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. 79 551 files from 1 750 authors, of which 61 898 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.
Build VS Code extensions from scratch or convert existing JS/React/Vue apps. Supports commands, webviews (React/Vue), custom editors, tree views, and AI agent integration via file-bridge IPC. Use when user wants to create a VS Code extension, convert a web app to an extension, add webviews or custom UIs to VS Code, implement tree views, build custom file editors, integrate with AI agents, or package/publish extensions (.vsix).
Expert WCAG (Web Content Accessibility Guidelines) advisor covering WCAG 2.0, 2.1, and 2.2 — the W3C international accessibility standards. Use this skill whenever a user asks about WCAG success criteria, conformance levels (A/AA/AAA), accessibility audits, POUR principles, accessibility statements, ARIA patterns, colour contrast, keyboard accessibility, screen reader compatibility, mobile accessibility, cognitive accessibility, WCAG 2.2 new criteria, WCAG 3.0 preview, legal requirements referencing WCAG (EN 301 549, EAA, ADA, Section 508), or mapping WCAG to accessibility laws. Trigger for any web or digital content accessibility question — even if the user doesn't say \"skill\" or \"WCAG\".
Guide for (a) auditing an existing whistleblower system or (b) drafting a compliant reporting policy from a provided template. Covers EU Directive 2019/1937, the amended Sapin II law (Waserman 2022), Decree 2022-1284, CNIL guidelines, public sector requirements, and duty of vigilance.
Writes a settlement letter on the right footing — and warns you when marking it 'without prejudice' won't actually keep it out of court. A genuine settlement letter is normally protected (the judge can't see it), but only if the substance is a real attempt to settle, and even then there are exceptions. The skill picks the correct footing — without prejudice (WP), without prejudice save as to costs (WPSATC / Calderbank), or open — drafts the finished letter, and surfaces the Unilever v Procter & Gamble exceptions that get WP material admitted despite the label, which a plain template won't flag. Built for juniors and in-house counsel drafting a settlement or Calderbank offer who need the footing right the first time. Use when the user asks to draft a WP letter, a Calderbank, a settlement letter, or wants to know whether material is likely protected from disclosure.
Edit, query, and transform Word documents (.docx) with the SuperDoc CLI. Use when the user asks to read, search, modify, format, comment, track changes, or review changes in .docx files. Triggers on any task involving Word documents — text replacement, redlining, contract markup, template filling, bulk edits, content extraction, or document review.
Toolkit for comprehensive document reading, editing, and creation with visual quality control. Use to work with Word documents (.docx files) for: (1) Reading or extracting content from existing DOCX files, (2) Creating new Word documents with professional formatting, (3) Editing documents requiring precise typography and layout, or any other DOCX reading or generation tasks.
Edit, query, and transform Word documents with the SuperDoc CLI v1 operation surface. Use when the user asks to read, search, modify, comment, or review changes in .docx files.
| Drafts a customized Customer Agreement starting from the Y Combinator standard form SaaS template. Tailors the agreement through structured intake questions covering fee structure, data handling, ML rights, implementation services, and more. Applies 18 always-on defaults that transform the raw YC form into a professional starting point (renamed to "Customer Agreement", data privacy section added, warranty restructured, consolidated SLA/support exhibit, etc.). Produces a clean .docx and a lawyer-facing memo explaining every change from the YC standard. Use when user says "draft a SaaS agreement", "YC SaaS", "startup SaaS contract", "customer agreement", "SaaS subscription agreement", or "I need a SaaS agreement starting from the YC form". Also trigger when the user is a startup founder discussing SaaS contracting, even if they don't mention YC specifically.
Direct browser control via the Browser Use Terminal CLI. Use when the user wants to automate, scrape, test, or interact with web pages — you drive the browser yourself with Python helpers.
> Guide for feature flags and A/B tests with the Flags SDK (`flags` npm package) and Vercel Flags. (add, list, enable, disable, inspect, archive, rm, sdk-keys), setting up providers/adapters (Vercel, Statsig, LaunchDarkly, PostHog, GrowthBook, Hypertune, Global Config, OpenFeature, Split, Flagsmith, Reflag, Optimizely, or custom adapters), implementing precompute patterns for static pages, setting up `identify`/`dedupe`, integrating Flags Explorer/Toolbar, working with flags in Next.js (App Router, Pages Router, Middleware) or SvelteKit, writing custom adapters, or encrypting/decrypting flag values. Flags Explorer, feature gates, flag overrides, Vercel Flags, vercel flags CLI, vercel flags add, vercel flags list, vercel flags enable, vercel flags disable, `flags/next`, `flags/sveltekit`, `flags/react`, `@flags-sdk/*`.
