Develop with
Superpowers

AI session compression techniques for managing multi-turn conversations efficiently through summarization, embedding-based retrieval, and intelligent context management.

High-performance monorepo build system with intelligent caching, task orchestration, and parallel execution for multi-package repositories and microservices.

Comprehensive guide to GPU-accelerated encoding and decoding with NVIDIA, Intel, AMD, Apple, and Vulkan.

```tsx 'use client';

Video analysis and editing with FFmpeg and Whisper. This skill should be used when video files are shared (.mov, .mp4, .avi, etc.) or when you encounter "cannot read binary files" errors for video files, when users request video analysis or summarization, or when users ask to edit videos (clip, merge, split).

Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.

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

This skill provides comprehensive knowledge for building type-safe, validated forms in React using React Hook Form and Zod schema validation. Use when: building forms with validation in React, integrating Zod schema validation with React Hook Form, using shadcn/ui Form or Field components, implementing client and server-side validation with a single schema, handling complex validation scenarios (nested objects, arrays, conditional fields, async validation), building multi-step forms or wizards, implementing dynamic form fields with useFieldArray, optimizing form performance and re-renders, ensuring accessible form error handling, or debugging form validation issues. Keywords: react-hook-form, useForm, zod validation, zodResolver, @hookform/resolvers, form schema, register, handleSubmit, formState, useFieldArray, useWatch, useController, Controller, shadcn form, Field component, client server validation, nested validation, array field validation, dynamic fields, multi-step form, async validation, zod refine, z.infer, form error handling, uncontrolled to controlled, resolver not found, schema validation error

Complete guide for OpenAI's Assistants API v2: stateful conversational AI with built-in tools (Code Interpreter, File Search, Function Calling), vector stores for RAG (up to 10,000 files), thread/run lifecycle management, and streaming patterns. Both Node.js SDK and fetch approaches. ⚠️ DEPRECATION NOTICE: OpenAI plans to sunset Assistants API in H1 2026 in favor of Responses API. This skill remains valuable for existing apps and migration planning. Use when: building stateful chatbots with OpenAI, implementing RAG with vector stores, executing Python code with Code Interpreter, using file search for document Q&A, managing conversation threads, streaming assistant responses, or encountering errors like "thread already has active run", vector store indexing delays, run polling timeouts, or file upload issues. Keywords: openai assistants, assistants api, openai threads, openai runs, code interpreter assistant, file search openai, vector store openai, openai rag, assistant streaming, thread persistence, stateful chatbot, thread already has active run, run status polling, vector store error

This skill provides project-specific coding conventions, architectural principles, repository structure standards, testing patterns, and contribution guidelines for the better-chatbot project (https://github.com/cgoinglove/better-chatbot). Use this skill when contributing to or working with better-chatbot to understand the design philosophy and ensure code follows established patterns. Includes: API architecture deep-dive, three-tier tool system (MCP/Workflow/Default), component design patterns, database repository patterns, architectural principles (progressive enhancement, defensive programming, streaming-first), practical templates for adding features (tools, routes, repositories). Use when: working in better-chatbot repository, contributing features/fixes, understanding architectural decisions, following server action validators, implementing tools/workflows, setting up Playwright tests, adding API routes, designing database queries, building UI components, handling multi-AI provider integration Keywords: better-chatbot, chatbot contribution, better-chatbot standards, chatbot development, AI chatbot patterns, API architecture, three-tier tool system, repository pattern, progressive enhancement, defensive programming, streaming-first, compound component pattern, Next.js chatbot, Vercel AI SDK chatbot, MCP tools, workflow builder, server action validators, tool abstraction, DAG workflows, shared business logic, safe() wrapper, tool lifecycle

