Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Expert knowledge for Azure Repos development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations, and coding patterns. Use for managing Git/TFVC repos, branch policies/PR checks, CodeQL/secret scanning, ELM sync, TFVC-to-Git migrations, and other Azure Repos development tasks. Not for Azure DevOps (use azure-devops), Azure Pipelines (use azure-pipelines), Azure Boards (use azure-boards), or Azure Artifacts (use azure-artifacts).
Highload blocks — HighloadBlockTable, compileEntity data classes, HLBLOCK_{id} user fields, hlblock links, iblock directory property, ORM events, hl_element_* rights. Use when creating HL dictionaries or reading/writing their records.
Expert-level blockchain, Web3, smart contracts, DeFi, and cryptocurrency development. Use when the user mentions Web3, smart contracts, DeFi, Ethereum, or Solidity, or when the task involves Blockchain Fundamentals, Web3 & DeFi, Smart Contract Security, or Gas Optimization.
Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+ files), complex multi-step workflows, iterative processing, or mentions efficiency/performance.
Expert guide for Electron development with Electron Vite and Electron Builder. Use when developing Electron applications, working with main/renderer processes, IPC communication, preload scripts, security configuration, native module handling, or build/distribution setup.
Expert blueprint for dedicated / headless multiplayer hosts: ENet/DTLS, authority validation, safe packet decode, matchmaker handoff, and health telemetry. Use when building authoritative servers, --headless hosts, or hardening host networking. Keywords: dedicated server, headless, ENet, DTLS, authority, safe_packet_decoder, multiplayer host, WebSocketMultiplayerPeer.
Use when building, configuring, or debugging enterprise Java applications with Spring Boot 3.x, microservices, or reactive programming. Invoke to implement WebFlux endpoints, optimize JPA queries and database performance, configure Spring Security with OAuth2/JWT, or resolve authentication issues and async processing challenges in cloud-native Spring applications.
Add OAuth authentication to MCP servers on Cloudflare Workers. Uses @cloudflare/workers-oauth-provider with Google OAuth for Claude.ai-compatible authentication. Prevents 9 documented errors including RFC 8707 audience bugs, Claude.ai connection failures, and CSRF vulnerabilities. Use when building MCP servers that need user authentication, implementing Dynamic Client Registration (DCR) for Claude.ai, or replacing static auth tokens with OAuth flows. Includes workarounds for production redirect URI mismatches and re-auth loop issues.
Use when diagnosing an unexplained failure in a Meteor 3 application before the failing layer or fix is known. Triggers on server crashes, client-only errors, stuck subscriptions, DDP or WebSocket disconnects, Minimongo/server data mismatches, hanging or flaky tests, slow builds, --inspect, console.log, .only, Playwright traces, Instrumentation lifecycle events, or requests to debug a Meteor app. Use this skill when evidence must distinguish Meteor tool, server, client, data, test, browser, mobile, or production boundaries. For test setup and authoring use meteor-testing; after confirming a domain cause, hand the repair to the owning skill.
Prepare and execute a Plannotator release—draft release notes with full contributor credit, bump versions across all package files, build in dependency order, and kick off the tag-driven release pipeline. Use this skill whenever the user mentions preparing a release, bumping versions, writing release notes, tagging a release, or publishing. Also trigger when the user says things like “let's ship”, “prep a release”, “what's changed since last release”, or “time to cut a new version”.
Full Sentry SDK setup for .NET. Use when asked to "add Sentry to .NET", "install Sentry for C#", or configure error monitoring, tracing, profiling, logging, or crons for ASP.NET Core, MAUI, WPF, WinForms, Blazor, Azure Functions, or any other .NET application.
System-level input polling, player movement control, and mobile on-screen controls in Decentraland. Covers inputSystem, InputModifier, PointerLock, PrimaryPointerInfo, and TouchScreenControls. Use when the user wants continuous key polling, WASD-controlled entities, to freeze the player during a cutscene, FPS-style cursor lock, multi-key combo patterns, or to hide/customize the mobile joystick, crosshair, or on-screen buttons. For event-driven clicks and hover on entities, see add-interactivity.
Animate objects in Decentraland scenes. Play GLTF model animations with Animator, create procedural motion with Tween, and chain sequences with TweenSequence. Use when the user wants to animate, move, rotate, scroll a texture, or create motion effects. Do not use for audio/video playback (see audio-video), player emotes (see player-avatar), authoring emote clips (see avatar-animations), or physics-driven motion (see player-physics).
Read real-time amplitude and 8-band frequency data from any AudioSource, AudioStream, or VideoPlayer entity in a Decentraland SDK7 scene with the AudioAnalysis component. Use when the user asks for music visualizers, beat reactivity, equalizers, or audio-reactive scenes. Do NOT use to play sound (see audio-video) or to detect player-emitted audio (this reads only entity-attached AudioSource/AudioStream/VideoPlayer audio).
