Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
UI5 development best practices and coding standards derived exclusively from official SAP UI5 guidelines. Use when writing UI5 applications to ensure modern, maintainable code following SAP standards. Covers: async module loading (sap.ui.define, ES6 imports, core:require), ComponentSupport initialization, data binding with OData types, i18n management, CSP compliance (no inline scripts), TypeScript event types (UI5 >= 1.115.0), MCP tooling (get_api_reference, run_ui5_linter), CAP integration patterns, and form creation rules (never SimpleForm, always Form with ColumnLayout). Keywords: ui5 coding standards, async loading, sap.ui.define, data binding, odata types, i18n translation, CSP no inline scripts, TypeScript event handlers, Button$PressEvent, ui5 linter, API reference, ComponentSupport, form layout, ColumnLayout, CAP integration, cds watch
Virtual memory skill for paging, page tables, and TLB. Use when explaining page faults, multi-level page tables, TLB behavior, or virtual vs physical addressing. Activates on queries about virtual memory, page table, TLB, page fault, mmap paging, or x86-64 paging.
Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding with conversational AI. Supports image URLs and base64 encoded images for multimodal interactions.
Submit GitHub issues, feature requests, bug reports, product suggestions, and feedback to the ZenMux repository (ZenMux/zenmux-doc). Use this skill whenever the user wants to: report a bug, request a feature, suggest a product improvement, give feedback, request support for a new model or provider, report a documentation issue, or share their experience. Trigger on phrases like: "submit issue", "file a bug", "feature request", "report a problem", "I have an idea", "提交issue", "提反馈", "功能建议", "报告bug", "产品建议", "提个需求", "新增模型", "新增供应商", "文档问题", "我想提个建议", "提交建议". If the user is describing a ZenMux problem or product idea and would benefit from submitting it formally, proactively offer to help them create an issue.
This skill should be used when the user asks about "LLM gateway", "Bankr LLM", "LLM credits", "top up credits", "auto top-up", "llm.bankr.bot", "Claude Code gateway", "OpenClaw setup", "Cursor setup", "OpenCode setup", "LLM models", or any LLM gateway configuration or usage topic.
Provides Base network configuration including RPC endpoints, chain IDs, and explorer URLs. Use when connecting wallets, configuring development environments, or setting up Base Mainnet or Sepolia testnet. Covers phrases like "Base RPC URL", "Base chain ID", "connect to Base", "add Base to wallet", "Base Sepolia config", "Base explorer URL", "what network is Base", or "Base testnet setup".
Device tree skill for Linux hardware description. Use when writing DTS/DTSI, bindings, overlays, phandles, or debugging OF platform probe failures. Activates on queries about device tree, DTS syntax, phandle, devicetree bindings, DT overlay, or OF graph.
Formatting patterns for the Dinero.js money library. Use when displaying monetary values to users, formatting prices with currency symbols, handling locale-specific number formats, or working with non-decimal currencies. Triggers on toDecimal, toUnits, toSnapshot calls, or Intl.NumberFormat usage with Dinero objects.
.NET and ASP.NET Core security patterns. Covers Identity, authentication, dependency auditing, secure coding practices, and OWASP for .NET ecosystem. USE WHEN: user works with "C#", ".NET", "ASP.NET Core", "Entity Framework", asks about ".NET vulnerabilities", "NuGet security", ".NET authentication", "Blazor security" DO NOT USE FOR: general OWASP concepts - use `owasp` or `owasp-top-10` instead, Java/Python security - use language-specific skills
Eino orchestration with Graph, Chain, and Workflow. Use when a user needs to build multi-step pipelines, compose components into executable graphs, handle streaming between nodes, use branching or parallel execution, manage state with checkpoints, or understand the Runnable abstraction. Covers Graph (directed graph with cycles), Chain (linear sequential), and Workflow (DAG with field mapping).
Multi-provider email sending for Cloudflare Workers and Node.js applications. Build transactional email systems with Resend (React Email support), SendGrid (enterprise scale), Mailgun (developer webhooks), or SMTP2Go (reliable relay). Includes template patterns, webhook verification, attachment handling, and error recovery. Use when sending emails via API, handling bounces/complaints, or migrating between providers.
Analyze and implement purposeful UI animations for Next.js + Tailwind + React projects. Use when user asks to add animations, enhance UI motion, animate pages/components, or improve visual feedback. Triggers on "add animations", "animate UI", "motion design", "hover effects", "scroll animations", "page transitions", "micro-interactions".
Expert blueprint for idle/clicker games including big number handling (mantissa + exponent system), exponential growth curves (cost_growth_factor 1.15x), generator systems (auto-producers), offline progress calculation, prestige systems (reset for permanent multipliers), number formatting (K/M/B suffixes, scientific notation). Use for incremental games, idle games, or cookie clicker derivatives. Trigger keywords: idle_game, big_number, exponential_growth, generator_system, offline_progress, prestige_system, number_formatting.
