Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Expert knowledge for Azure AI Language development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using CLU, custom/health NER, CQA, sentiment/PII APIs, or Language/TA/health containers, and other Azure AI Language related development tasks. Not for Azure AI Search (use azure-cognitive-search), Azure AI Document Intelligence (use azure-document-intelligence), Azure Speech in Foundry Tools (use azure-speech), Azure Translator (use azure-translator).
Expert knowledge for Azure Translator development, including troubleshooting, best practices, decision-making, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when working with Translator REST/SDK APIs, Custom Translator, glossaries, batch document jobs, or Docker containers, and for other Azure Translator-related development tasks. Not for Azure AI Language (use azure-language-service) or Azure Speech in Foundry Tools (use azure-speech).
PRD facilitator (John the PM). Authors and maintains the Product Requirements Document: functional requirements (FR-###), non-functional requirements (NFR-###), an epics outline, user stories, acceptance criteria, and MoSCoW/RICE prioritization. Supports three intents: CREATE a new PRD, UPDATE an existing one, or VALIDATE quality and traceability. Emits prd.md plus addendum.md (overflow/notes) and appends decisions to decision-log.md. Use when the user says: “create a PRD,” “write the product requirements,” “draft requirements,” “define functional/non-functional requirements,” “break this into epics and stories,” “prioritize features,” “MoSCoW,” “RICE score these features,” “update the PRD,” “add a requirement,” “validate my PRD,” “is my PRD complete,” or “review requirements traceability.” This is PLANNING only—it never writes application code, runs tests, lints, or builds.
Use when building a PlayCanvas game's on-screen interface such as ready, pause, and victory overlays, menus, and live indicators like gauges, timers, or reload meters, so the interface is driven by game state, readable over the scene, and separate from the 3D hierarchy.
Add production-ready authorization (RBAC, ABAC, ReBAC) to Convex apps with O(1) permission checks. Use when implementing roles, permissions, access control, multi-tenancy, or relationship-based authorization in a Convex project. Inspired by Google Zanzibar / SpiceDB
A five-step development workflow. Supports requirements understanding, solution design, implementation, code review, and bug fixing. Use when the user mentions “requirements analysis,” “solution design,” “implementation,” “code review,” “understand the requirements,” “technical design,” “start coding,” “Review,” “check the code,” “bug,” “error,” “crash,” “exception,” or “something went wrong.”
Checks whether a developer understands a pull request before they merge it, especially code an AI agent wrote. It reviews the author rather than the code by questioning them about changes they can't explain. Use whenever someone is about to open, submit, review, or merge a PR, branch, or diff containing AI-generated code, or wants to ensure they understand a change before shipping.
A skill for creating and developing custom view plugins for Mingdao Cloud HAP. Trigger immediately when the user mentions “HAP view plugin,” “custom view,” “mdye,” “view development,” “plugin development,” “initialize view project,” or “start view debugging.” Provides a complete development workflow, API usage guide, and best practices.
Use when structuring a PlayCanvas game's control flow — a small state machine such as ready, playing, paused, and over, pointer-lock capture, pausing on focus or pointer-lock loss, a full reset, and a stable clock and timestep — so the loop stays deterministic and recoverable.
Execute the next task of a free local or server-planned Altitude learning project — the learner writes every line of what is being taught, drills each new concept in a scratch file first, predicts before runs that exercise new material, and is reviewed only on what they have already learned. Use when the user says "next lesson", "let's continue the project", "next task", or invokes /next-lesson.
Gate an implementation plan BEFORE agents execute it — catch phantom paths and false reuse, not typos: read the full plan markdown and its companion JSON, reality-check every file path and reuse claim against the actual repo, challenge scope, architecture, the dependency graph, and risk and test coverage, then score each section and render an APPROVE / REVISE / REJECT verdict — runs as a forked review workflow with its own reasoning budget, isolated from the main execution flow. The verdict follows only from evidence-backed findings: never rubber-stamps a non-trivial plan and never invents findings, but a genuinely clean section is allowed to pass; read-only, never edits the plan. Use when the user asks to review or gate a plan before execution.