Complete guide for OpenAI's traditional/stateless APIs: Chat Completions (GPT-5, GPT-4o), Embeddings, Images (DALL-E 3), Audio (Whisper + TTS), and Moderation. Includes both Node.js SDK and fetch-based approaches for maximum compatibility. Use when: integrating OpenAI APIs, implementing chat completions with GPT-5/GPT-4o, generating text with streaming, using function calling/tools, creating structured outputs with JSON schemas, implementing embeddings for RAG, generating images with DALL-E 3, transcribing audio with Whisper, synthesizing speech with TTS, moderating content, deploying to Cloudflare Workers, or encountering errors like rate limits (429), invalid API keys (401), function calling failures, streaming parse errors, embeddings dimension mismatches, or token limit exceeded. Keywords: openai api, chat completions, gpt-5, gpt-5-mini, gpt-5-nano, gpt-4o, gpt-4-turbo, openai sdk, openai streaming, function calling, structured output, json schema, openai embeddings, text-embedding-3, dall-e-3, image generation, whisper api, openai tts, text-to-speech, moderation api, openai fetch, cloudflare workers openai, openai rate limit, openai 429, reasoning_effort, verbosity

This skill provides comprehensive knowledge for Cloudflare Images, covering both the Images API (upload/storage) and Image Transformations (optimize any image). It should be used when uploading images to Cloudflare, resizing images, optimizing image delivery, implementing direct creator uploads, creating image variants, generating signed URLs for private images, transforming images via Workers, or encountering image upload/transformation errors. Use when: setting up Cloudflare Images storage, implementing user-uploaded images, creating responsive images, optimizing image formats (WebP/AVIF), resizing images via URL or Workers, debugging CORS errors with direct uploads, handling image transformation errors (9401-9413), implementing signed URLs, managing image variants, or building image CDNs. Keywords: cloudflare images, image upload cloudflare, imagedelivery.net, cloudflare image transformations, /cdn-cgi/image/, direct creator upload, image variants, cf.image workers, signed urls images, flexible variants, webp avif conversion, responsive images cloudflare, error 5408, error 9401, error 9403, CORS direct upload, multipart/form-data, image optimization cloudflare

Backend AI functionality with Vercel AI SDK v5 - text generation, structured output with Zod, tool calling, and agents. Multi-provider support for OpenAI, Anthropic, Google, and Cloudflare Workers AI. Use when: implementing server-side AI features, generating text/chat completions, creating structured AI outputs with Zod schemas, building AI agents with tools, streaming AI responses, integrating OpenAI/Anthropic/Google/Cloudflare providers, or encountering AI SDK errors like AI_APICallError, AI_NoObjectGeneratedError, streaming failures, or worker startup limits. Keywords: ai sdk core, vercel ai sdk, generateText, streamText, generateObject, streamObject, ai sdk node, ai sdk server, zod ai schema, ai tools calling, ai agent class, openai sdk, anthropic sdk, google gemini sdk, workers-ai-provider, ai streaming backend, multi-provider ai, ai sdk errors, AI_APICallError, AI_NoObjectGeneratedError, streamText fails, worker startup limit ai

Use this skill when contributing code to open source projects. The skill covers proper pull request creation, avoiding common mistakes that annoy maintainers, cleaning up personal development artifacts before submission, writing effective PR descriptions, following project conventions, and communicating professionally with maintainers. It prevents 16 common contribution mistakes including working on main branch, not testing before PR submission, including unrelated changes, submitting planning documents, session notes, temporary test files, screenshots, and other personal artifacts. Includes 3 Critical Workflow Rules that must NEVER be skipped: (1) Always work on feature branches, (2) Test thoroughly with evidence before PR, (3) Keep PRs focused on single feature. The skill includes automation scripts to validate PRs before submission, templates for PR descriptions and commit messages, and comprehensive checklists. This skill should be used whenever creating pull requests for public repositories, contributing to community projects, or submitting code to projects you don't own. Keywords: open source contributions, github pull request, PR best practices, contribution guidelines, feature branch workflow, PR description, commit messages, open source etiquette, maintainer-friendly PR, PR checklist, clean PR, avoid personal artifacts, session notes cleanup, planning docs cleanup, test before PR, unrelated changes, working on main branch, focused PR, single feature PR, professional communication, community contributions, public repository contributions, fork workflow, upstream sync

