claude-api

Build Claude API and Anthropic SDK integrations for chat, streaming, and tool use.

Updated Mar 29, 2026
One-click install
npx skills add https://github.com/zizhenchen47-oss/claude-skills --skill claude-api-zizhenchen47-oss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-api
Source: https://github.com/zizhenchen47-oss/claude-skills/tree/main/claude-api
Command: npx skills add https://github.com/zizhenchen47-oss/claude-skills --skill claude-api-zizhenchen47-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you build reliable applications with the Claude API and Anthropic SDKs without having to piece together model selection, streaming, tool use, and request formatting on your own.

Core Features & Use Cases

  • Language-specific integration guidance: Covers Python, TypeScript, Java, Go, Ruby, C#, PHP, and raw HTTP so you can start in the stack you already use.
  • Production API workflows: Shows how to handle chat, streaming, tool calling, batch processing, file uploads, prompt caching, structured outputs, thinking, and compaction.
  • Developer guardrails: Explains exact model IDs, error handling patterns, and the right SDK types and request shapes to avoid common integration mistakes.
  • Use cases: Build chat assistants, agentic workflows, document analysis pipelines, cached multi-turn conversations, and high-volume batch jobs.

Quick Start

Open the Claude API guide for your programming language and follow its first message example to send a prompt with the correct model and max token settings.

Frequently Asked Questions about claude-api

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

FAQPage Schema
How do I implement streaming with the Claude API in Python or TypeScript?

Streaming with the Claude API is implemented through SDK-specific request and response handling patterns for Python, TypeScript, and other supported languages to process chat tokens incrementally. The Skill provides language-specific integration guidance to handle streaming workflows correctly.

What's the best way to structure tool use and batch processing in Anthropic SDK applications?

Tool use and batch processing in Anthropic SDK applications are structured using specific SDK request shapes for function calling and high-volume batch jobs. The Skill demonstrates production API workflows for agentic automation and document processing pipelines.

Does this Claude API integration guide support Go, Ruby, C#, PHP, and raw HTTP workflows?

Yes, the Claude API integration guide supports Go, Ruby, C#, PHP, and raw HTTP workflows alongside Python, TypeScript, and Java. It covers language-specific SDK types and request formatting for application development across these stacks.

Why do I need exact model IDs and adaptive thinking for Claude 4.6 models in my API requests?

Exact model IDs and adaptive thinking for Claude 4.6 models are required developer guardrails to avoid common integration mistakes and ensure correct API request formatting. The Skill explains these constraints to build reliable applications.

Can I use prompt caching and structured outputs for multi-turn conversations with the Claude API?

Yes, prompt caching and structured outputs can be used for cached multi-turn conversations with the Claude API. The Skill shows how to handle these production API workflows to optimize token usage and enforce response schemas.

What are common limitations and error handling patterns when building agentic workflows with the Anthropic SDK?

Common limitations when building agentic workflows with the Anthropic SDK involve incorrect request shapes, missing exact model IDs, and compaction errors. The Skill explains developer guardrails and error handling patterns to avoid these integration mistakes.