Develop ComfyUI server-side V3 custom nodes (Python) using Comfy API v0_0_2/latest, schema-based inputs/outputs, ComfyExtension entrypoints, and UI preview helpers. Use when asked to create or update ComfyUI custom_nodes, V3 nodes, or Comfy API-based nodepacks.
Use when building an internal admin-facing AI agent in a Medusa project. These agents are operated by merchants and store operators — not customers. Covers data models, module service, agent runtime (tools, system prompt, streamText), streaming API routes (NDJSON), and admin UI chat extensions. Load for any internal agent type: store operations assistant, product audit, cohort analysis, customer service tooling for support staff, etc. Do NOT use for customer-facing agents (storefront chatbots, buyer-side assistants).
Run an edit, perform a real check, read the actual error, fix the root cause, and rerun until the check passes or the cap is hit. Use when you change code that has tests, a type checker, a build, or a runnable app, or before you claim any fix works. Invoke as /ds-verify-loop.
Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.
Expert patterns for adding multiplayer to single-player games including client-server architecture, authoritative server design, MultiplayerSynchronizer, lag compensation (client prediction, server reconciliation), input buffering, and anti-cheat measures. Use when retrofitting multiplayer, porting to online play, or designing networked gameplay. Trigger keywords: MultiplayerPeer, ENetMultiplayerPeer, SceneMultiplayer, MultiplayerSynchronizer, rpc, rpc_id, multiplayer_authority, client_prediction, server_reconciliation, lag_compensation, rollback.
Expert blueprint for Metroidvanias including ability-gated exploration (locks/keys), interconnected world design (backtracking with shortcuts), persistent state tracking (collectibles, boss defeats), room transitions (seamless loading), map systems (grid-based revelation), and ability versatility (combat + traversal). Use for exploration platformers or action-adventure games. Trigger keywords: metroidvania, ability_gating, interconnected_world, backtracking, map_system, persistent_state, room_transition, soft_locks.
Translate Cypher and Neo4j-style queries into direct HelixDB v3 Rust SDK requests. Use when the input contains Cypher, Neo4j, MATCH, OPTIONAL MATCH, WHERE, RETURN, ORDER BY, LIMIT, DISTINCT, MERGE, CASE, UNWIND, FOREACH, DETACH DELETE, IS NULL, or variable-length path patterns. When the target is Helix Cloud, always use helix-mcp first.
Miaoda (Spark/Miaoda) app development and hosting: app creation, local full-stack development, cloud generation and iteration, creative design (UI mockups / interactive prototypes / wireframes / landing pages / dashboards / slide decks / visual exploration), integration of AI capabilities, Feishu platform capabilities, or other external capabilities, log/Trace/monitoring metrics/PV/UV queries, environment variable management, app collaborators and collaboration permissions, app roles and members, and automation triggers (scheduled / record changes / Webhook / Feishu approval). Use when users want to develop or create a system, tool, platform, or app; develop locally or in the cloud; modify, deploy, publish, launch, or get a shareable link; build pages or websites with HTML and deploy them to Miaoda; design, create mockups, prototypes, wireframes, PPT/decks, or explore visuals; or mention Miaoda/Spark/Miaoda (app runtime domains such as *.aiforce.cloud), app databases, app file storage, open API Keys, visibility, app collaborators/development permissions, app roles/role members, production logs, API request volume, error counts, latency, traffic, environment variables, or setting up automation for Miaoda apps, including scheduled triggers or triggers after approval. Not responsible for ordinary cloud drive file uploads (lark-drive), Feishu document editing (lark-doc), or native slide creation (lark-slides).
Transform legacy codebases into AI-ready projects with Claude Code configurations. Use when (1) analyzing old projects to generate AI coding configurations, (2) creating CLAUDE.md, skills, subagents, slash commands, hooks, or rules for existing projects, (3) user wants to enable vibe coding for a codebase, (4) onboarding new team members with AI-assisted development, (5) user mentions "make project AI-ready", "generate Claude config", or "create coding standards for AI"
Use when choosing, evaluating, adopting, configuring, or debugging a package from Meteor's documented community catalog, or moving from a community package to a promoted core package such as roles. Triggers on community package recommendations, Atmosphere vs npm selection, Packosphere maintenance checks, jam:* helpers, Meteor.publish.once, Meteor.publish.stream, meteor-rpc, Wormhole, cluster, mail-preview, meteor add --search, or adopting a Git-hosted Atmosphere package. Use this skill when the user asks which maintained package fits or how its documented integration works. Route Meteor 2-to-3 package failures to migrate-to-meteor-3 and underlying core API design to its owning skill.
