Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Runs a brutal, revenue-first SEO teardown of a site and its codebase, fixes fatal crawl, programmatic, layout, authority, and AI-visibility blockers in a fix PR, and ships a revenue-ordered seo/roast-roadmap.md (plus an optional client deck). Use when the user says “roast my SEO,” “why don't we rank,” “audit my site,” “SEO teardown,” asks why traffic or signups are flat, or wants an SEO review that ends in fixes instead of a checklist
Not tax advice and not a filed return. Convert currencies to/from Israeli New Shekel (NIS/ILS) using Bank of Israel official representative rates (shaar yatzig). Use when user asks to convert shekels, NIS, ILS, asks about exchange rates, "shaar yatzig" (representative rate), or needs currency conversion for Israeli tax or business purposes, including which date's rate applies to foreign-currency income, to VAT on a payment from a foreign client, or as the customs rate for import VAT. Covers the official Bank of Israel published currencies (14 currencies) with current and historical (tax-date) rates. Do NOT use for cryptocurrency or unofficial money exchange rates.
Use when the user asks to see something rather than read about it - "show me", "let me see it", "what does it look like", "give me options", or any moment you are about to describe a layout, a plan, a comparison or a design in prose. Renders it as a self-contained HTML page and opens it in the browser, in front of them.
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.
Implement Syncfusion WPF SfAccordion for collapsible and expandable panel layouts. Use this when working with accordion controls, expandable panels, or collapsible section navigation in WPF. Covers populating items declaratively or via data binding, selection modes (One/OneOrMore/ZeroOrOne/ZeroOrMore), programmatic selection, appearance customization (AccentBrush, HeaderTemplate, ContentTemplate), and theming with SfSkinManager.
Implement Syncfusion WPF SfAIAssistView for AI chat and conversational assistant interfaces. Use this when building AI assistant UIs, message threads with AI responses, or integrating OpenAI/SemanticKernel in WPF. Covers typing indicators, suggestions, input/response toolbars, stop-responding features, conversation history, input placeholder text, empty view templates, and PromptRequest events using Syncfusion.SfChat.Wpf.
Implements the Syncfusion WPF ColorPickerPalette control for color selection from themed and standard color palettes. Use this when adding color pickers with predefined palettes, customizing color options, or handling color selection events in WPF applications. Covers setup, color management, appearance customization, and interaction patterns.
Implement Syncfusion WPF ColorPicker for color and gradient selection. Use this skill whenever users need to add color picking functionality, select solid colors, create linear/radial gradients, customize palettes, apply themes, or handle color-changed events in WPF applications. Covers XAML and C# implementations.
Implement Syncfusion WPF Ribbon component for modern desktop applications. Use this skill when creating ribbon interfaces in WPF with tabs, groups, buttons, menus, and galleries. Covers advanced features like application menus, backstage views, state persistence, multi-document ribbon merge, keyboard accessibility, touch support, and ribbon customization.
Create and configure WPF TileView controls for organizing and displaying content in tile layouts. Use this skill whenever users need to implement tile-based layouts, arrange tiles in matrix positions, add drag-drop functionality to tiles, maximize/minimize tile items, customize tile headers and appearance, bind data to tile views, or create responsive dashboard-like layouts. Essential for building WPF applications with interactive tiled interfaces.
Production-ready Tailwind CSS patterns for common website components: responsive layouts, cards, navigation, forms, buttons, and typography. Includes spacing scale, breakpoints, mobile-first patterns, and dark mode support. Use when building UI components, creating landing pages, styling forms, implementing navigation, or fixing responsive layouts.
Guide for editing speech-led videos where spoken delivery or conversation drives the cut — single-speaker talking-head / 口播, two- or multi-speaker interview / 访谈, video podcast, lecture, tutorial, course, and similar formats. Load before analyzing, planning, or performing non-trivial edits of those formats, including speech cleanup (剪口播 / 口播剪辑 / 去口癖 / clean up fillers / smooth speech), pause or repeated-take removal, motion graphics layered onto the footage (口播加 MG / 加动画), B-roll (加 B-roll / add B-roll), music, or captions. For motion graphics specifically, use this together with the active Motion Graphics skill/workflow available in the current ChatCut environment — this skill adds speech-specific guidance (rhythm-aware timing, frame-aware placement, subject/caption protection, placement verification).
