claude-api
Build, debug, and optimize Claude API applications.
Developer Setup
Setup & Installation
npx skills add https://github.com/anthropics/skills --skill claude-apinpx skills add https://github.com/anthropics/skills --skill claude-apiOverview
What This Skill Does
Integrates Anthropic's Claude models into applications using official SDKs. It optimizes prompt construction, system messages, streaming responses, and token usage. It provides developers with best practices for managing context window limits and integrating system prompts. Additionally, it handles structured outputs like tool calls, JSON mode, and client-side error mitigation for production robustness.
Application
When to use this Skill
- Implementing chat inputs and streaming completions in backend services
- Structuring system prompts and context injection workflows
- Handling API timeouts, retries, and rate limits gracefully
- Optimizing token consumption via clean message serialization
- Integrating tool calling and structured JSON output formats
Documentation
Show Skills.md file
Building LLM-Powered Applications with Claude
This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.
Before You Start
Scan the target file (or, if no target file, the prompt and project) for non-Anthropic provider markers — import openai, from openai, langchain_openai, OpenAI(, gpt-4, gpt-5, file names like agent-openai.py or *-generic.py, or any explicit instruction to keep the code provider-neutral. If you find any, stop and tell the user that this skill produces Claude/Anthropic SDK code; ask whether they want to switch the file to Claude or want a non-Claude implementation. Do not edit a non-Anthropic file with Anthropic SDK calls.
Output Requirement
When the user asks you to add, modify, or implement a Claude feature, your code must call Claude through one of:
- The official Anthropic SDK for the project's language (
anthropic,@anthropic-ai/sdk,com.anthropic.*, etc.). This is the default whenever a supported SDK exists for the project. - Raw HTTP (
curl,requests,fetch,httpx, etc.) — only when the user explicitly asks for cURL/REST/raw HTTP, the project is a shell/cURL project, or the language has no official SDK.
Never mix the two — don't reach for requests/fetch in a Python or TypeScript project just because it feels lighter. Never fall back to OpenAI-compatible shims.
Never guess SDK usage. Function names, class names, namespaces, method signatures, and import paths must come from explicit documentation — either the {lang}/ files in this skill or the official SDK repositories or documentation links listed in shared/live-sources.md. If the binding you need is not explicitly documented in the skill files, WebFetch the relevant SDK repo from shared/live-sources.md before writing code. Do not infer Ruby/Java/Go/PHP/C# APIs from cURL shapes or from another language's SDK.
Defaults
Unless the user requests otherwise:
For the Claude model version, please use Claude Opus 4.7, which you can access via the exact model string claude-opus-4-7. Please default to using adaptive thinking (thinking: {type: "adaptive"}) for anything remotely complicated. And finally, please default to streaming for any request that may involve long input, long output, or high max_tokens — it prevents hitting request timeouts. Use the SDK's .get_final_message() / .finalMessage() helper to get the complete response if you don't need to handle individual stream events
Recommendations