skills.rest
danielbere1973
danielbere1973COMMUNITY
Explore all skills by this author →
GitHub

claude-api

Implements Claude API and Anthropic SDK integrations across eight programming languages.

Updated May 15, 2026
Search Tags:#streaming#tool use#llm integration#claude api#prompt caching#anthropic sdk#managed agents
One-click install
npx skills add https://github.com/danielbere1973/promoar --skill claude-api-danielbere1973
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-api
Source: https://github.com/danielbere1973/promoar/tree/main/.agents/skills/claude-api
Command: npx skills add https://github.com/danielbere1973/promoar --skill claude-api-danielbere1973

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Building applications on the Claude API requires accurate, current knowledge of model IDs, pricing, SDK bindings, streaming, tool use, prompt caching, and beta features — details that are easy to get wrong from memory. This Skill provides authoritative, language-specific reference documentation so generated code uses correct SDK calls, current model strings, and proper parameter configurations. ## Core Features & Use Cases - Multi-language SDK guidance: Language detection routes to dedicated references for Python, TypeScript, Java, Go, Ruby, C#, PHP, and cURL, covering messages, streaming, tool use, thinking, and structured outputs. - Model and parameter accuracy: Cached model tables with exact IDs and pricing, plus rules for adaptive thinking, effort levels, compaction, and prompt caching prevent hallucinated API usage. - Managed Agents and migration support: Dedicated guides for server-managed agents, the ant CLI, model migration workflows, and subcommands like /claude-api migrate. - Use Case: A developer asks to add streaming tool use to a TypeScript app; the Skill detects the language, loads the TypeScript reference, and produces code using the correct @anthropic-ai/sdk tool runner with claude-opus-4-8. ## Quick Start Ask the assistant to add a Claude API feature to your project, for example implement streaming chat with tool use in your Python application.

Frequently Asked Questions about claude-api

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

FAQPage Schema
How do I add Claude API streaming to my application?▼

Use the official Anthropic SDK for your language and call the streaming messages endpoint, then accumulate events with helpers like get_final_message or the stream accumulator. The Skill provides per-language streaming examples for Python, TypeScript, Java, Go, Ruby, C#, PHP, and cURL.

Which Claude model should I use for my project?▼

Default to claude-opus-4-8 unless the user explicitly names another model such as Sonnet or Haiku. The Skill includes a current model table with exact IDs, context windows, and pricing, plus a Models API lookup for live capability checks.

Does the Anthropic SDK support tool use in Go or Java?▼

Yes, both SDKs support beta tool use with automatic tool runners: Go uses BetaToolRunner in the toolrunner package, and Java uses annotated classes with BetaToolRunner. The Skill documents manual loop patterns as well for fine-grained control.

Can I use Managed Agents on Amazon Bedrock or Vertex AI?▼

No, Managed Agents is only available on the first-party API and Claude Platform on AWS. On Bedrock, Vertex AI, or Microsoft Foundry, use the Claude API with client-side tool use to build agents instead.

Why does my prompt caching show zero cache read tokens?▼

Zero cache reads indicate a silent invalidator such as timestamps in the system prompt, unsorted JSON, or a changing tool set breaking the prefix match. The Skill's prompt caching reference includes an audit checklist and breakpoint placement patterns.

How do I migrate existing Claude code to a newer model?▼

Invoke the migrate subcommand, which loads the model migration guide and walks through scope confirmation, file classification, and per-target breaking changes. It covers transitions to Opus 4.8, 4.7, and Fable 5 including thinking and effort parameter changes.

Related Skills

Explore More Software Engineering Skills→
Buntyarora97Buntyarora97

ai-integrations-anthropic

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

Community
Intermediate
awsaws
2.3k

agents-optimize

Configure evaluators, observability, and cost governance for AgentCore agents.

Official
Advanced
TakMczkTakMczk
1

cost-aware-llm-pipeline

Route LLM API calls by task complexity with budget tracking and retry logic.

Community
Advanced
The-InterdependencyThe-Interdependency
1

gemini-api

Access Google Gemini models via the google-genai SDK or OpenAI-compatible endpoint.

Official
Advanced