anthropic-api-prolisted

## Overview The Anthropic API exposes Claude models via the Messages API: a clean messages-in, message-out interface with best-in-class tool use, prompt caching (the cost story for long contexts), and extended thinking for hard reasoning. Claude's strengths — careful instruction-following, long-context handling, and reliable tool calling — shape how you should use it. This skill covers the Messages API properly: message construction, tool use patterns, prompt caching for cost control, extended thinking, and production practices. ## When to use - Calling the Claude Messages API. - Implementing tool use (function calling). - Reducing costs with prompt caching. - Using extended thinking for complex reasoning. - Streaming responses with tool use. - Choosing between Claude models (Opus/Sonnet/Haiku). - Migrating from OpenAI-style APIs. ## Core concepts - **Messages API.** `POST /v1/messages`: `model`, `max_tokens` (required), `system`, `messages` (user/assistant turns). Stateless — you manage conversation history. Clean and explicit; no legacy baggage. - **Model tiers.** Opus (frontier capability), Sonnet (the workhorse — intelligence per dollar), Haiku (fast/cheap for simple tasks). Sonnet is the default choice; Opus for the hardest problems; Haiku for high-volume simple work. - **System prompts.** Separate `system` parameter (not a message) — supports caching and keeps instruction hierarchy clean. Long, detailed system prompts are where Claude shines; invest in them. - **T