Use when configuring or tuning the Meteor 3 modern build stack: SWC transpiler, SWC-based minifier, modern @parcel/watcher, web-arch skipping in development, .meteorignore, and Rspack integration. Triggers on package.json "meteor": { "modern": true }, .swcrc, swc.config.js, [Transpiler] Used Babel Fallback logs, rspack.config.js, rspack.config.ts, defineConfig from @meteorjs/rspack, Meteor.compileWith* helpers, Meteor.extendConfig, Meteor.extendSwcConfig vs Meteor.replaceSwcConfig, Meteor.splitVendorChunk, Meteor.persistDevFiles, Meteor.disablePlugins, Meteor.enablePortableBuild, HtmlRspackPlugin customization, RSPACK_DEVSERVER_PORT, TOOL_NODE_FLAGS, pnpm workspaces, Rspack 2, skeleton selection, PWA, Workbox and service-worker build setup. Use this skill when asked about SWC vs Babel or Rspack configuration. Route existing-app bundler migration to migrate-to-rspack, Blaze PWA scaffolding to meteor-blaze, declarations to meteor-typescript, and jam:offline data to meteor-community-packages.
This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token and cost estimation, choosing between single-agent and multi-agent at the project level, structured output design for downstream parsing, and structuring agent-assisted iteration. Use this when the unit of work is a whole project or a multi-stage pipeline. Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization.
Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality. Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, context augmentation, similarity search, or embedding-based indexing.
Ruby on Rails performance and maintainability optimization guidelines for building backend APIs and frontend web applications. This skill should be used when writing, reviewing, or refactoring Ruby on Rails code to ensure optimal patterns for controllers, models, ActiveRecord queries, caching, views, API design, security, and background jobs. Triggers on tasks involving Rails controllers, ActiveRecord queries, migrations, Turbo/Hotwire, API endpoints, background jobs, or Rails performance improvements.
Builds, optimizes, and debugs cross-platform mobile applications with React Native and Expo. Implements navigation hierarchies (tabs, stacks, drawers), configures native modules, optimizes FlatList rendering with memo and useCallback, and handles platform-specific code for iOS and Android. Use when building a React Native or Expo mobile app, setting up navigation, integrating native modules, improving scroll performance, handling SafeArea or keyboard input, or configuring Expo SDK projects.
Create and manage interactive Kanban boards with Syncfusion Angular component. Use this skill when you need to build workflow visualization tools with drag-and-drop cards, swimlanes, columns, and real-time data binding. Covers setup, configuration, events, properties, methods, and best practices for implementing task management and project tracking interfaces
Telegram Bot development skill using the grammY framework, TypeScript, Drizzle ORM, Vitest testing, and Biome linting, deployed to Cloudflare Workers with a D1 database. Use for: (1) creating new Telegram Bot projects; (2) adding commands or features to existing Bots; (3) configuring Cloudflare Workers deployment; (4) setting up Drizzle + D1 database integration; (5) writing Bot test cases; (6) configuring Git hooks and GitHub Actions CI/CD
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
Event-driven interactivity for Decentraland entities. Covers pointerEventsSystem, proximity events, trigger areas (enter/exit zones), raycasting, and one-shot key presses on entities. Use when the user wants clickable objects, hover highlights, proximity-based interactions, detecting when a player enters a zone, E/F key actions on an entity, or ray-hit detection. For system-level polling (held keys, WASD movement, cursor lock, InputModifier, action bar), see advanced-input. For screen-space UI buttons, see build-ui.
Advanced rendering in Decentraland scenes. Billboard, TextShape, PBR materials, GltfNodeModifiers, and VisibilityComponent. Use when the user wants billboards, floating labels, 3D text, material effects, glow, transparency, or model node control. Do NOT use for screen-space UI (see build-ui) or loading 3D models (see add-3d-models).
Auto-generate and run a per-repo Claude Code agent team. Probes the current repo (build/CI/env manifests, agent launchers, slash commands, spec dirs) and writes `.claude/agents/{role}.md` subagent definitions for relevant roles from a library (coder, reviewer, auditor, tester, documenter, release, architect, researcher, spec-keeper, fact-checker, web-ux), plus a `.claude/agent-team.md` workflow doc. Use when (1) `/agent-team init` creates the team for the current repo, (2) `/agent-team update` refreshes it after project changes, (3) `/agent-team {task}` runs a task with the team (spawning teammates, driving orchestration, and stopping at user gates), or (4) `/agent-team reflect` reviews the session’s agents and proposes refactors and new roles. Roles include a frontmatter `version:` for staleness detection. Triggers include “/agent-team,” “spin up a team,” “auto-create agents,” “agent team for this repo,” “team-on-task,” and “reflect on the agents.”
Add sound effects, music, audio streaming, and video players to Decentraland scenes with AudioSource, AudioStream, and VideoPlayer. Use when the user wants sound, music, video screens, radio, live streams, or media playback. Do not use for player emotes (see player-avatar) or screen-space UI sounds (sounds attach to entities, not UI).
This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when the user's request has multiple valid interpretations that need clarification.
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
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.