skills.rest
AmirEmad11
AmirEmad11COMMUNITY
Explore all skills by this author →
GitHub

ai-integrations-anthropic

Integrates Anthropic Claude models into TypeScript apps via Replit AI Integrations proxy.

Updated Apr 20, 2026
Search Tags:#typescript#claude#batch processing#anthropic#llm integration#replit#sse streaming
One-click install
npx skills add https://github.com/AmirEmad11/instabot --skill ai-integrations-anthropic-amiremad11
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-integrations-anthropic
Source: https://github.com/AmirEmad11/instabot/tree/main/.local/skills/ai-integrations-anthropic
Command: npx skills add https://github.com/AmirEmad11/instabot --skill ai-integrations-anthropic-amiremad11

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @anthropic-ai/sdk, p-limit, p-retry, and includes references (resource) components.

What problem does it solve? Setting up Anthropic Claude access normally requires obtaining and managing your own API key, configuring billing, and wiring SDK clients, database tables, and streaming endpoints by hand. This Skill provisions Anthropic access through the Replit AI Integrations proxy with auto-configured environment variables and provides ready-made templates for the client, batch processing, database schema, and API routes. ## Core Features & Use Cases - Keyless Anthropic Access: Provisions AI_INTEGRATIONS_ANTHROPIC_BASE_URL and AI_INTEGRATIONS_ANTHROPIC_API_KEY automatically, with charges billed to Replit credits. - Pre-built Integration Package: Provides a TypeScript workspace package with a pre-configured Anthropic SDK client, batch processing utilities with rate limiting and retries, and SSE streaming support. - Full-Stack Chat Scaffold: Includes Drizzle schemas for conversations and messages tables plus OpenAPI spec entries for chat endpoints under the /anthropic prefix. - Use Case: Build a streaming chat application backed by claude-sonnet-4-6 with persistent conversation history, without ever handling an Anthropic API key. ## Quick Start Set up the Anthropic AI integration and build a streaming chat endpoint using the provided client and conversation templates.

Frequently Asked Questions about ai-integrations-anthropic

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I use the Anthropic API without my own API key?▼

Use the Replit AI Integrations proxy by calling setupReplitAIIntegrations with the anthropic provider slug. It automatically sets AI_INTEGRATIONS_ANTHROPIC_BASE_URL and AI_INTEGRATIONS_ANTHROPIC_API_KEY, and usage is billed to your Replit credits.

How do I stream Anthropic Claude responses with SSE in Express?▼

Use anthropic.messages.stream() with text/event-stream headers, write each content_block_delta text chunk as an SSE data event, then send a final done event and end the response. Consume it on the client with fetch and ReadableStream, not EventSource.

Which Claude models are available through Replit AI Integrations?▼

Available models include claude-opus-4-7, claude-opus-4-6, claude-opus-4-5, claude-opus-4-1, claude-sonnet-4-6, claude-sonnet-4-5, and claude-haiku-4-5. Models not on this list are not available through the integration.

Does the Anthropic integration support the Batch API or Files API?▼

No, the Batch API and Files API are not supported by Anthropic AI integrations. For those capabilities you must use Anthropic directly with your own API key instead of the proxy.

Why does my Anthropic request fail with a 400 error on claude-opus-4-7?▼

claude-opus-4-7 rejects temperature, top_p, and top_k parameters set to non-default values, and extended thinking budgets are unsupported. Omit those parameters entirely and use adaptive thinking instead.

How do I handle rate limits when making many Anthropic API calls?▼

Use the provided batchProcess utility, which wraps calls with p-limit concurrency control and p-retry exponential backoff for rate limit errors. Defaults are concurrency 2 and 7 retries, both configurable via options.

Related Skills

Explore More Software Engineering Skills→
SaberAlouiSaberAloui

pnpm-workspace

Guides development of pnpm monorepos with TypeScript project references, OpenAPI codegen, and workspace conventions.

Community
Advanced
TanStackTanStack
3.0k

ai-core/chat-experience

Implement streaming SSE chat endpoints and clients with TanStack AI.

Official
Advanced
ricardorochericardoroche
2

model-selection

Automate LLM model and provider selection with registry-driven configuration.

Community
Intermediate
Buntyarora97Buntyarora97

ai-integrations-anthropic

Integrate Anthropic AI models via Replit AI Integrations proxy without API keys.

Community
Intermediate