Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Design interfaces that detect and respond to system-level user preferences. Use when implementing dark mode, reduced motion, high contrast, text scaling, or any user preference that affects how the interface renders. Triggers on: user preference, system preference, prefers-reduced-motion, prefers-contrast, prefers-color-scheme, forced-colors, media query, user settings, system settings, accessibility settings, OS settings.
Graph database implementation for relationship-heavy data models. Use when building social networks, recommendation engines, knowledge graphs, or fraud detection. Covers Neo4j (primary), ArangoDB, Amazon Neptune, Cypher query patterns, and graph data modeling.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Implement immersive and spatial video experiences on Apple Vision Pro (visionOS 27), including AVKit AVExperienceController, RealityKit VideoPlayerComponent setup, Apple Projected Media Profile (APMP), portal/progressive/full immersive viewing modes, transitions and events, comfort mitigation, and Apple Immersive Video authoring workflows.
Helps write C# node classes for vvvv gamma — the [ProcessNode] lifecycle pattern, Update() method, out parameters, pin configuration, change detection, stateless operation nodes, the public-API import model, and service consumption via NodeContext (IFrameClock, Game access, logging). Use when writing a node class, adding pins, implementing change detection, accessing services in node constructors, persisting runtime state through Create pins, creating stateless utility methods, or deciding whether a class needs [ProcessNode] at all. Requires the assembly to have one of [assembly: ImportAsIs] / [assembly: ImportNamespace] / [assembly: ImportType] set (see vvvv-node-libraries).
Use when the user says 'why is my checkout broken', 'audit my woocommerce store', 'cart problems woocommerce', or 'losing sales woocommerce'. Diagnoses checkout and cart failures, AJAX mismatches, caching conflicts, payment gateway setup, and SSL enforcement.
WordPress ACF and content modeling review. Use when reviewing Advanced Custom Fields usage, field group architecture, CPT and taxonomy design, options pages, repeaters, flexible content, block-bound field groups, meta storage patterns, or when user mentions "ACF", "field groups", "flexible content", "repeater", "custom post type design", "taxonomy design", "content model", "relationship fields", "ACF JSON", "options page", or "meta query performance". Detects schema drift, weak content modeling, brittle field naming, and performance issues in meta-heavy WordPress builds.
Writes commit messages and pull request descriptions for the adk-python repository: Conventional Commits types and scopes, subject lines that say why a change was made, and the linked-issue and testing-plan sections the PR template requires. Use when writing or rewording a commit message, squashing commits before a pull request, drafting a PR description, or checking that a change is shaped to land. Don't use for generic git mechanics such as rebasing, resolving conflicts, cherry-picking, or branch surgery; those need no skill. Don't use to judge the content of a change (use adk-review) or for code style and naming (use adk-style).
Unified WebView remote debugging toggle for Android projects. `android-webview-debug-enable` sets all `setWebContentsDebuggingEnabled` calls to `true` and records modified locations with their original content; `android-webview-debug-revert` restores from the record, listing any mismatched entries at the end for manual confirmation. Triggers: 「开启 WebView 调试」「恢复 WebView 调试」 / android-webview-debug-enable, android-webview-debug-revert. Suitable for Android projects that need to uniformly enable or restore WebView debugging.
Use this skill whenever the user wants to develop, edit, push, deploy, debug, or manage Google Apps Script (GAS) projects using the clasp CLI. Triggers on any mention of clasp, Apps Script, .gs files, script.google.com, appsscript.json, Google Sheets/Docs/Forms/Slides/Drive automation, GAS triggers, or local GAS development. Also use this when someone wants to automate Google Workspace, build a Sheet macro, create a web app on GAS, set up a time trigger, write any script that runs in Google's cloud, use TypeScript with Apps Script, create a GAS library, or integrate Gemini AI into a Sheet — even if they don't say "clasp" explicitly.
Use the `asc` CLI tool (App Store Connect CLI) to manage iOS/macOS apps on App Store Connect. Use this skill when: (1) User wants to manage App Store Connect resources from terminal or CI (2) User is migrating from fastlane, Xcode GUI, or manual App Store Connect workflows (3) User asks about submitting, uploading, TestFlight, metadata, screenshots, IAPs, subscriptions, code signing, or any ASC operation (4) User says "submit my app", "list my apps", "upload screenshots", "check builds", "update app name", "create IAP", "add subscription", "migrate from fastlane", etc. (5) Setting up authentication or managing multiple App Store Connect accounts (6) Building CI/CD pipelines for App Store releases
Build Business Manager extension cartridges with custom admin tools, menu items, and dialog actions. Use this skill whenever the user needs to create bm_* cartridges, add menu actions or dialog buttons in BM, configure bm_extensions.xml, or extend admin pages with form overlays. Also use when customizing the BM interface for back-office workflows -- even if they just say 'add a button to BM' or 'custom admin page'.