This skill should be used when Claude needs to build or reuse a reusable Make API-call shell by discovering the correct app-specific Make an API Call module, resolving or requesting the right connection, explicitly setting the scenario interface, running the scenario, and using that shell as the retrieval transport for email, CRM, tickets, and similar SaaS systems.
Instrument a Backstage frontend plugin with analytics events using the Backstage Analytics API. Use this skill when adding, reviewing, or extending event capture (`captureEvent`, `AnalyticsContext`) in plugin components, deciding whether an interaction warrants an event, or writing tests for analytics behavior.
Use when a Unity 6.3 task involves character animation or cameras: Mixamo or mocap humanoid import and retargeting, Animator Controllers, blend trees, layers and avatar masks, root motion, foot sliding, IK and Animation Rigging, Playables, Timeline cutscenes, custom tracks and markers, Cinemachine 3 cameras, camera jitter, flipping blends or cameras hitting walls; or when clips import with no animation, a character T-poses, an idle drifts, feet slide or the head misses its aim target.
Spring Boot best practices and patterns. Use when creating controllers, services or repositories, or when the user asks about Spring Boot layering, wiring, configuration or exception handling. For JPA and Hibernate behaviour, use jpa-patterns instead.
Symfony UX frontend stack -- decision tree and orchestrator for choosing between Stimulus, Turbo, TwigComponent, LiveComponent, UX Icons, and UX Map. Use when the user is unsure which tool fits, wants to combine multiple UX packages, or asks a general frontend architecture question in Symfony. Also trigger when the user asks "which UX package should I use", "how to make this interactive", "should I use Stimulus or LiveComponent", "how to structure my Symfony frontend", "what is the difference between Turbo and LiveComponent", "should this be a Frame or a LiveComponent", "how do these UX packages work together", "what is the Symfony way to do frontend". Do NOT trigger when the user clearly names a specific tool (stimulus, turbo, twig-component, live-component, ux-icons, ux-map) -- defer to the specialized skill instead.
Guide for implementing Syncfusion Blazor ListView component. Use this when building list-based interfaces with data binding, filtering, grouping, virtual scrolling, selection modes, and custom templates. Covers installation, templating, event handling, and advanced patterns.
Build interactive timeline components that display events and milestones sequentially. Use SfTimeline with alignment controls, custom items, and event handlers. This skill covers timeline configuration and customization for creating visual timelines in Blazor applications.
Lead workflow for developing vgpu features and Blender assets with the repository's subharness specialists. Use for agent-based research, API design, implementation, shaders, materials, simulations, or ImageGen-guided asset iteration, and when the human mentions the agent flow or subharness team.
Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension architecture, manifest v3, content scripts, popup UIs, monetization strategies, and Chrome Web Store publishing. Use when: browser extension, chrome extension, firefox addon, extension, manifest v3.
Add headless Chrome automation with Puppeteer/Playwright on Cloudflare Workers. Use when: taking screenshots, generating PDFs, web scraping, crawling sites, browser automation, or troubleshooting XPath errors, browser timeouts, binding not passed errors, session limits, page.evaluate __name errors, or waitForSelector timeout issues.
Build durable workflows with Cloudflare Workflows (GA April 2025). Features step.do, step.sleep, waitForEvent, Vitest testing, automatic retries, and state persistence for long-running tasks. Prevents 12 documented errors. Use when: creating workflows, implementing retries, or troubleshooting NonRetryableError, I/O context, serialization errors, waitForEvent timeouts, getPlatformProxy failures.
Expert blueprint for platformer games including precision movement (coyote time, jump buffering, variable jump height), game feel polish (squash/stretch, particle trails, camera shake), level design principles (difficulty curves, checkpoint placement), collectible systems (progression rewards), and accessibility options (assist mode, remappable controls). Based on Celeste/Hollow Knight design research. Trigger keywords: platformer, coyote_time, jump_buffer, game_feel, level_design, precision_movement.
Use when working with multi-item data, batches, paginated APIs, rate-limited APIs, fan-out across multiple branches, anything that needs to "do this for each", or any time the user mentions looping, iterating, batching, paging, parallelism, or "loop over items". Triggers on "loop", "iterate", "for each", "batch", "page through", "paginate", "rate limit", "process all", "fan-out", "parallel branches", "concurrency", or any node that should run once vs once-per-item.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Reshape the commits a branch carries on top of its target branch into a clean, logical sequence without changing the final committed tree. Use when a branch needs presentable history before review or merge, when iterative work left fixups, WIP commits, or interleaved refactors, when another skill needs clean commits, or when the user says "recommit" or asks to tidy the git history.
