claude-apilisted

Claude API and Anthropic SDK reference for model selection, pricing, parameters, streaming, tool use, MCP, agents, caching, token counting and migrations. Use whenever the request names Claude, Anthropic, Opus, Sonnet, Haiku, the anthropic packages or Claude model IDs; when choosing or debugging a Claude API feature; or when an LLM-shaped task names no provider. Before editing, inspect the target for another provider. Do not use this skill when the user or project explicitly targets OpenAI, Gemini, Llama, Mistral, Cohere or Ollama; ask before switching an existing non-Anthropic implementation to Claude. Verify time-sensitive model, price and limit claims against current official documentation.
trugurpala/divan · ★ 0 · AI & Automation · score 69

Install: claude install-skill trugurpala/divan

# 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: 1. **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. 2. **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.