Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
Use this skill when working with tilemaps in Phaser 4. Covers loading Tiled JSON maps, creating tilemap layers, tile collision, dynamic tiles, tile properties, and tilemap camera culling. Triggers on: Tilemap, Tiled, tilemap layer, tile collision, tile properties.
Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration. The only SDK supporting image generation (ai.createImageModel + generateImage). Text via ai.createModel with groups cloudbase, the legacy hunyuan-v3 / hunyuan-exp, or custom-*; model ids (e.g. deepseek-v4-flash, glm-5, kimi-k2.6) go in the `model` field of generateText/streamText. MUST run two-step preflight before code — see body. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).
Apply SLDS-compliant UI using the correct blueprints, styling hooks, utility classes, and icons. Use when building any UI that needs SLDS, choosing between Lightning Base Components and SLDS Blueprints, applying styling hooks for theming, using utility classes for layout and spacing, or selecting icons. Triggers include "build a modal", "create a form", "data table", "SLDS styling", "style with hooks", "add an icon".
Generates EventCatalog documentation files (systems, services, agents, events, commands, queries, domains, flows, channels, containers, ADRs, data products, entities, diagrams) with correct frontmatter, folder structure, and best practices. Use when the user asks to "document a system", "document a service", "document an agent", "document an AI agent", "create EventCatalog files", "add an event to the catalog", "document my architecture", "generate catalog documentation", "create documentation for my microservice", "document a database", "create an ADR", "document a data product", or "document an entity".
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution
Starting point for any Dodo Payments integration, covering Merchant of Record basics, SDK installation and client setup, test and live environments, API keys, and the canonical checkout-to-webhook flow. Use when starting a new integration, initializing the dodopayments client, choosing an architecture, or unsure which Dodo Payments skill applies.
Build assistant-ui chat experiences for Expo and bare React Native with `@assistant-ui/react-native` and `@assistant-ui/ai-sdk`. Use when setting up an absolute mobile chat endpoint, `AssistantRuntimeProvider`, `useChatRuntime`, `AssistantChatTransport`, native `ThreadPrimitive`, `ComposerPrimitive`, `MessagePrimitive`, thread lists, attachments, React Native styles, `Metro` `withAui` for a `"use generative"` toolkit, local or remote thread adapters, or migrating a web chat surface to iOS and Android. Route here when a relative API URL fails on device, a native primitive lacks runtime state, `Metro` does not compile a toolkit, or web Elements are being used in a native app. Route web setup and DOM primitive work to `../setup/SKILL.md` and `../primitives/SKILL.md`.
Creative coding skills for Claude Code, claude.ai and Cowork. Motion, micro-interactions and design systems across Web (GSAP, Motion, Three.js, CSS), Android (Jetpack Compose) and Apple (SwiftUI). Proposes an interaction thesis you approve before it writes any code. Anti-AI-slop.
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
Catalyst Signals — event-driven architecture platform for near-instantaneous communication between decoupled applications. Supports Zoho publishers, Catalyst publishers, custom publishers, webhooks, functions, circuits, event filtering, transformation, batch/scheduled dispatch, and retry policies. Trigger on 'Signals', 'event bus', 'publisher', 'event-driven', 'webhook target', 'dispatch policy', 'event transformation', 'rule filter', or 'event ordering'. Console-only service — no SDK or programmatic API.
Catalyst SmartBrowz — browser automation and document generation service. Includes Headless (connect to remote Chrome/Firefox with Puppeteer/Playwright/Selenium), Browser Logic (serverless functions for browser tasks in Java/Node.js), PDF & Screenshot (generate visual documents from HTML/URL/Template), Templates (design dynamic content templates), Browser Grid (parallel headless browsers with auto-scaling, Early Access), and Dataverse (data scraping APIs). Trigger on 'SmartBrowz', 'headless browser', 'Headless Browser', 'Puppeteer', 'Selenium', 'Playwright', 'Browser Logic', 'PDF generation', 'screenshot', 'PDF/Screenshot generation', 'PDF & Screenshot', 'browser automation', 'Browser Grid', or 'web scraping'. Console + SDK (Java/Node.js/Python for PDF/Screenshot + Browser Grid) + CLI (for Browser Logic functions).
Use this skill when learning about new features, game objects, components, and rendering capabilities added in Phaser 4. Covers Filters, RenderNodes, CaptureFrame, Gradient, Noise, SpriteGPULayer, TilemapGPULayer, Lighting component, RenderSteps, and new tint modes. Triggers on: new in v4, Phaser 4 features, RenderNode, SpriteGPULayer, CaptureFrame, Gradient game object, Noise game object, new tint modes. For migrating v3 code to v4, see the v3-to-v4-migration skill instead.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies
Add a new gameplay feature to an existing browser game following its architecture patterns. Use when the user says "add a feature", "add double-jump", "add a power-up", "add a leaderboard", or describes a specific game mechanic to implement. Do NOT use for visual-only changes (use design-game) or replacing shapes with sprites (use add-assets).
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through diagnosing the failure via OPENCLI_DIAGNOSTIC, patching the adapter, and retrying. Works with any AI agent.
Retrieves MLflow traces using CLI or Python API. Use when the user asks to get a trace by ID, find traces, filter traces by status/tags/metadata/execution time, query traces, or debug failed traces. Triggers on "get trace", "search traces", "find failed traces", "filter traces by", "traces slower than", "query MLflow traces".
