Loading...
Loading...
Found 2,542 Skills
Use this skill when building MCP (Model Context Protocol) servers with FastMCP in Python. FastMCP is a framework for creating servers that expose tools, resources, and prompts to LLMs like Claude. The skill covers server creation, tool/resource definitions, storage backends (memory/disk/Redis/DynamoDB), server lifespans, middleware system (8 built-in types), server composition (import/mount), OAuth Proxy, authentication patterns, icons, OpenAPI integration, client configuration, cloud deployment (FastMCP Cloud), error handling, and production patterns. It prevents 25+ common errors including storage misconfiguration, lifespan issues, middleware order errors, circular imports, module-level server issues, async/await confusion, OAuth security vulnerabilities, and cloud deployment failures. Includes templates for basic servers, storage backends, middleware, server composition, OAuth proxy, API integrations, testing, and self-contained production architectures. Keywords: FastMCP, MCP server Python, Model Context Protocol Python, fastmcp framework, mcp tools, mcp resources, mcp prompts, fastmcp storage, fastmcp memory storage, fastmcp disk storage, fastmcp redis, fastmcp dynamodb, fastmcp lifespan, fastmcp middleware, fastmcp oauth proxy, server composition mcp, fastmcp import, fastmcp mount, fastmcp cloud, fastmcp deployment, mcp authentication, fastmcp icons, openapi mcp, claude mcp server, fastmcp testing, storage misconfiguration, lifespan issues, middleware order, circular imports, module-level server, async await mcp
Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared state or ordering dependencies.
Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.
Review inbox status across multiple email accounts with per-account breakdown and cross-account priorities.
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
Reverse engineer Single Page Applications built with React + Vite + Workbox — analyze SPA internals via Chrome DevTools Protocol (CDP), write browser extensions, intercept service workers, and extract runtime state for SDK integration.
Configure, explore, and optimize Nx monorepo workspaces. Use when setting up Nx, exploring workspace structure, configuring project boundaries, running tasks, analyzing affected projects, optimizing build caching, or implementing CI/CD with affected commands. Keywords - nx, monorepo, workspace, projects, targets, affected, build, lint, test.
Setup Spanora AI observability in any project (JavaScript/TypeScript or Python). Use when user asks to "add spanora", "setup spanora", "integrate spanora", "add AI observability", "monitor LLM calls with spanora", "track AI costs", or mentions spanora in the context of adding observability to their project. Detects the language and installed AI SDKs (Vercel AI, Anthropic, OpenAI, LangChain) and configures the optimal integration pattern.
How to work in artist directories — including creating, enumerating, and editing them. Use when creating or onboarding a new artist ("create artist", "onboard X", "add this artist", "set up a new artist") — this skill scaffolds the artist's `RECOUP.md` checklist file and drives the multi-step setup from it. Use when adding or updating artist context (identity, brand, voice, audience), adding songs, organizing files inside an artist directory, or figuring out where something belongs. Also use when the account asks inventory questions like "what artists do I have", "list my artists", "which orgs am I in", "what's in this sandbox" — the filesystem tree is the authoritative answer. And use when the account mentions an artist by name and the task involves their files, context, or content — even if they don't say "artist directory." This includes tasks like researching an artist, creating content for an artist, updating an artist's brand, or adding a face guide.
Find mutual availability with attendees and suggest meeting times.
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.