Design a structured lesson plan for any subject, audience, or format. Use when asked to write a lesson plan, course outline, teaching session, workshop curriculum, or training module. Produces a complete lesson plan with learning objectives, activities, timing, assessment, and differentiation guidance.
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.
A quantitative signal-scanning and position-sizing tool based on the original Turtle Trading system. Uses the longbridge CLI to retrieve market data for A-shares, Hong Kong stocks, US stocks, and Singapore stocks, and automatically calculates ATR (N value), breakout signals (System 1 / System 2), stop-loss prices, add-on points, and Unit position size. Use when users mention 海龟, turtle, 海龟交易, 海龟信号, turtle signal, turtle trading, ask about breakout signals, ATR, N value, Unit position, stop-loss prices, add-on points, S1/S2 signals, 20-day highs/lows, 55-day breakouts, or request scanning watchlists/indexes for trading signals using the turtle system. Also triggers when users say “扫描突破信号”, “帮我算Unit”, “海龟止损”, “海龟系统分析”, or any variation combining a stock name/code with “海龟”. **Suitable for:** - Scanning for breakout signals after each day's close (20-day/55-day high/low breakouts) - Calculating ATR, stop-loss prices, and add-on points for one or multiple stocks - Calculating suitable Unit position size based on account equity - Checking whether existing positions meet exit or add-on conditions - Scanning watchlists/index constituents for Turtle signals **Not suitable for:** - Fundamental analysis (the Turtle system is purely technical) - Predicting price direction - Automatic order placement (outputs signals only; users trade themselves) - Opening short positions in A-shares, Hong Kong stocks, or Singapore stocks
Generate a series of Xiaohongshu infographics with 10 visual styles and 8 layouts. Split the content into 1–10 cartoon-style images, optimized for Xiaohongshu engagement. Use when users mention “Xiaohongshu images,” “XHS images,” “Xiaohongshu seeding,” or need Chinese social media infographics.
Orchestrated, holistic UX review of a screen, flow, or component. Establishes context once, auto-runs the always-relevant lenses (usability, microcopy, dark patterns), offers the context-dependent ones (accessibility, aesthetics, IA, mobile, visual foundations), and returns one prioritized report. Trigger when the user asks for a full design review, "review my UI/screen/flow", "is this good UX", "audit this design", or general design feedback — but NOT when they name a single specific lens.
Transcribe audio files to text via POST /audio/transcriptions. Covers supported models (Parakeet, Whisper, Wizper, Scribe, xAI STT), accepted containers (wav/flac/m4a/aac/mp4/mp3/ogg/webm), response formats (json/text only), per-model timestamps (word/segment/char), language hints, the 25 MB cap, and per-audio-second pricing. OpenAI-compatible multipart
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.
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.
Use this skill when the agent needs to complete Xiaohongshu login, cookie validation, video upload, or image-and-text publishing through the installed `sau` CLI. This skill applies to environments where `social-auto-upload` is already installed and the `sau` command is available. Prefer this skill for a stable command-based Xiaohongshu workflow rather than reading uploader source code first.
Use when Java implementation work should be guided by Test-Driven Development, including maintaining a test list, choosing the next behavior, writing a failing test first, implementing only enough production code to pass, and refactoring while keeping tests green. This should trigger for requests such as Apply TDD; Use test-driven development; Drive this Java change with tests; Write the failing test first; Red-green-refactor this feature. Part of Plinth Toolkit
Add a new model to a live LiteLLM proxy. Walks the user through picking a provider, entering the deployment name and credentials, calls POST /model/new, then test-calls the model to confirm it routes correctly. Use when the user wants to add, register, deploy, or configure a new model on a LiteLLM proxy instance.
Master the Amazon Associates affiliate program with commission optimization, link strategies, compliance requirements, and monetization best practices. Use when implementing affiliate marketing, creating product reviews, optimizing conversions, or building Amazon affiliate content.