Generate JSON-LD structured data for AEM Edge Delivery Services pages. Analyzes page content and metadata to determine the appropriate schema.org types, extracts relevant properties, and produces validated JSON-LD snippets ready for implementation in head.html or scripts.js. Use when adding rich results support, improving search appearance, or auditing existing structured data.
Guide to implementing Syncfusion Blazor ProgressBar components in Blazor applications. Use when displaying progress indicators, loading states, task completion status, or file upload progress. Covers linear and circular progress bars, indeterminate loaders, buffer states, and progress tracking. Ideal for visual feedback during operations, showing completion percentages, and any scenario requiring visual progress indicators
When you want to integrate an external tool, API, MCP server, or service into a project — the wizard walks you through auth, config, env vars, client wrapper code, example usage, and an optional smoke test. Scoped to Next.js and Rails projects. Interactive Q&A — starts with the tool name, asks structured questions until the integration is specified, then scaffolds files. Examples — Stripe, Kit, Sanity, Notion, Neon, Supabase, Resend, Postmark, Twilio, Anthropic, OpenAI, Vercel Blob, custom internal APIs. For MCP servers, also handles the .mcp.json wiring. Triggers on "/toolify," "integrate X," "add X to this project," "wire up X," "set up the X integration," "hook up X," "connect X," "add MCP for X." Part of the -ify trifecta (skillify / toolify / loopify). NOT for adding new SKILL.md files — that's skillify. NOT for cron/agent loops — that's loopify.
Guide for Vercel AI SDK v5 implementation patterns including generateText, streamText, useChat hook, tool calling, embeddings, and MCP integration. Use when implementing AI chat interfaces, streaming responses, tool/function calling, text embeddings, or working with convertToModelMessages and toUIMessageStreamResponse. Activates for AI SDK integration, useChat hook usage, message streaming, or tool calling tasks.
Use when you need to verify Java performance optimizations by comparing profiling results before and after refactoring — including baseline validation, post-refactoring report generation, quantitative before/after metrics comparison, side-by-side flamegraph analysis, regression detection, or creating profiling-comparison-analysis and profiling-final-results documentation. This should trigger for requests such as Verify performance fix; Verify the performance; Verify the memory; Verify the threading; Compare before and after profiling results; Check for performance regressions after refactoring. Part of Plinth Toolkit
Transloco i18n best practices for Angular. Covers runtime translation, lazy-loaded translation files per route, and test mocking. Activates when working with @jsverse/transloco. Do not use for ngx-translate or i18next. Install alongside angular-best-practices for full coverage.
This skill should be used when building the async job workflow, implementing polling loops, handling job status transitions, processing rich data, managing conversation threads, or understanding the full submit-poll-complete lifecycle of the Bankr Agent API.
A complete development guide for Baidu Maps JSAPI WebGL (BMapGL), covering map initialization, overlays, layers, events, styles, and performance optimization to build high-performance 3D map applications in one place. Triggers automatically when users mention BMapGL, Baidu Maps, jsapi-gl, or related map development needs.
MUST be used whenever creating an AtlasTool (client-side tool) for an Atlas agent. Do NOT manually write AtlasTool definitions or wire them into useAtlasChat — this skill handles the TypeBox schema, execute function, and hook wiring. This includes tools that fetch data, render UI, call APIs, show charts, query local state, or perform any browser-side action. Triggers: AtlasTool, client tool, add tool, create tool, new tool, tool definition, agent tool.
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Integrate Internet Identity authentication. Covers passkey, OpenID (Google, Apple, Microsoft), and organization SSO sign-in with @icp-sdk/auth, the SSO domain check (getSsoStatus), identity attributes (verified email, name) and their backend verification, sessions shared across subdomains, alternative origins, and the /.well-known/ii-app-metadata document. Use when adding sign-in, login, auth, passkeys, SSO, or Internet Identity to a frontend or canister. Do NOT use for wallet integration or ICRC signer flows (use wallet-integration) or for an agent or CLI signing in as a user (use agent-web-identity)
Use when the user wants to step through a feature's checkpoints chronologically, pausing at each step to ask questions. Triggers on phrases like "replay <feature>", "walk me through how X was built", "show me the journey of", "step me through how Y was implemented", and "replay the last week"
This skill should be used when the user needs a "sharded counter", "distributed counter", to "count likes / views at scale", handles a "high-write counter" or "hot counter contention", asks about "approximate counting", "real-time counts", or "HyperLogLog". It gives the recipe for absorbing write-heavy counting without a single hot row. Use it whenever one row/key takes concurrent increments faster than it can serialize them, even if the user doesn't say "sharded counter".
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.