Найдите подходящую возможность для вашего агента.
Four slash commands for documentation lifecycle: /docs, /docs-init, /docs-update, /docs-claude. Create, maintain, and audit CLAUDE.md, README.md, and docs/ structure with smart templates. Use when: starting new projects, maintaining documentation, auditing docs for staleness, or ensuring CLAUDE.md matches project state.
Convert websites into LLM-ready markdown with Firecrawl v4 API. Handles JavaScript rendering, anti-bot bypass, and structured data extraction for RAG and AI applications. Use when: scraping websites, crawling sites, or troubleshooting content not loading, JavaScript rendering, or bot detection.
Generate complete, accessible color palettes from a single brand hex. Creates 11-shade scale (50-950), semantic tokens (background, foreground, card, muted), and dark mode variants. Includes WCAG contrast checking for text accessibility. Use when: setting up design system, creating Tailwind theme, building brand colors from single hex, converting designs to code, checking color accessibility.
Build on Snowflake's AI Data Cloud with snow CLI, Cortex AI (COMPLETE, SUMMARIZE, AI_FILTER), Native Apps, and Snowpark. Covers JWT auth, account identifiers, Marketplace publishing. Use when: Snowflake apps, Cortex AI SQL, Native App publishing. Troubleshoot: JWT auth failures, account locator confusion, release channel errors.
Build with D1 serverless SQLite database on Cloudflare's edge. Use when: creating databases, writing SQL migrations, querying D1 from Workers, handling relational data, or troubleshooting D1_ERROR, statement too long, migration failures, or query performance issues.
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 AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Use when: building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures.
Connect Workers to PostgreSQL/MySQL with Hyperdrive's global pooling and caching. Use when: connecting to existing databases, setting up connection pools, using node-postgres/mysql2, integrating Drizzle/Prisma, or troubleshooting pool acquisition failures, TLS errors, or nodejs_compat missing.
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.
Build type-safe D1 databases with Drizzle ORM. Includes schema definition, migrations with Drizzle Kit, relations, and D1 batch API patterns. Prevents 12 errors including SQL BEGIN failures and foreign key issues. Use when: defining D1 schemas, managing migrations, or troubleshooting D1_ERROR, BEGIN TRANSACTION, foreign keys.
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 16 documented errors. Use when: building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors.
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. Use when: Gemini integration, multimodal AI, reasoning with thinking mode. Troubleshoot: SDK deprecation, model not found, context window, function calling errors.
Set up Tailwind v4 with shadcn/ui using @theme inline pattern and CSS variable architecture. Four-step pattern: CSS variables, Tailwind mapping, base styles, automatic dark mode. Use when initializing React projects with Tailwind v4, or fixing colors not working, tw-animate-css errors, v3 migration.
Build conversational AI voice agents with ElevenLabs Platform. Configure agents, tools, RAG knowledge bases, multi-voice, and Scribe STT across React, React Native, or Swift. Prevents 27 documented errors. Use when: building voice agents, AI phone systems, or troubleshooting @11labs deprecated, webhook errors, CSP violations.
Add bot protection with Turnstile (CAPTCHA alternative). Use when: protecting forms, securing login/signup, preventing spam, migrating from reCAPTCHA, integrating with React/Next.js/Hono, implementing E2E tests, or debugging CSP errors, token validation failures, or error codes 100*/300*/600*.
Build with OpenAI stateless APIs - Chat Completions (GPT-5.2, o3), Realtime voice, Batch API (50% savings), Embeddings, DALL-E 3, Whisper, and TTS. Use when: implementing GPT-5 chat, streaming, function calling, embeddings for RAG, or troubleshooting rate limits (429), API errors.
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.
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.
Create maintainer-friendly pull requests with clean code and professional communication. Prevents 16 common mistakes that cause PR rejection. Use when: contributing to open source, submitting PRs, or troubleshooting PR rejection, CI failures, or personal artifacts in commits.
Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. Deprecated (sunset August 2026); use openai-responses for new projects. Use when: maintaining legacy chatbots, implementing RAG with vector stores, or troubleshooting thread errors, vector store delays.