Complete knowledge domain for Cloudflare Workflows - durable execution framework for building multi-step applications on Workers that automatically retry, persist state, and run for hours or days. Use when: creating long-running workflows, implementing retry logic, building event-driven processes, scheduling multi-step tasks, coordinating between APIs, or encountering "NonRetryableError", "I/O context", "workflow execution failed", "serialization error", or "WorkflowEvent not found" errors. Keywords: cloudflare workflows, workflows workers, durable execution, workflow step, WorkflowEntrypoint, step.do, step.sleep, workflow retries, NonRetryableError, workflow state, wrangler workflows, workflow events, long-running tasks, step.sleepUntil, step.waitForEvent, workflow bindings

This skill provides comprehensive knowledge for working with the Anthropic Messages API (Claude API). It should be used when integrating Claude models into applications, implementing streaming responses, enabling prompt caching for cost savings, adding tool use (function calling), processing images with vision capabilities, or using extended thinking mode. Use when building chatbots, AI assistants, content generation tools, or any application requiring Claude's language understanding. Covers both server-side implementations (Node.js, Cloudflare Workers, Next.js) and direct API access. Keywords: claude api, anthropic api, messages api, @anthropic-ai/sdk, claude streaming, prompt caching, tool use, vision, extended thinking, claude 3.5 sonnet, claude 3.7 sonnet, claude sonnet 4, function calling, SSE, rate limits, 429 errors

Use this skill when building AI voice agents with the ElevenLabs Agents Platform. This skill covers the complete platform including agent configuration (system prompts, turn-taking, workflows), voice & language features (multi-voice, pronunciation, speed control), knowledge base (RAG), tools (client/server/MCP/system), SDKs (React, JavaScript, React Native, Swift, Widget), Scribe (real-time STT), WebRTC/WebSocket connections, testing & evaluation, analytics, privacy/compliance (GDPR/HIPAA/SOC 2), cost optimization, CLI workflows ("agents as code"), and DevOps integration. Prevents 17+ common errors including package deprecation, Android audio cutoff, CSP violations, missing dynamic variables, case-sensitive tool names, webhook authentication failures, and WebRTC configuration issues. Provides production-tested templates for React, Next.js, React Native, Swift, and Cloudflare Workers. Token savings: ~73% (22k → 6k tokens). Production tested. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication

Frontend React hooks for AI-powered chat interfaces, completions, and streaming UIs with Vercel AI SDK v5. Includes useChat, useCompletion, and useObject hooks for building interactive AI applications. Use when: building React chat interfaces, implementing AI completions in UI, streaming AI responses to frontend, handling chat message state, building Next.js AI apps, managing file attachments with AI, or encountering errors like "useChat failed to parse stream", "useChat no response", unclosed streams, or streaming issues. Keywords: ai sdk ui, useChat hook, useCompletion hook, useObject hook, react ai chat, ai chat interface, streaming ai ui, nextjs ai chat, vercel ai ui, react streaming, ai sdk react, chat message state, ai file attachments, message persistence, useChat error, streaming failed ui, parse stream error, useChat no response, react ai hooks, nextjs app router ai, nextjs pages router ai

Build full-stack React apps with TanStack Start on Cloudflare Workers. Type-safe routing, server functions, SSR/streaming, D1/KV/R2 integration. Use when building full-stack React apps with SSR, migrating from Next.js, or from Vinxi to Vite (v1.121.0+). Prevents 9 documented errors including middleware bugs, file upload limitations, and deployment config issues.

Integrate Gemini API with @google/genai SDK (NOT deprecated @google/generative-ai). Text generation, multimodal (images/video/audio/PDFs), function calling, thinking mode, streaming. 1M input tokens. Prevents 14 documented errors. Use when: Gemini integration, multimodal AI, reasoning with thinking mode. Troubleshoot: SDK deprecation, model not found, context window, function calling errors, streaming corruption, safety settings, rate limits.