Bans the 43 tells of a vibecoded website (purple gradient on black, indigo Tailwind buttons, bento grid, liquid glass, sparkles icon, fake counters, "Most popular" pricing, the "Create Next App" tab, no legal pages...) while Claude builds or reviews a site, so it looks made by a human. Use when building, redesigning or reviewing a website, landing page or web app UI, or when the user types /anti-vibecode, "vibecodé", "ça fait IA", "looks AI generated".
Load this skill whenever the project contains dynamic content updates, status messages, alerts, notifications, loading indicators, or any use of aria-live, role="status", role="alert", or role="log". Under no circumstances add or modify live-region markup without applying these rules. Prioritize correct politeness levels and avoid redundant announcements. Never use a fixed-delay clear-and-reinsert workaround — no standard guarantees it works.
Maintain profiler performance cases containing only JSONL under ascend-kernel's csrc/ops/<op>/test. Collect data with torch_npu.profiler (fixed warmup=5, active=5), summarize Total Time(us) from ASCEND_PROFILER_OUTPUT/op_statistic.csv, and output a standardized Markdown comparison report (custom operator vs. benchmark) with a DType column. Do not generate perf_cases.json or *_profiler_results.json. See examples/layer_norm_profiler_reference/ for a reference implementation.
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 Attestation development, including troubleshooting, best practices, security, configuration, and deployment. Use when validating attestation tokens, authoring policies, enforcing SGX/TPM baselines, configuring private endpoints, and for other Azure Attestation development tasks. Not for Azure Confidential Computing (use azure-confidential-computing), Azure Virtual Enclaves (use azure-virtual-enclaves), Azure Dedicated HSM (use azure-dedicated-hsm), or Azure Key Vault (use azure-key-vault).
Expert knowledge for Azure Cloud Hsm development, including troubleshooting, best practices, limits and quotas, security, and integrations and coding patterns. Use when configuring Cloud HSM authentication/networking, routing logs, managing PKCS#11 keys/certs, handling capacity/algorithm limits, or performing other Azure Cloud Hsm-related development tasks. Not for Azure Dedicated HSM (use azure-dedicated-hsm), Azure Key Vault (use azure-key-vault), or Azure Payment Hsm (use azure-payment-hsm).
Expert knowledge for Azure AI Custom Vision development, including best practices, decision-making, limits and quotas, security, integrations, coding patterns, and deployment. Use for exporting Custom Vision models, calling prediction APIs, using ONNX/TensorFlow, managing CMK/RBAC, Smart Labeler, and other Azure AI Custom Vision development tasks. Not for Azure AI Vision (use azure-ai-vision), Azure AI services (use microsoft-foundry-tools), Azure Machine Learning (use azure-machine-learning), or Azure AI Foundry Local (use microsoft-foundry-local).
Expert knowledge for Azure Network Function Manager development, including security and configuration. Use when setting up NF Manager prerequisites, resource groups, managed identities, role assignments, or secure NF access, and for other Azure Network Function Manager development tasks. Not for Azure Firewall Manager (use azure-firewall-manager), Azure Virtual Network Manager (use azure-virtual-network-manager), Azure Virtual Network (use azure-virtual-network), or Azure Virtual WAN (use azure-virtual-wan).
Expert knowledge for Azure Operator Nexus development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, and deployment. Use when managing Nexus cluster templates, network fabric (BGP/ACLs/QoS), RBAC/Key Vault, bare metal, or upgrades, and for other Azure Operator Nexus-related development tasks. Not for Azure Operator Insights (use azure-operator-insights), Azure Operator Service Manager (use azure-operator-service-manager), Azure Networking (use azure-networking), or Azure Virtual Network (use azure-virtual-network).
Expert knowledge for Azure Red Hat OpenShift development, including troubleshooting, best practices, decision making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when sizing ARO clusters, configuring HCP/VNet topology, Entra/OIDC identity, ACR/Key Vault access, or SDN‑OVN/HCP upgrades, and for other Azure Red Hat OpenShift development tasks. Not for Azure Kubernetes Service (AKS) (use azure-kubernetes-service), Azure Container Apps (use azure-container-apps), Azure Container Instances (use azure-container-instances), or Azure Stack Edge (use azure-stack-edge).
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.