> Sets up, migrates, or enhances Azure Monitor Application Insights in .NET applications. Detects application type and existing instrumentation automatically. Use when adding Application Insights, Azure Monitor, observability, or telemetry to ASP.NET Core, Worker Service, ASP.NET Classic, or Console apps, upgrading from Application Insights 2.x to 3.x, migrating from TelemetryClient to OpenTelemetry, or adding Entity Framework, Redis, SQL, or OTLP telemetry to apps already using Application Insights.
Use when working on accessibility, a11y, WCAG, ARIA, screen readers, keyboard nav, focus order, contrast, alt text, captions, reduced motion, or target sizes; not language/culture/device (see inclusive-design).
Use when creating a feature, designing folder structure, adding repositories/services/view models, wiring dependency injection, or deciding which layer owns logic.
Use when creating a Cubit or Bloc, modeling state with sealed classes or status enums, wiring BlocBuilder/BlocListener/BlocProvider, writing bloc tests, or choosing between Cubit and Bloc.
Use when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.
Use when writing switch statements, refactoring if-else chains, creating data classes, choosing records vs classes, destructuring values, or modernizing pre-Dart-3 code.
Use when building AI agents in Dart, implementing Genkit flows or tools, integrating LLMs into Dart or Flutter applications, or using Genkit Dart plugins.
Use when writing Dart code, reviewing for style, refactoring naming, adding doc comments, structuring imports, or enforcing type annotations.
Use when setting up firebase_ai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
Use when logging analytics events, setting user properties, configuring default event parameters, building funnels, or adding screen-view tracking.
Use when implementing app attestation, configuring App Check providers, setting up debug tokens, enabling backend enforcement, or managing token refresh.
Use when setting up auth, managing auth state, implementing email/password or social sign-in, handling auth errors, or managing users.
Use when setting up Firestore, designing schemas, doing CRUD, creating listeners, paginating queries, configuring indexes, enabling offline persistence, or writing security rules.
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.
Use when setting up Data Connect, writing GraphQL queries/mutations, configuring generated SDKs, handling offline, or applying security rules.
Use when syncing real-time data, structuring JSON trees, reading/writing, creating listeners, enabling offline persistence, managing presence, sharding, or writing security rules.
Use when running in-app message campaigns, triggering/suppressing messages, configuring opt-in data collection, testing on specific devices, or handling message callbacks.
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.
Use when setting up Storage, uploading/downloading files, managing metadata, handling errors, or applying security rules.
Use when scaffolding a project, refactoring into layers, creating view models/repositories, configuring dependency injection, or implementing unidirectional data flow (MVVM).
Use when writing, reviewing, refactoring, or planning Flutter/Dart code — screens, features, project structure, state management, folders, widgets, cubits/blocs, repositories, services, or tests.
Use when setting up ChangeNotifier models, providing them to the widget tree, consuming state with Consumer or Provider.of, or optimizing rebuilds.
Use when hitting layout errors (RenderFlex overflow, unbounded constraints, RenderBox not laid out), scroll errors, or setState-during-build errors.
Use when preloading fonts, asset/network images, Lottie/Rive animations, local JSON/config, warming initial API data, or optimizing Flutter Web startup.
Use when building any Flutter screen or component to choose responsive Row, Column, Expanded, Flexible, and Spacer layouts before fixed-size or coordinate-based alternatives.
Use when adding Firebase to a Flutter project, running flutterfire configure, initializing Firebase in main.dart, or configuring multiple flavors.
Use when working on inclusion, i18n/localization, global name/address forms, low-end devices, slow/metered networks, affordability, or first-time/low-confidence users; not WCAG/screen readers (see accessibility).
Use when generating mocks, stubbing methods, verifying interactions, capturing arguments, or choosing between mocks, fakes, and real objects (Mockito).
Use when creating mocks, stubbing methods, verifying interactions, registering fallback values, or choosing between mocks, fakes, and real objects (Mocktail).
Use when writing E2E/integration tests, testing native interactions like permissions or system dialogs, capturing UI regressions, or validating cross-platform behavior (Patrol 4.x).
Use when setting up providers, consuming state, optimizing rebuilds, using ProxyProvider, or migrating from deprecated providers (Provider package).
Use when testing RevenueCat purchases/subscriptions, setting up sandbox testing, debugging a purchase/restore/trial, verifying entitlements or events, or writing an IAP QA plan.
Use when setting up providers, combining requests, managing state disposal, passing arguments, performing side effects, or testing providers (Riverpod).
Use when writing store copy to character limits (name, subtitle, descriptions, keywords) or preparing listing images (icon, feature graphic, screenshots, preview video).
Use when writing or reviewing Flutter/Dart tests (unit, widget, golden), fixing flaky tests, adding coverage, or choosing between unit and widget tests.
