations. DO NOT USE FOR: file access errors unrelated to MSBuild (OS-level locking), single-project single-TFM builds, non-MSBuild build systems.
Generate MSBuild binary logs (binlogs) for build diagnostics and analysis. USE FOR: adding /bl:{} to any dotnet build, test, pack, publish, or restore command to capture a full build execution trace, prerequisite for binlog-failure-analysis and build-perf-diagnostics skills, enabling post-build investigation of errors or performance. Requires MSBuild 17.8+ / .NET 8 SDK+ for {} placeholder; PowerShell needs -bl:{{}}. DO NOT USE FOR: non-MSBuild build systems (npm, Maven, CMake), analyzing an existing binlog (use binlog-failure-analysis instead).
Analyzes the variety and depth of assertions across test suites in any language. Use when the user asks to evaluate assertion quality, find shallow testing, identify assertion-free tests (no assertions or only trivial ones like Assert.IsNotNull / expect(x).toBeTruthy() / assert x is not None), flag self-referential or tautological assertions (output equals input on identity/round-trip operations), measure assertion coverage diversity, or audit whether tests verify different facets of correctness. Produces metrics and actionable recommendations. Polyglot: .NET (MSTest/xUnit/NUnit/TUnit), Python (pytest/unittest), TS/JS (Jest/Vitest/Mocha/Jasmine/node:test), Java (JUnit/TestNG), Go, Ruby (RSpec/Minitest), Rust, Swift (XCTest/Swift Testing), Kotlin (JUnit/Kotest), PowerShell (Pester), C++ (GoogleTest/Catch2/doctest). DO NOT USE FOR: writing new tests (use code-testing-agent, or writing-mstest-tests for MSTest), anti-patterns like flakiness or duplication (use test-anti-patterns), fixing assertions.
>- Provides file paths to language-specific extension files for the code-testing pipeline. Call this skill to discover available extension guidance files (e.g., dotnet.md for .NET, cpp.md for C++). Do not use directly — invoked by code-testing agents and skills that need language-specific references.
> Calculates targeted CRAP (Change Risk Anti-Patterns) scores for a named .NET method, class, or single source file. Use when the user explicitly asks to compute CRAP scores or assess risky untested code for a specific target, combining Cobertura coverage data with cyclomatic complexity analysis. coverage" diagnosis, what's blocking coverage, or where to add tests across a project (use coverage-analysis); writing tests; running tests without CRAP context.
> Scan C# source files for hard-to-test static dependencies — DateTime.Now/UtcNow, File.*, Directory.*, Environment.*, HttpClient, Console.*, Process.*, and other untestable statics. Produces a ranked report of static call sites by frequency. identify hard-to-mock code, find DateTime.Now usage, detect static coupling, testability report, static analysis for testability. migrating code (use migrate-static-to-wrapper), general code review, or finding statics that are already behind abstractions.
Guide for MSBuild extensibility: CustomBefore/CustomAfter hooks, wildcard imports with alphabetic ordering, import gating with control properties, NuGet package build extension layout (build/buildTransitive), and the MicrosoftCommonPropsHasBeenImported guard. USE FOR: diagnosing and fixing MSBuild import and hook patterns, reviewing and fixing extension point anti-patterns in Directory.Build files, fixing missing Exists() guards on imports that break fresh clones, fixing NuGet package hooks being silently dropped instead of appended, making build targets extensible for other projects, injecting custom logic into the build pipeline, creating NuGet packages that extend the build, conditionally disabling imports. DO NOT USE FOR: target authoring patterns (use target-authoring), props vs targets placement (use directory-build-organization), general anti-patterns (use msbuild-antipatterns), non-MSBuild build systems.
> Project-wide code coverage and CRAP (Change Risk Anti-Patterns) score analysis for .NET projects. Calculates CRAP scores per method and surfaces risk hotspots — complex code with low coverage that is dangerous to modify. Use to diagnose why coverage is stuck or plateaued, identify what methods block improvement, or get project-wide coverage analysis with risk ranking. blocking coverage, coverage gap, CRAP scores, risk hotspots, where to add tests, coverage analysis, coverage report. writing tests, running tests without coverage, or troubleshooting test execution (use run-tests).
Reference data for .NET test framework detection patterns, assertion APIs, skip annotations, setup/teardown methods, and common test smell indicators across MSTest, xUnit, NUnit, and TUnit. Loaded by test analysis skills (test-anti-patterns) as framework-specific lookup tables.
Guide for diagnosing and improving MSBuild project evaluation performance. USE FOR: builds slow before any compilation starts, high evaluation time in binlog analysis, expensive glob patterns walking large directories (node_modules, .git, bin/obj), deep import chains (>20 levels), preprocessed output >10K lines indicating heavy evaluation, property functions with file I/O ($([System.IO.File]::ReadAllText(...))), multiple evaluations per project. Covers the 5 MSBuild evaluation phases, glob optimization via DefaultItemExcludes, import chain analysis with /pp preprocessing. DO NOT USE FOR: compilation-time slowness (use build-perf-diagnostics), incremental build issues (use incremental-build), non-MSBuild build systems.