Used to start, reset, or troubleshoot the XGENT portal Docker one-box local integration environment in the App's own repository; no need to clone or modify the portal source code. Handles image pulling, registration, ports, health checks, and integration troubleshooting.
Wires every side effect and native channel as an injectable interface behind a Provider that throws UnimplementedError until the composition root overrides it, with one live impl per flavor, value-typed signatures returning typed results, hand-written contract-honouring fakes over mocks, MethodChannel quarantined to one lib/native/ directory, and versioned cross-language contracts edited on both sides in one commit. Use when adding or changing a ShareService/AnalyticsService/RemoteConfigService or any side-effect port, injecting a Clock (package:clock) via clockProvider, a MethodChannel/platform channel or native widget bridge, a flavor entrypoint (main_*.dart) or per-flavor provider override, a shared-file/JSON contract mirrored in Kotlin/Swift, replacing a stray DateTime.now() or direct SDK call inside a widget/notifier/repository, or wiring a fake via ProviderScope(overrides:) in tests.
Kick off a learn-to-code-by-building project. Interviews the user to find a project idea sized to their experience, defines an MVP, and maps the core components (the “trunk”) they'll learn end to end. Use when a beginner wants to start a learning project, says “help me pick a project”, “I want to learn to code by building something real”, or invokes /start-project.
Comprehensive guide for implementing Syncfusion WPF Charts (SfChart) in Windows Presentation Foundation applications. Use this when working with WPF charts, data visualization, or interactive charting features. This skill covers chart series types, axes configuration, data binding, appearance customization, financial charts, technical indicators, and interactive features like zooming and tooltips for WPF applications.
Implements the Syncfusion WPF Color Palette (SfColorPalette) control for color selection interfaces with swatches. Use this when implementing color picker functionality, color swatches, or color binding in WPF applications. Covers setup, color selection, data binding, swatch navigation, appearance customization, and theming.
Comprehensive guide for implementing, registering, and troubleshooting Syncfusion licensing across all platforms. Covers license key registration, license validation errors, RegisterLicense API, SyncfusionLicenseProvider configuration, trial vs. licensed versions, CI/CD build server setup, and platform-specific licensing requirements. Use this skill when users need help with Syncfusion license registration, licensing validation issues, or license-related troubleshooting.
Generates a heat-map and metrics report of a repository based on code complexity, lack of tests, and 'TODO/FIXME' density. Use when you need to identify high-risk areas for refactoring or when planning technical debt reduction sprints.
WhatsApp messaging deep-dive reference. Covers the 24-hour service window rules (free-form vs template mode), sandbox setup for testing, template approval workflow, production sender requirements, and WhatsApp-specific error handling. For sending WhatsApp messages, use twilio-send-message instead. Use this skill when setting up WhatsApp for the first time or debugging WhatsApp-specific delivery behavior
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.
WHAPI.cloud WhatsApp API guide for AI agents. Use this skill when building WhatsApp bots, automations, CRM integrations, or broadcast systems with WHAPI. Prevents the most common AI mistakes: wrong Chat ID format, wrong message type, polling instead of webhooks, and hallucinated parameters.
