Agent skill · Backend & API

using-anthropic-platform

Claude SDK development with Messages API, Tool Use, Extended Thinking, streaming, and prompt caching

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill using-anthropic-platform --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 9 KB
Bundled scripts: none
Path: skills/ai-llm/using-anthropic-platform/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Anthropic Claude SDK - Quick Reference ## When to Use Load this skill when: - `anthropic` package in `requirements.txt` or `pyproject.toml` - `@anthropic-ai/sdk` in `package.json` dependencies - `ANTHROPIC_API_KEY` environment variable present - User mentions "Anthropic", "Claude", or Claude models **For detailed patterns**: See [REFERENCE.md](./REFERENCE.md) --- ## Table of Contents 1. [Claude Models](#claude-models-january-2026) 2. [Quick Start](#quick-start) 3. [Messages API Essentials](#messages-api-essentials) 4. [Streaming](#streaming) 5. [Tool Use (Function Calling)](#tool-use-function-calling) 6. [Extended Thinking](#extended-thinking) 7. [Vision](#vision) 8. [Prompt Caching](#prompt-caching) 9. [Error Handling](#error-handling) 10. [Platform Features](#platform-features) 11. [Further Reading](#further-reading) --- ## Claude Models (January 2026) | Model | Context | Max Output | Thinking | Best For | |-------|---------|------------|----------|----------| | `claude-opus-4-5-20251101` | 200K | 32K | Yes | Maximum intelligence | | `claude-sonnet-4-20250514` | 200K | 64K | Yes | Complex reasoning, coding | | `claude-3-5-sonnet-20241022` | 200K | 8K | No | Standard tasks | | `

What's inside
Steps it walks through
  1. When to Use
  2. Table of Contents
  3. Claude Models (January 2026)
  4. Model Selection
  5. Pricing (per 1M tokens)
  6. Quick Start
  7. Python
  8. TypeScript
  9. Async Python
  10. Messages API Essentials
  11. With System Prompt
  12. Multi-Turn Conversation
  13. Common Parameters
  14. Streaming
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the using-anthropic-platform skill do?

Claude SDK development with Messages API, Tool Use, Extended Thinking, streaming, and prompt caching

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill using-anthropic-platform --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going