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Creative coding skills for Claude Code, claude.ai and Cowork. Motion, micro-interactions and design systems across Web (GSAP, Motion, Three.js, CSS), Android (Jetpack Compose) and Apple (SwiftUI). Proposes an interaction thesis you approve before it writes any code. Anti-AI-slop.
OmniStudio OmniScript creation and validation with 120-point scoring. Use when building guided digital experiences, multi-step forms, or interactive processes that orchestrate Integration Procedures and Data Mappers. TRIGGER when: user creates OmniScripts, designs step flows, configures element types, or reviews existing OmniScript configurations. DO NOT TRIGGER when: building FlexCards (use sf-industry-commoncore-flexcard), creating Integration Procedures directly (use sf-industry-commoncore-integration-procedure), or analyzing dependencies (use sf-industry-commoncore-omnistudio-analyze)
Triage GitHub issues, review contributor pull requests, diagnose CI, and prepare explicitly requested releases for VoiceStudio's Electron desktop app and Python backend. Use for repository maintenance work, not ordinary VoiceStudio audio generation.
Use when Jetpack Compose code reads scroll, animation, gesture, or other frame-rate State in composition, passes changing values across composable boundaries, uses value-form layout/draw modifiers, or back-writes observable state from a later phase into one that's already run.
Deploy, import, interact with, and monitor smart contracts using Circle Smart Contract Platform APIs. Supports bytecode deployment, template contracts (ERC-20/721/1155/Airdrop), ABI-based read/write calls, and webhook event monitoring. Keywords: contract deployment, smart contract, ABI interactions, template contracts, event monitoring, contract webhooks, bytecode, ERC-1155, ERC-20, ERC-721.
CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, AI agent development, or migrating existing/GitHub apps that need VPC access to MySQL/PostgreSQL/Redis. Also use when diagnosing CloudRun container deploy failures (deploy_failed, readiness/probe failed, image won't start, docker.io pull loops) or a deploy stuck behind a running deploy task. For stateless HTTP services, prefer HTTP cloud functions.
System audit. Triggers: reviewing a system, scanning for bugs/security/performance/architectural debt, and producing a findings list. Do not use for reviewing a single change diff (cs-code-review), fixing a known bug (cs-issue), implementing a feature (cs-feat), behavior-preserving refactoring (cs-refactor), or documenting established knowledge (cs-keep). This is a repository-wide, read-only investigation that identifies issues but does not fix them.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
Skill for Skyline mini program JSON configuration conventions. Covers app.json global configuration (renderer, rendererOptions, componentFramework), page JSON configuration (navigationStyle, disableScroll), and project.config.json project configuration. Use when creating a new Skyline project, migrating a WebView project, or configuring hybrid rendering. Trigger keywords: app.json, page configuration, renderer, rendererOptions, Skyline configuration, navigationStyle, disableScroll, componentFramework, glass-easel, project.config.json.
Agile product ownership toolkit for Senior Product Owner including INVEST-compliant user story generation, sprint planning, backlog management, and velocity tracking. Use for story writing, sprint planning, stakeholder communication, and agile ceremonies
Use this skill when handling user input in Phaser 4. Covers keyboard keys, mouse clicks and movement, touch events, pointer handling, drag and drop, hit areas, interactive objects, and gamepad support. Triggers on: keyboard, mouse, touch, pointer, drag, drop, click, input, gamepad, cursor keys.
Use this skill when working with Phaser 4 scenes. Covers scene lifecycle methods, scene transitions, parallel scenes, scene communication, sleeping, pausing, restarting, and the SceneManager. Triggers on: Scene, scene lifecycle, preload, create, update, scene transition, SceneManager.
Create and validate OmniStudio Data Mappers (formerly DataRaptor) with 100-point scoring. Use when building Extract, Transform, Load, or Turbo Extract Data Mappers, mapping Salesforce object fields, or reviewing existing Data Mapper configurations. Trigger when users create Data Mappers, configure field mappings, work with OmniDataTransform metadata, or ask about DataRaptor/Data Mapper patterns. Do not trigger when building Integration Procedures (use sf-industry-commoncore-integration-procedure), authoring OmniScripts (use sf-industry-commoncore-omniscript), or analyzing cross-component dependencies (use sf-industry-commoncore-omnistudio-analyze).
Creates a fully functional Drizzle ORM setup with a provisioned Neon database. Installs dependencies, provisions database credentials, configures connections, generates schemas, and runs migrations. Results in working code that can immediately connect to and query the database. Use when creating new projects with Drizzle, adding ORM to existing applications, or modifying database schemas.
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
Cross-cutting OmniStudio analysis skill for namespace detection, dependency visualization, and impact analysis across OmniScripts, FlexCards, Integration Procedures, and Data Mappers. Trigger when users ask about OmniStudio dependencies, want namespace detection (Core vs vlocity_cmt vs vlocity_ins), need impact analysis, or request dependency diagrams. Do not trigger when authoring OmniScripts (use sf-industry-commoncore-omniscript), building FlexCards (use sf-industry-commoncore-flexcard), creating Integration Procedures (use sf-industry-commoncore-integration-procedure), or configuring Data Mappers (use sf-industry-commoncore-datamapper).
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.