工具

Assist with core product management activities including writing PRDs, analyzing features, synthesizing user research, planning roadmaps, and communicating product decisions. Use when you need help with PM documentation, analysis, or planning workflows that integrate with your codebase.

Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools. Includes v4→v5 migration and 12 error solutions. Use when: implementing AI SDK v5/v6, migrating versions, troubleshooting AI_APICallError, Workers startup issues, or Output API validation errors.

Build React Native 0.76+ apps with Expo SDK 52+. Covers mandatory New Architecture (0.82+), React 19 changes, new CSS properties, and Swift iOS template. Use when building Expo apps, migrating to New Architecture, or fixing Fabric, TurboModule, propTypes, or Swift AppDelegate errors.

Build agentic AI with OpenAI Responses API - stateful conversations with preserved reasoning, built-in tools (Code Interpreter, File Search, Web Search), and MCP integration. Use when: building agents with persistent reasoning, using server-side tools, or migrating from Chat Completions for better multi-turn performance.

Integrate Vercel Blob for file uploads and CDN-delivered assets in Next.js. Supports client-side uploads with presigned URLs and multipart transfers for large files. Use when implementing file uploads (images, PDFs, videos) or troubleshooting missing tokens, size limits, or client upload failures.

Generate structured planning docs for web projects with context-safe phases, verification criteria, and exit conditions. Creates IMPLEMENTATION_PHASES.md plus conditional docs. Use when: starting new projects, adding major features, or breaking large work into manageable phases.

Post team updates to Google Chat Spaces via webhook. Deployment notifications, bug fixes, feature announcements, questions. Reads config from .claude/settings.json, includes git context. Use when: "post to team", "notify team", after deployments, completing features, fixing bugs, asking team questions.

Build type-safe, file-based React routing with TanStack Router. Supports client-side navigation, route loaders, and TanStack Query integration. Use when implementing file-based routing patterns, building SPAs with TypeScript routing, or troubleshooting devtools dependency errors, type safety issues, or Vite bundling problems.

Build type-safe validated forms using React Hook Form v7 and Zod v4. Single schema works on client and server with full TypeScript inference via z.infer. Use when building forms, multi-step wizards, or fixing uncontrolled warnings, resolver errors, useFieldArray issues.

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, or session limits.

Build MCP servers with TypeScript on Cloudflare Workers. Covers tools, resources, prompts, tasks, authentication (API keys, OAuth, Zero Trust), and Cloudflare service integrations. Use when exposing APIs to LLMs or troubleshooting export syntax errors, transport leaks, or CORS misconfigurations.

Minimal Chrome DevTools Protocol tools for browser automation and scraping. Use when you need to start Chrome, navigate pages, execute JavaScript, take screenshots, or interactively pick DOM elements.

Self-hosted auth for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, RBAC, and 15+ plugins. Requires Drizzle ORM or Kysely for D1 (no direct adapter). Self-hosted alternative to Clerk/Auth.js. Use when: self-hosting auth on D1, building OAuth provider, multi-tenant SaaS, or troubleshooting D1 adapter errors, session caching, rate limits.

Build React chat interfaces with Vercel AI SDK v6. Covers useChat/useCompletion/useObject hooks, message parts structure, tool approval workflows, and 12 UI error solutions. Use when: implementing AI chat UIs, migrating v5→v6, troubleshooting "useChat failed to parse stream", "stale body values", or React update depth errors.

Design effective Claude Code skills with optimal descriptions, progressive disclosure, and error prevention patterns. Covers freedom levels, token efficiency, and quality standards. Use when: creating new skills, improving skill descriptions, optimizing token usage, structuring skill content, or debugging why skills aren't being discovered.

Manage shadcn/ui components using MCP tools. Use when user needs to: (1) Add new shadcn components to a project (2) Build complex UI features requiring multiple components (3) Research component implementations and examples (4) Get component installation commands Triggers: "add shadcn", "shadcn component", "build UI with shadcn", "install component", "create form", "create dialog"

Build type-safe APIs with Hono for Cloudflare Workers, Deno, Bun, Node.js. Routing, middleware, validation (Zod/Valibot), RPC, streaming (SSE), WebSocket, security (CSRF, secureHeaders). Use when: building Hono APIs, streaming SSE, WebSocket, validation, RPC. Troubleshoot: validation hooks, RPC types, middleware chains.

Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with plugins system and hooks for event-driven workflows. Prevents 12 documented errors. Use when: building coding agents, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors.

Build with Claude Messages API using structured outputs for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, and model deprecations. Prevents 12 documented errors. Use when: building chatbots/agents, troubleshooting rate_limit_error, prompt caching issues, or streaming SSE parsing errors.

Build MCP servers in Python with FastMCP to expose tools, resources, and prompts to LLMs. Supports storage backends, middleware, OAuth Proxy, OpenAPI integration, and FastMCP Cloud deployment. Prevents 25+ errors. Use when: creating MCP servers, or troubleshooting module-level server, storage, lifespan, middleware, or OAuth errors.