claude-code-guide

原文涵盖的主题

• Claude Code Guide
• Purpose
• Configuration (CLAUDE.md)
• Template (General)
• Advanced Features
• Thinking Keywords
• Debugging
• Best Practices

To provide a comprehensive reference for configuring and using Claude Code (the agentic coding tool) to its full potential. This skill synthesizes best practices, configuration templates, and advanced usage patterns. When starting a new project, create a CLAUDE.md file in the root directory to guide the agent. Use these keywords in your prompts to trigger deeper reasoning from the agent: "Think step-by-step" "Analyze the root cause" "Plan before executing" "Verify your assumptions" If the agent is stuck or behaving unexpectedly: 1. Clear Context: Start a new session or ask the agent to "forget previous instructions" if confused. 2. Explicit Instructions: Be extremely specific about paths, filenames, and desired outcomes. 3. Logs: Ask the agent to "check the logs" or "run the command with verbose output". 1. Small Contexts: Don't dump the entire codebase into the context. Use grep or find to locate relevant files first. 2. Iterative Development: Ask for small changes, verify, then proceed. 3. Feedback Loop: If the agent makes a mistake, correct it immediately and ask it to "add a lesson" to its memory (if supported) or CLAUDE.md. Based on Claude Code Guide by zebbern.