claude-api

Integrate Claude API patterns for Python and TypeScript into consistent workflows.

4|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/Yog-Sotho/claude-skills --skill claude-api-yog-sotho
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-api
Source: https://github.com/Yog-Sotho/claude-skills/tree/main/claude-api
Command: npx skills add https://github.com/Yog-Sotho/claude-skills --skill claude-api-yog-sotho

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Anthropic Claude API integration patterns for Python and TypeScript that codify best practices, model selection, and workflow structure, reducing integration time and errors.

Core Features & Use Cases

  • Messages API usage, including synchronous and streaming calls
  • Tool use, vision, PDF input, extended thinking, prompt caching, and batches
  • Structured outputs, token counting, and agentic loop patterns for multi-turn interactions

Quick Start

Install the appropriate Claude API SDKs and start applying the documented patterns in your Python or TypeScript projects.

Frequently Asked Questions about claude-api

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

FAQPage Schema
How do I use the Claude API for streaming and tool use in Python?

Using the Claude API for streaming and tool use in Python involves applying consistent SDK patterns for asynchronous calls and multi-turn agentic loops. This approach codifies Messages API workflows into production-ready structures.

What is the best way to structure TypeScript Anthropic SDK calls for structured outputs?

Structuring TypeScript Anthropic SDK calls for structured outputs requires enforcing model selection guidelines, pinned IDs, and safe defaults. This ensures consistent, production-ready workflows for token counting and structured responses.

Can I use Claude API patterns for prompt caching and PDF input?

Claude API patterns fully support prompt caching and PDF input alongside vision and extended thinking. These features integrate into asynchronous workflows to optimize multi-turn interactions and batch processing.

Does the Anthropic SDK support asynchronous batch processing and token counting?

The Anthropic SDK supports asynchronous batch processing and token counting through standardized API integration patterns. Default asynchronous handling manages these operations efficiently within agentic loops.

Why should I enforce pinned model IDs when building Claude API workflows?

Enforcing pinned model IDs when building Claude API workflows prevents disruptions from potential model changes and ensures stability. Safe defaults and consistent model selection guidelines maintain reliable integration behavior.