Work inside the wonder-image/app framework package — the Composer library at github.com/wonder-image/app. This is the framework core, not a site that consumes it. Trigger when: - the repo's composer.json declares `"name": "wonder-image/app"` - editing files under `class/App/*`, `app/config/routes/*`, `app/http/*`, `app/bootstrap/*`, `app/middleware/*`, `class/App/Module/*`, `class/Console/*` - editing shared UI components under `class/Elements/Components/*`, media under `class/Elements/Media/*`, or their renderers under `class/Themes/{Wonder,Bootstrap}/*` - modifying Model, Resource, PageSchema, Repeater, ModelRegistry, ResourceRegistry, ResourceRouteRegistrar, Credentials, or the `wonder-image.php` entrypoint - changing bootstrap order, `ROOT`/`.env` resolution, module discovery, generated backend/API CRUD routes, or `php forge ...` command sources - editing `docs/components/*`, `class/Docs/*` or `bin/docs.php` (the component catalogue) - editing request, auth or security code under `class/Http/*`, `class/Auth/*`, `class/Api/*`, `class/Backend/*`, `class/App/Security/*`, or `class/App/Support/Upload*` (CSRF, cookies, redirects, uploads, exports, API tokens) - updating `docs/app/*` for bootstrap, architecture, routing, or layout conventions SKIP when: - the repo is a Wonder site that installs wonder-image/app under `vendor/` (e.g. wonder-image/new-site or any project scaffolded from it) — use wi-site - the change is in `custom/`, `app/Models`, `app/Resources`, `lang/`, or `assets/` of a site - the task is in wonder-image/lib (the JS/CSS design system) — different repo
MSIX packaging, code signing, and distribution for WinUI 3 apps with WinApp CLI 0.7+ — SDK-native project packaging, Native AOT, certificates, self-contained deployment, CI/CD, and Microsoft Store handoff. Use when preparing for release, creating MSIX installers, managing certificates, setting up CI/CD packaging, or publishing to the Microsoft Store.
Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.
Use when debugging schema migration crashes, concurrency thread-confinement errors, N+1 query performance, SwiftData to Core Data bridging, or testing migrations without data loss — systematic Core Data diagnostics with safety-first migration patterns
Expert knowledge for Azure Digital Twins development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when modeling DTDL graphs, integrating IoT Hub/ADx, configuring endpoints/routes, securing access, tuning query units, and for other Azure Digital Twins development tasks. Not for Azure IoT Hub (use azure-iot-hub), Azure IoT Central (use azure-iot-central), or Azure IoT Operations (use azure-iot-operations).
Expert knowledge for Azure IoT development including best practices, security, configuration, integrations & coding patterns, and deployment. Use when managing Device Registry namespaces, device certs/CAs, fleet config, IoT SDK connectivity, or software updates, and other Azure IoT related development tasks. Not for Azure IoT Central (use azure-iot-central), Azure IoT Edge (use azure-iot-edge), Azure IoT Hub (use azure-iot-hub), Azure Defender For Iot (use azure-defender-for-iot).
Expert knowledge for Azure IoT Edge development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring EFLOW devices, DPS/X.509 provisioning, gateway/nested topologies, CI/CD deployments, or IoT Edge metrics/logs, and other Azure IoT Edge related development tasks. Not for Azure IoT Hub (use azure-iot-hub), Azure IoT (use azure-iot), Azure IoT Operations (use azure-iot-operations), Azure Stack Edge (use azure-stack-edge).
Generate various documents based on the current project or code, including thesis sections, project overviews, key issues, and resume project descriptions. Use when users ask to generate thesis sections, project overviews, technical challenges, or resume project descriptions. For onboarding documents for new colleagues (new-hire guides, architecture docs, code walkthroughs, onboarding), use project-docs.
Copy a PostHog endpoint (a saved HogQL/insight query exposed as an API route) to another project in the same organization, or duplicate it under a new name in the same project. Use when the user wants to duplicate an endpoint, promote an endpoint from staging to production, replicate an endpoint's query/variables/freshness config in another workspace, or clone an endpoint to iterate on it. Unlike feature flags and experiments, endpoints have NO native cross-project copy tool — this skill covers the read-then-recreate flow (endpoint-get then endpoint-create), the active-project switching it requires, name-collision checks, and the safe defaults (land unmaterialised in the target, verify with endpoint-run). Does not cover editing endpoint versions (see managing-endpoint-versions) or authoring a brand-new endpoint from scratch (see creating-an-endpoint).
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.