Develop Custom SCAPI REST endpoints with api.json routes, schema.yaml definitions, and OAuth scope configuration. Use this skill whenever the user needs to create a custom API on the Commerce platform, define OpenAPI 3.0 schemas for request/response, structure the rest-apis cartridge folder, or debug endpoint registration and 404 issues. Also use when building headless commerce integrations, choosing between Shopper (`ShopperToken`) and Admin (`AmOAuth2`) APIs, or troubleshooting why a Custom API endpoint isn't appearing or returning 404 in `b2c scapi custom status` — even if they just say 'custom REST endpoint', 'expose my script as an API', or 'my admin custom API isn't registering'.
Define Page Designer page types and component types with regions, attributes, and rendering scripts. Use this skill whenever the user needs to create a new page or component type, configure regions with allowed component constraints, define attribute_definition_groups, debug why a component does not appear in the editor, or fix enum/color attribute pitfalls. Also use when building visual merchandising experiences -- even if they just say 'my component is missing from PD' or 'add a hero banner component'.
Use when adding localization to a Bevy 0.20 app with `es-fluent-manager-bevy` 0.21, defining typed messages with `#[derive(EsFluent)]`, wrapping UI text in `FluentText<T>`, auto-registering locale updates with `#[derive(BevyFluentText)]`, or switching locales via `LocaleChangeMessage` / `LocaleChangedMessage`. Covers `I18nPlugin`, `RequestedLanguageId`, `ActiveLanguageId`, `i18n.toml` config, and hot-reload of `.ftl` assets.
Provides comprehensive guidance for Bootstrap Vue 3 component library including Bootstrap components, grid system, utilities, and Vue 3 integration. Use when the user asks about Bootstrap Vue 3, needs to use Bootstrap components in Vue 3, or implement responsive layouts.
Provides comprehensive guidance for Bootstrap Vue 3 component library including Bootstrap components, grid system, utilities, and Vue 3 integration. Use when the user asks about Bootstrap Vue 3, needs to use Bootstrap components in Vue 3, or implement responsive layouts.
Compile a PAM control's Android Kotlin module into the runtime-loadable DEX for a `.ppmplugin`. Creates a staged Gradle build with the pinned wrapper and `react-android` compile dependency, verifies manifest/module/package alignment and runtime-loading constraints, builds the release AAR, then runs `d8 --min-api 24`. Writes `ppmplugin/staging/android/<PascalName>Plugin.dex` and surfaces actionable Gradle or d8 failures. Requires JDK 17+ and Android SDK Build-Tools 35.0.0; `d8` is located from the SDK and system Gradle is optional. Run after /generate-ppmplugin-manifest and before /assemble-ppmplugin.
This skill should be used when the user asks to "分析构建错误", "analyze build errors", "查看编译错误", "检查构建日志", "诊断链接错误", "fix build errors", "resolve compilation errors", "分析 last_error.log", "extract build error", "分析SDK的编译错误", "分析 SDK 编译错误", "analyze SDK build errors", "check SDK errors", "诊断 sdk 编译错误", or mentions analyzing build failures, compilation errors, linker errors, undefined symbols, SDK compilation errors, or needs to fix build issues. Focuses on reading last_error.log from out/<product>/ directory (or out/sdk/ for SDK builds) and providing specific fix recommendations based on error patterns and historical cases.
Compile a PAM control's iOS Obj-C/Swift module into the FLAT device-slice `.framework` for a `.ppmplugin` bundle (never an `.xcframework` — the wrap CI won't descend into one). Mac-only (Xcode). Builds from a throwaway staged copy so canonical `ios/` and the podspec stay untouched, references React-Core headers only (React is weak-linked and provided by the wrap host at runtime, no CocoaPods), generates the required umbrella header, module map and Info.plist, sets the critical build settings, asserts manifest conformance, then runs a device-only `xcodebuild archive` and copies out the flat framework to `ppmplugin/staging/ios/`. Known limitation — the React weak-link flags aren't yet validated against a live wrap host and the RN pin must match the host's. Run after /generate-ppmplugin-manifest for an iOS or Both target, before /assemble-ppmplugin.
