- Setup Claude Code: https://github.com/anthropics/claude-code
- Quick Starts: https://github.com/anthropics/anthropic-quickstarts
- Claude Cookbooks: https://github.com/anthropics/anthropic-cookbook
- Claude Developer Docs: https://docs.anthropic.com/en/home
- Claude User Guides: https://docs.anthropic.com/en/docs/welcome
- Claude API Reference: https://docs.anthropic.com/en/api/getting-started
- Claude Release Notes: https://docs.anthropic.com/en/release-notes/overview
- Claude Code: https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview
- Claude Desktop: https://claude.ai/download
- Claude MCP:
- MCP Overview: https://github.com/modelcontextprotocol
- MCP Quick Start | Claude Desktop Users: https://modelcontextprotocol.io/quickstart/user
- ChatGPT Overview: https://openai.com/index/chatgpt/
The prompt engineering pages in this section have been organized from most broadly effective techniques to more specialized techniques. When troubleshooting performance, we suggest you try these techniques in order, although the actual impact of each technique will depend on your use case.
- Prompt generator
- [Be clear and direct]
- [Use examples (multishot)]
- [Let Claude think (chain of thought)]
- Use XML tags
- [Give Claude a role (system prompts)]
- [Prefill Claude’s response]
- [Chain complex prompts]
- [Long context tips]
- Claude Prompt Library