claude-api

Build and migrate Claude API integrations across multiple SDKs.

Updated Mar 17, 2026
One-click install
npx skills add https://github.com/GayanKavinda/gayankavinda.github.io --skill claude-api-gayankavinda
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-api
Source: https://github.com/GayanKavinda/gayankavinda.github.io/tree/main/skills/skills/claude-api
Command: npx skills add https://github.com/GayanKavinda/gayankavinda.github.io --skill claude-api-gayankavinda

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps teams build, migrate, and troubleshoot Claude API integrations without guessing model IDs, request shapes, or beta feature requirements.

Core Features & Use Cases

  • Build Claude API applications in Python, TypeScript, Java, Go, Ruby, C#, PHP, or raw cURL.
  • Implement streaming, tool use, prompt caching, structured outputs, compaction, files, and managed agents correctly.
  • Migrate existing apps across model versions and remove deprecated parameters safely.
  • Use it for chat experiences, agent workflows, long-running sessions, and production SDK integrations.

Quick Start

Use the claude-api skill to inspect your project, identify the target language, and generate the correct Claude API integration or migration plan.

Frequently Asked Questions about claude-api

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

FAQPage Schema
How do I migrate my Claude API integration to a new model version?

Claude API streaming works by configuring your Anthropic SDK to parse Server-Sent Events, enabling real-time message generation. You can implement this across Python, TypeScript, Java, Go, Ruby, C#, PHP, or cURL to receive tokens incrementally as they are produced.

Does the Anthropic SDK support prompt caching and tool use simultaneously?

Yes, the Anthropic SDK supports combining prompt caching and tool use within the same request. You can configure your Claude API integration to send cached system prompts alongside tool definitions, optimizing latency and token costs for complex agent workflows.

What are the exact Anthropic model IDs required for Claude API requests?

Exact Anthropic model IDs are mandatory for Claude API requests to route correctly and avoid failures. Using the correct model identifiers ensures your integration accesses the intended features like adaptive thinking, compaction, and managed agents without triggering deprecated parameter errors.

How do I implement long-running sessions and compaction with the Claude API?

Implementing long-running sessions and compaction involves managing context windows and using the API's compaction features to summarize conversation history. This prevents token limit overflows, ensuring your managed agents maintain context efficiently across extended chat experiences.

Why does my Claude API integration fail when using non-Claude provider code paths?

Your Claude API integration fails because the Anthropic SDK requires SDK-specific request shapes and avoids non-Claude provider code paths. You must ensure your implementation strictly follows Claude's messages API format for structured outputs and tool use to function correctly.