skills.rest
SESELOVSKYDarian
SESELOVSKYDarianCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

claude-api

Build, debug, and optimize applications using the Claude API and Anthropic SDKs.

Updated Mar 31, 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/SESELOVSKYDarian/Vase --skill claude-api-seselovskydarian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-api
Source: https://github.com/SESELOVSKYDarian/Vase/tree/main/.agents/skills/claude-api
Command: npx skills add https://github.com/SESELOVSKYDarian/Vase --skill claude-api-seselovskydarian

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Developers integrating Claude into their applications often guess SDK method signatures, use deprecated parameters, or pick the wrong API surface, leading to broken code, cache misses, and wasted tokens. This Skill provides verified, language-specific guidance for building with the Claude API and Anthropic SDKs. ## Core Features & Use Cases - Multi-language SDK guidance: Language detection and dedicated references for Python, TypeScript, Java, Go, Ruby, C#, PHP, and raw cURL/HTTP. - Surface selection: Decision trees for choosing between single API calls, tool-use workflows, and Managed Agents (server-managed stateful agents with hosted workspaces). - Production patterns: Prompt caching, adaptive thinking, effort control, streaming, compaction, structured outputs, batch processing, and the Files API. - Use Case: A developer adding tool use to a TypeScript app gets correct @anthropic-ai/sdk code with the tool runner, prompt caching breakpoints, and streaming — without hallucinated method names. ## Quick Start Ask the assistant to add a Claude API call with tool use and prompt caching to your project file, and it will detect your language and generate verified SDK code.

Frequently Asked Questions about claude-api

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

FAQPage Schema
How do I add tool use to a Claude API application?▼

Define tools via decorators, Zod schemas, or JSON schema, then use the SDK's tool runner for automatic loop handling, or write a manual loop checking stop_reason for tool_use. Language-specific examples exist for Python, TypeScript, Java, Go, Ruby, and PHP.

Which Claude model should I use for my application?▼

Default to claude-opus-4-6 with adaptive thinking for complex tasks. Use the exact model ID strings without date suffixes, and query the Models API for live capability and context-window information.

Does the Claude API support prompt caching?▼

Yes, prompt caching uses cache_control breakpoints with prefix matching; any byte change in the prefix invalidates everything after it. Keep stable content first, place volatile content last, and verify hits via usage.cache_read_input_tokens.

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

No, Managed Agents is first-party only and unavailable on Bedrock, Vertex AI, or Microsoft Foundry. On third-party providers, use the Claude API with tool use for all agent workloads.

Why does my Claude API request fail with budget_tokens?▼

budget_tokens is deprecated on Opus 4.6 and Sonnet 4.6 and causes errors. Use thinking with type adaptive instead, which lets Claude dynamically decide thinking depth without a fixed token budget.

When should I use raw HTTP instead of the Anthropic SDK?▼

Use raw HTTP only when the user explicitly requests cURL/REST, the project is shell-based, or no official SDK exists for the language. Never mix raw HTTP with SDK calls in languages that have an official SDK.

Related Skills

Explore More Software Engineering Skills→
nerinanarinenerinanarine

claude-api

Integrate Claude API or Anthropic SDKs into applications for NLP tasks.

Community
Advanced
LLM-Dev-OpsLLM-Dev-Ops
1

V3 MCP Optimization

Optimize CLAUDE MCP v3 server startup latency and response times.

Official
Advanced
kiurakkukiurakku
15

llm-integration

Integrate LLM APIs into production applications with streaming, cost control, and fallbacks.

Community
Advanced
bereniketechbereniketech

multi-model-model-agnostic-platforms

Route tasks across multiple AI models with cost-aware fallback strategies.

Community
Advanced