Makes a Capacitor iOS app work in windows that resize while running (iPad Split View, Slide Over, Stage Manager, windowed apps, the foldable iPhone). Audits the web layer (viewport, `100vh`, device sniffing, `screen.width`, `window.orientation`, cached safe-area insets) and native code in the app and node_modules plugins (`UIScreen.main`, `interfaceOrientation`, `userInterfaceIdiom`, `keyWindow`, AppDelegate lifecycle, hard-coded bar heights), then applies trait-, window- and scene-based replacements. Checks Info.plist `UIRequiresFullScreen` (ignored on iOS 27, TN3192), iPad orientations, launch screen (ITMS-90870) and the UIScene lifecycle (Capacitor 8.5+). Use for "support iPad multitasking", "Stage Manager layout broken", "app does not resize", "foldable iPhone", or a plugin overlay mis-sized in split view. Do not use for notch padding only (safe-area-handling) or the SceneDelegate migration (capacitor-uiscene-migration).
Advise developers on using Contentstack branches for isolated content development and aliases for zero-downtime content deployments. Cover branch strategy, branch-specific vs global modules, CI/CD integration, merge behavior, and rollback patterns. Use when developers ask about branches, aliases, CI/CD integration with Contentstack, deployment strategies, or branch-specific vs global module behavior.
Surface-independent commerce domain logic — pricing models (customer groups, channel fallback, high-precision money), discount stacking (Product/Cart/Code/Direct/Groups), shipping predicates and cart score, tax modes, payment object modeling, Import API bulk patterns, and catalog architecture. Use for commerce-domain questions that are independent of surface (storefront, MC app, Connect).
Expertise in compiler development using LLVM infrastructure including frontend design, IR generation, optimization passes, and code generation. Use this skill when building custom programming languages, implementing DSL compilers, or working on compiler internals.
Load this skill when debugging behavior in external libraries by reading local OpenSrc mirrors (Effect, TanStack, TRPC, Drizzle, Better Auth, Sentry, Pino), or when docs conflict with runtime behavior and source-level verification is required.
Instrument an AI application with DeepEval's native tracing so its behavior is visible in Confident AI. TRIGGER when the user wants to add DeepEval tracing or @observe to an LLM app, agent, RAG pipeline, or chatbot; wire a framework, model-provider, or vector-database integration (LangGraph, LangChain, OpenAI Agents, LlamaIndex, Pydantic AI, CrewAI, and others); choose between a native integration and manual instrumentation; set span types, tags, or metadata; or send DeepEval-SDK traces to Confident AI's Observatory. DO NOT TRIGGER for building DeepEval pytest eval suites, datasets, goldens, metrics, or deepeval test run (use the `deepeval` skill), or for raw OpenTelemetry / OTLP export without the deepeval package (use the `deepeval-otel` skill). This skill is purely DeepEval-SDK instrumentation — producing well-formed traces, not running evals.
Implements Flutter screens from designer screenshots and handoff notes using Material 3. Two-pass workflow: mockup-brief with Implementation spec, then AppShell + route screens. Use when approved mockups exist for a HeyEddi Flutter app.
This skill should be used for structured feature development with codebase understanding. Triggers on /do command. Provides a 5-phase workflow (Understand, Clarify, Design, Implement, Complete) using codeagent-wrapper to orchestrate code-explorer, code-architect, code-reviewer, and develop agents in parallel.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Export Figma variables to design token files in DTCG, CSS custom properties, Tailwind v4/v3, SCSS, TypeScript, JSON, Style Dictionary, or Tokens Studio. Use when the user wants to pull design tokens OUT of Figma into code — triggers: 'export tokens', 'export Figma variables', 'generate CSS variables from Figma', 'turn my Figma variables into a tokens.json / Tailwind config / SCSS', 'sync design tokens to code'. Works on ANY Figma plan (reads via the Plugin API, not the Enterprise-only Variables REST API). For the reverse direction (code → Figma) use import-tokens-figma.
Design, inspect, or repair game mechanics, core loops, rules, goals, actions, state, chance, secrets, skills, and emergent dynamics. Use when building gameplay systems, combat, puzzles, progression, simulations, board/card mechanics, or any feature where rules create player behavior.
Implement a complete closed-loop process for handling web editor to-dos via the Axhub AI Extension (Chrome extension) together with the @axhub/genie CLI. Guide users through installing the extension and detecting connection status, discovering online editor clients, reading user annotations and to-do nodes, exporting context screenshots and images, setting edit status (editing/idle/completed/error four-state lifecycle), completing code changes and writing back the final state. Supports communication stability safeguards such as CLI automatic retries, exponential backoff reconnection, tab visibility awareness, and task state persistence. Use when the user has annotated web modification to-dos via Genie Editor and wants AI to handle them.
Git commit unified entry point. Triggers when user says 「提交代码」「git commit」「帮我提交」「写 commit message」「生成 commit」「提交一下」「git-commit」「自动提交代码」「git-commit-auto」 (commit code / help me commit / write commit message / generate commit / auto commit), or when invoked by jira-fix-workflow phase 7.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.