Async data in Reactor — `UseResource` (single fetch), `UseMutation` (writes + optimistic updates), `UseInfiniteResource` (cursor pagination), and `Pending` (bubble-up fallback). Use when fetching, caching, paginating, or mutating server data.
> Create WinUI 3 desktop applications using the Reactor framework — a React-inspired declarative C# projection over WinUI 3. No XAML, no data binding, no templates. This file is the legacy single-file skill — prefer the `reactor` plugin under `plugins/reactor/` (or `agentkit/plugins/reactor/` in the NuGet) for a more efficient skill-loading experience.
Reactor.Advanced Win2D canvases — choosing Win2DCanvas, Win2DAnimatedCanvas, or Win2DVirtualCanvas; using UseDrawState, UseCanvasResources, UseDrawCommand; and following threading/device-loss rules.
Author or remove Reactor "did-you-mean" / diagnostic analyzers and the matching `mur check` rules in the microsoft/microsoft-ui-reactor repo. Activate when a contributor asks to "add a REACTOR_ diagnostic", "add a did-you-mean for <mistake>", "add/remove a mur check rule", "suggest the right factory/argument", "write a Roslyn analyzer for Reactor", or "wire an in-build suggestion". Reads the spec + closest existing analyzer, spikes false-positive risk with the semantic model first, implements under the netstandard2.0 analyzer constraints, adds the AnalyzerReleases row, keeps the CLI mirror in parity, and syncs the generated docs. Applies changes; does NOT push.
Building Reactor apps and reading diagnostics — `mur check <path>` is the build (same exit code as `dotnet build`, never re-run to confirm) with one-line diagnostics, skill pointers, and `→ try:` did-you-mean suggestions to use verbatim. Covers iteration vs `--final` workflow, the common-build-errors cheat table mapping `REACTOR_HOOKS_*` / `REACTOR_DSL_*` / `REACTOR_THEME_*` / `REACTOR_A11Y_*` / `REACTOR_OPT_*` / `CS*` IDs to fixes, when single-file vs `.csproj` matters for analyzer coverage, build prerequisites. Use when a build fails, you see an analyzer warning, or you want a structured diagnostic stream instead of raw MSBuild output.
Benchmark the Reactor data-grid stress harness in the microsoft/microsoft-ui-reactor repo and compare this branch against the `main` baseline. Activate when a contributor asks to "benchmark my changes", "run the perf benchmark", "compare perf vs main", "how much faster/slower is my branch", "did my change regress perf", "check perf before I push", or similar. Builds + runs StressPerf.ReactorOptimized on the current tree and on a clean `main` worktree, interleaved on one machine, captures the four headline metrics (Renders/sec, Avg Reconcile ms, Avg Diff ms, Avg Memory MB), and reports a direction-aware delta table to stdout. Does NOT apply fixes.
Raise test coverage for the microsoft/microsoft-ui-reactor repo with non-vacuous tests, picking the right tier (headless unit / selftest / E2E). Activate when a contributor asks to "improve test coverage", "add tests for X", "raise coverage", "cover the uncovered lines", "write selftests / e2e for this", "close coverage gaps", or "add unit tests". Baselines with tools/coverage, classifies each gap by tier, writes narrowly-scoped tests whose assertions fail if the target code is deleted, mutation-checks the key oracles, and runs the pr-review multi-model cross-check on the final commit. Applies changes (adds tests); does NOT change product code to chase coverage.
Reactor commanding — actions that appear in multiple surfaces (menu + toolbar), need keyboard shortcuts, or need `CanExecute`. `Command`, `StandardCommand`, `UseCommand`, `CommandHost`. Use when wiring shared actions or shortcuts.
Reactor charts and data visualization — choosing a chart type (line, bar, area, donut, `TreeChart`, `ForceGraph`), the chart DSL, `LabelView` / `XTickLabelView` / `YTickLabelView` for icon-plus-text and rich labels, and the visualization-best-practices rules. Use when adding charts or designing visualizations.
Reactor navigation — `UseNavigation` hook, `NavigationHost` renderer, `NavigationView` sidebar, `TabView` tabs, route params, stack operations, page lifecycle, deep linking, transitions, caching. Use when building multi-page apps or wiring sidebar/tab navigation.
Pointer to the full Reactor API signatures index (`references/reactor.api.txt`). The 90% of DSL content — hooks, components, common factories, modifiers, theme tokens, gotchas, React-to-Reactor mapping — already lives in `reactor-getting-started`. Load this skill only when you need to verify a less-common signature against the alphabetized full index.
Windows 11 design rules for Reactor — theme tokens, High Contrast, typography (`Heading`/`SubHeading`/`Caption`), 4px grid, acrylic surfaces, accessibility, animation, and a code-review checklist. Use when authoring, reviewing, or fixing visual styling.
Claude Skills — questions
Answers built from the skills we actually parsed.