工具

Integrate Vercel Blob object storage for file uploads, image management, and CDN-delivered assets in Next.js applications. Supports client-side uploads with presigned URLs and multipart transfers. Use when implementing file uploads (images, PDFs, videos), managing user-generated content, or troubleshooting missing tokens, size limit errors, or client upload failures.

Generate typed TypeScript SDKs for AI agents to interact with MCP servers. Converts verbose JSON-RPC curl commands to clean function calls (docs.createDocument() vs curl). Auto-detects MCP tools from server modules, generates TypeScript types and client methods, creates runnable example scripts. Use when: building MCP-enabled applications, need typed programmatic access to MCP tools, want Claude Code to manage apps via scripts, eliminating manual JSON-RPC curl commands, validating MCP inputs/outputs, or creating reusable agent automation.

Integrate Gemini API with correct current SDK (@google/genai v1.27+, NOT deprecated @google/generative-ai). Supports text generation, multimodal (images/video/audio/PDFs), function calling, and thinking mode. 1M input tokens. Use when: integrating Gemini API, implementing multimodal AI, using thinking mode for reasoning, function calling with parallel execution, streaming responses, deploying to Cloudflare Workers, building chat, or troubleshooting SDK deprecation, context window, model not found, function calling, or multimodal format errors. Keywords: gemini api, @google/genai, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-3-pro-preview, multimodal gemini, thinking mode, google ai, genai sdk, function calling gemini, streaming gemini, gemini vision, gemini video, gemini audio, gemini pdf, system instructions, multi-turn chat, DEPRECATED @google/generative-ai, gemini context window, gemini models 2025, gemini 1m tokens, gemini tool use, parallel function calling, compositional function calling, gemini 3

Generate structured planning documentation for web projects with context-safe phases, verification criteria, and exit conditions. Creates IMPLEMENTATION_PHASES.md plus conditional docs (DATABASE_SCHEMA, API_ENDPOINTS, UI_COMPONENTS, CRITICAL_WORKFLOWS). Use when: starting new Cloudflare Workers/React projects, adding major features to existing apps, breaking large work into manageable phases, or need verified planning before coding begins.

Build ChatGPT apps with MCP servers on Cloudflare Workers. Extend ChatGPT with custom tools and interactive widgets (HTML/JS UI). Use when: developing ChatGPT extensions, implementing MCP servers, or troubleshooting CORS blocking (allow chatgpt.com), widget 404s (missing ui://widget/), wrong MIME type (text/html+skybridge), or ASSETS binding undefined.

Set up serverless Postgres with Neon or Vercel Postgres for Cloudflare Workers/Edge. Includes connection pooling, git-like branching for preview environments, and Drizzle/Prisma integration. Use when: setting up edge Postgres, configuring database branching, or troubleshooting "TCP not supported", connection pool exhausted, SSL config (sslmode=require), or Prisma edge compatibility.

Post team updates to Google Chat Spaces via webhook. Supports deployment notifications, bug fixes, feature announcements, and questions. Reads config from .claude/settings.json, formats messages with rich formatting, and includes git context (commits, branches, changed files). Use when: "post to team", "notify team", "update the team", after deployments, completing features, fixing bugs reported by team, or asking questions that need team input. Keywords: google spaces, google chat, team notifications, webhook, deployment updates, team chat, chat spaces api, notify team, post update, team collaboration, slack alternative

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 in React using React Hook Form and Zod schema validation. Single schema works on both client and server for DRY validation with full TypeScript type inference via z.infer. Use when: building forms with validation, integrating shadcn/ui Form components, implementing multi-step wizards, handling dynamic field arrays with useFieldArray, or fixing uncontrolled to controlled warnings, resolver errors, async validation issues.

Build authentication systems for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, RBAC, OAuth 2.1 provider, and 15+ plugins. Self-hosted alternative to Clerk/Auth.js. IMPORTANT: Requires Drizzle ORM or Kysely for D1 - no direct D1 adapter. Workers require nodejs_compat flag. v1.4.10 adds OAuth 2.1 Provider (MCP deprecated), Bearer tokens, Google One Tap, SCIM, Anonymous auth, rate limiting, Patreon/Kick/Vercel providers. Use when: self-hosting auth on Cloudflare D1, building OAuth provider for MCP servers, multi-tenant SaaS, admin dashboards, API key auth, guest users, or troubleshooting D1 adapter errors, session caching, rate limits, database hooks.

Build type-safe APIs with Hono - fast, lightweight routing for Cloudflare Workers, Deno, Bun, and Node.js. Covers routing, middleware, validation (Zod/Valibot), RPC client/server, streaming (SSE, streamText), WebSocket, security middleware (secureHeaders, CSRF), and combine middleware. Use when: building APIs with Hono, streaming responses (SSE, AI), WebSocket connections, security middleware (CSRF, secureHeaders), request validation, RPC communication, or troubleshooting validation hooks, RPC types, middleware chains.

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.

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 React chat interfaces with Vercel AI SDK v6. Covers v6 stable (agent integration, tool approval, message parts structure, auto-submit), v5→v6 migration, useChat/useCompletion/useObject hooks, and 12 UI error solutions (stream parsing, stale body values, React update depth). Use when: implementing AI SDK v6 chat UIs, migrating v5→v6, troubleshooting "useChat failed to parse stream", "useChat no response", or "stale body values" errors, or building AI chat interfaces.

Build autonomous AI agents with Claude Agent SDK. Structured outputs (v0.1.45, Nov 2025) guarantee JSON schema validation, plugins system, hooks for event-driven workflows. Use when: building coding agents with validated JSON responses, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors.

Build with Claude Messages API using structured outputs (v0.69.0+, Nov 2025) for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, model deprecations (3.5/3.7 retired Oct 2025). Use when: building chatbots/agents with validated JSON responses, or troubleshooting rate_limit_error, structured output validation, prompt caching not activating, streaming SSE parsing.

Build stateless MCP servers with TypeScript on Cloudflare Workers using @modelcontextprotocol/sdk. Provides patterns for tools, resources, prompts, and authentication (API keys, OAuth, Zero Trust). Use when exposing APIs to LLMs, integrating Cloudflare services (D1, KV, R2, Vectorize), or troubleshooting export syntax errors, unclosed 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.

Generate structured task lists from specs or requirements. IMPORTANT: After completing ANY spec via ExitSpecMode, ALWAYS ask the user: "Would you like me to generate a task list for this spec?" Use when user confirms or explicitly requests task generation from a plan/spec/PRD.