Claude Code Prompts

Claude Code is Anthropic's official AI-powered CLI tool that helps developers write, edit, debug, and understand code directly in the terminal.

Run `claude` in your terminal from any project directory to start an interactive session with the AI assistant.

Claude Code can read files, write code, run tests, and execute shell commands autonomously, completing complex multi-step tasks end-to-end.

Navigate to your project root before starting Claude Code — it will automatically have context of all files in the working directory.

"Read [filename] and explain what it does" or simply "Read [filename]" before asking questions about its contents.

Describe the bug and what you expected: "This function returns null when the user has no orders, but it should return an empty array instead."

Be specific about the goal: "Refactor this function to use async/await instead of callbacks" or "Extract this logic into a separate helper function."

"Write unit tests for [function/file] covering edge cases including null inputs, empty arrays, and boundary values."

Running `/help` inside Claude Code displays available slash commands, keyboard shortcuts, and usage information.

`/clear` resets the conversation context, clearing all prior messages and starting a fresh session.

`/compact` compresses the conversation history to save context space while preserving the essential information.

`/cost` displays the token usage and estimated API cost for the current Claude Code session.