claude-api

Select Anthropic API surfaces and SDKs for Claude-powered applications.

Updated Mar 16, 2026
One-click install
npx skills add https://github.com/zlovexforever/zlx-claude-skills --skill claude-api-zlovexforever
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-api
Source: https://github.com/zlovexforever/zlx-claude-skills/tree/main/claude-api
Command: npx skills add https://github.com/zlovexforever/zlx-claude-skills --skill claude-api-zlovexforever

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you choose the correct Anthropic/Claude API surface and wire it up correctly so you can build LLM-powered applications without trial-and-error.

Core Features & Use Cases

  • Guided surface selection: Pick Claude API for single calls or workflows, use tool use for orchestration, and choose Agent SDK when you need built-in web/file/terminal capabilities.
  • Language-aware implementation guidance: Detect your project language and follow the matching SDK instructions (Python, TypeScript, Java, Go, Ruby, C#, PHP) or use cURL/raw HTTP when needed.
  • Production-ready setup defaults: Apply consistent model/streaming/thinking defaults (notably claude-opus-4-6 and adaptive thinking) and steer toward safer patterns like streaming and structured outputs.
  • Tooling and agentic patterns: Cover tool use, manual agentic loops, tool runners (where available), code execution, web fetch/search concepts, batching, files API, and compaction for long conversations.
  • Reliability and cost controls: Use prompt caching, token counting guidance, batch processing for cost savings, and error-handling references.

Quick Start

Ask: Build a Claude API (Messages API) integration in my language, using claude-opus-4-6, streaming, and tool use only if I need multi-step actions.

Frequently Asked Questions about claude-api

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

FAQPage Schema
How do I choose the right Claude API surface for my application workflow?

To choose the right Claude API surface, match your workflow complexity to the correct tier: single-call Q&A uses the Messages API directly, multi-step orchestration uses tool use, and agentic flows needing file, web, or terminal access use the Agent SDK.

Can I use the Anthropic API with TypeScript, Go, or other non-Python languages?

Yes, the Anthropic API supports multiple SDK languages including Python, TypeScript, Java, Go, Ruby, C#, and PHP. The Skill detects your project language and applies the matching SDK instructions, or you can use cURL and raw HTTP when needed.

What is the recommended default model and configuration for Claude API integration?

The recommended default model for Claude API integration is `claude-opus-4-6` with adaptive thinking enabled. The Skill enforces these production-ready defaults along with safer patterns like streaming and structured outputs.

How do I implement tool use loops and agentic patterns with the Claude API?

Implement tool use loops and agentic patterns with the Claude API by setting up multi-step tool-orchestrated pipelines. The Skill provides guidance on manual agentic loops, tool runners, code execution, and web fetch/search concepts for complex workflows.

Does the Claude API support prompt caching and batch processing to reduce costs?

Yes, the Claude API supports prompt caching and batch processing to reduce costs. The Skill provides guidance on token counting, prompt caching for context reuse, and batch processing for non-time-sensitive workloads to optimize reliability and expenses.

How do I handle long conversations with the Claude API when context limits are reached?

Handle long conversations with the Claude API by using compaction to manage context limits. The Skill provides guidance on compaction for long conversations, error handling, and using the files API to maintain reliable multi-turn interactions.