後端開發

Store and transform images with Cloudflare Images API and transformations. Use when: uploading images, implementing direct creator uploads, creating variants, generating signed URLs, optimizing formats (WebP/AVIF), transforming via Workers, or debugging CORS, multipart, or error codes 9401-9413.

Build MCP servers in Python with FastMCP framework to expose tools, resources, and prompts to LLMs. Supports storage backends (memory/disk/Redis), middleware, OAuth Proxy, OpenAPI integration, and FastMCP Cloud deployment. Use when: creating MCP servers, defining tools or resources, implementing OAuth authentication, configuring storage backends for tokens/cache, adding middleware for logging/rate limiting, deploying to FastMCP Cloud, or troubleshooting module-level server, storage, lifespan, middleware order, circular imports, or OAuth errors.

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 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.

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.

Audit claude-skills repository documentation with systematic 9-phase review: standards compliance, official docs verification via Context7/WebFetch, code examples accuracy, cross-file consistency, and version drift detection. Auto-fixes unambiguous issues with severity classification. Use when: investigating skill issues, major package updates detected (e.g., v1.x → v2.x), skill not verified >90 days, before marketplace submission, or troubleshooting outdated API patterns, contradictory examples, broken links, version drift.

Build backend AI with Vercel AI SDK v5/v6. v6 stable introduces Output API (Output.object/array/choice replace deprecated generateObject/streamObject), plus speech synthesis, transcription, image generation, embeddings, reranking, MCP tools, and middleware. Covers v4→v5 migration, latest models (GPT-5.2, Claude 4.x, Gemini 2.5), Workers startup fix, and 12 error solutions. Use when: implementing AI SDK v5/v6, using Output API, speech/transcription/image features, embeddings, MCP tools, migrating v4→v5, troubleshooting errors, or fixing Workers startup issues.

Build Python APIs with FastAPI, Pydantic v2, and SQLAlchemy 2.0. Covers project structure, async patterns, JWT authentication, validation, and database integration with uv package manager. Use when: creating Python APIs, setting up FastAPI projects, implementing JWT auth, configuring SQLAlchemy async, or troubleshooting 422 validation errors, CORS issues, or async blocking.

Build agentic AI applications with OpenAI's Responses API - the stateful successor to Chat Completions. Preserves reasoning across turns for 5% better multi-turn performance and 40-80% improved cache utilization. Use when: building AI agents with persistent reasoning, integrating MCP servers for external tools, using built-in Code Interpreter/File Search/Web Search, managing stateful conversations, implementing background processing for long tasks, or migrating from Chat Completions to gain polymorphic outputs and server-side tools.

Build CLI scripts alongside MCP servers for terminal environments. Scripts provide file I/O, batch processing, caching, and richer output formats that remote MCP servers cannot offer. Includes templates for TypeScript scripts and SCRIPTS.md. Use when: creating MCP server companion scripts, adding batch processing to MCP tools, saving MCP results to files, building CLI wrappers for APIs, or troubleshooting "context too large", "no file access", or batch input handling.

Comprehensive backend development workflow that orchestrates expert analysis, architecture design, implementation, and deployment using the integrated toolset. Handles everything from API design and database architecture to security implementation and DevOps automation.

API contract testing, authentication flows, rate limit handling, and error scenario coverage for n8n integrations with external services. Use when testing n8n node integrations.

Comprehensive n8n workflow testing including execution lifecycle, node connection patterns, data flow validation, and error handling strategies. Use when testing n8n workflow automation applications.

n8n expression syntax validation, context-aware testing, common pitfalls detection, and performance optimization. Use when validating n8n expressions and data transformations.

Unvarnished technical criticism combining Linus Torvalds' precision, Gordon Ramsay's standards, and James Bach's BS-detection. Use when code/tests need harsh reality checks, certification schemes smell fishy, or technical decisions lack rigor. No sugar-coating, just surgical truth about what's broken and why.

Guide for implementing Cloudflare Browser Rendering - a headless browser automation API for screenshots, PDFs, web scraping, and testing. Use when automating browsers, taking screenshots, generating PDFs, scraping dynamic content, extracting structured data, or testing web applications. Supports REST API, Workers Bindings (Puppeteer/Playwright), MCP servers, and AI-powered automation. (project)

Guide for implementing Shopify apps, extensions, themes, and integrations using GraphQL/REST APIs, Shopify CLI, Polaris UI, and various extension types (Checkout, Admin, POS). Use when building Shopify apps, implementing checkout extensions, customizing admin interfaces, creating themes with Liquid, or integrating with Shopify's APIs.

PROACTIVELY search auto-generated documentation when receiving ANY user instruction. Search for function signatures, API documentation, class definitions, and code comments BEFORE implementing anything. Your codebase documentation is valuable - use it first.

Sets up NX monorepo for TypeScript backend projects optimized for AI-assisted development. Delegates to NX commands where possible, patches configs as last resort. Triggers on: 'set up typescript backend project', 'create backend project', 'initialize typescript backend', 'create monorepo', or when working in an empty project folder.

Force honest confidence assessment before claiming conclusions. Triggers on 'root cause identified', 'problem identified', 'complete clarity'. Express confidence as percentage, explain what's stopping 100%, validate assumptions before presenting.