> Generate wrapper interfaces and DI registration for hard-to-test static dependencies in C#. Produces IFileSystem, IEnvironmentProvider, IConsole, IProcessRunner wrappers, or guides adoption of TimeProvider and IHttpClientFactory. make static testable, make class testable, create abstraction for File.*, generate DI registration, TimeProvider adoption, IHttpClientFactory setup, testability wrapper, mock-friendly interface, mock time in tests, create the right abstraction to mock, how to mock DateTime, test code using File.ReadAllText, what abstraction for Environment, how to make statics injectable, adopt System.IO.Abstractions, make file calls testable. sites (use migrate-static-to-wrapper), general interface design not about testability.
Reference data for test filter syntax across all platform and framework combinations: VSTest --filter expressions, MTP filters for MSTest/NUnit/xUnit v3/TUnit, and VSTest-to-MTP filter translation. DO NOT USE directly — loaded by run-tests, mtp-hot-reload, and migrate-vstest-to-mtp when they need filter syntax.
> Grades a specified set of test methods individually and produces a concise table mapping each test (fully-qualified name) to a letter grade (A–F), a score band, pseudo-mutation resilience, a one-line note, and a concrete improvement for every grade below A — designed to be posted as a PR comment. Use when the caller wants per-test feedback on a curated list of methods (for example, the new or modified tests in a pull request), not a Go, Ruby (RSpec/Minitest), Rust, Swift (XCTest/Swift Testing), Kotlin (JUnit/Kotest), PowerShell (Pester), C++ (GoogleTest/Catch2/doctest). Input is a list of test methods (or method bodies / file+line spans); full suite audits (use test-quality-auditor agent or test-anti-patterns), writing new tests (use code-testing-generator agent or writing-mstest-tests), fixing failures, or measuring code coverage.
> Migrate MSTest v1 or v2 test project to MSTest v3. Use when user says "upgrade MSTest", "upgrade to MSTest v3", "migrate to MSTest v3", "update test framework", "modernize tests", "MSTest v3 migration", "MSTest compatibility", "MSTest v2 to v3", or build errors after updating MSTest packages from 1.x/2.x to 3.x. (Microsoft.VisualStudio.QualityTools.UnitTestFramework) or MSTest v2 NuGet (MSTest.TestFramework 1.x-2.x) to MSTest v3, fixing assertion overload errors (AreEqual/AreNotEqual), updating DataRow constructors, replacing .testsettings with .runsettings, timeout behavior changes, target framework compatibility (.NET 5 dropped -- use .NET 6+; .NET Fx older than 4.6.2 dropped), adopting MSTest.Sdk. First step toward MSTest v4 -- after this, use migrate-mstest-v3-to-v4. migrating between frameworks (MSTest to xUnit/NUnit), or general .NET upgrades unrelated to MSTest.
> Fix build errors and breaking changes after upgrading MSTest from v3 to v4, or plan a complete MSTest v3-to-v4 migration. Use when user says "upgrade to MSTest v4", "MSTest 4 migration", "MSTest v4 breaking changes", "tests don't compile after upgrading MSTest", or has errors CS0507, CS0103, CS1061, CS1615 after updating MSTest packages from 3.x to 4.x. sealed custom attributes, ClassCleanupBehavior removal, TestContext.Properties Contains to ContainsKey, Assert.ThrowsException to ThrowsExactly, Assert.IsInstanceOfType out parameter removal, ExpectedExceptionAttribute removal, TestTimeout enum removal, [TestMethod("name")] to DisplayName syntax, TreatDiscoveryWarningsAsErrors, TestContext.TestName in ClassInitialize, MSTest.Sdk MTP changes, dropped TFMs (net6.0/net7.0 to net8.0+). first), migrating between test frameworks, or general .NET upgrades.
> Migrates .NET test projects from VSTest to Microsoft.Testing.Platform (MTP). Use when user asks to "migrate to MTP", "switch from VSTest", "enable Microsoft.Testing.Platform", "use MTP runner", or mentions EnableMSTestRunner, EnableNUnitRunner, or UseMicrosoftTestingPlatformRunner. discovered, --ignore-exit-code, TESTINGPLATFORM_EXITCODE_IGNORE), conditioning OutputType=Exe to test projects when centralizing MTP properties in Directory.Build.props. Supports MSTest, NUnit, xUnit.net v2 (via YTest.MTP.XUnit2), and xUnit.net v3 (native MTP). Covers runner enablement, CLI argument translation, xUnit.net v3 filter migration (--filter-class, --filter-trait, --filter-query), Directory.Build.props and global.json config, CI/CD pipeline updates, and MTP extension packages. xUnit.net v2 to v3 API migration, MSTest version upgrades, TFM upgrades, or UWP/WinUI test projects.
Claude Skills — questions
Answers built from the skills we actually parsed.