Founder of Baixing.com: My Experience with Claude Code in Fourteen Points

Author: Wang Jianshuo

A simple record of my experiences with Claude Code so far, purely personal exploration, not necessarily applicable to everyone.

1. Focus on one tool and use it intensively. I use Claude Code. I don't think it's better than Codex, but the ROI of comparing tools may not be high, even though it can create a false sense of achievement by articulating the differences convincingly.

2. Remember the most important shortcuts. Control+G opens the editor, which helps in writing longer content; Control+A, Control+E, Control+U are very useful shortcuts for quickly moving the cursor in the command line. Although they are not new in the AI era, they are as important as Control+C and Control+V when in use.

3. Use voice input. HoldSpeak is very helpful.

4. For a project, first write PROJECT.md, using a structured approach to jot down everything you think of in one go.

5. Claude agents are the default opening method.

6. Claude Code, github.com, and cloudflare.com are a perfect match, handing over all operations related to the build process, release process, and domain management to the infrastructure.

7. Separate what is written by humans and what is written by machines. Manually maintain the core CLAUDE.md, and do not read the .md or code written by Claude Code. Machines belong to machines, and humans belong to humans. Understand what AI writes by asking AI, not by looking at the source code.

8. Drag files into the Claude Code window—audio, video, documents, screenshots—if it's unclear, use Command+Shift+5 to take a screenshot and then drag it over, the fastest way.

9. Reconstruct the memory system. Centered around ~/.claude/CLAUDE.md, categorize and reference multiple memory files, requiring not to use the project's memory, and place all memory files in git, syncing to GitHub (private), so that your memory is permanent and accumulative, rather than scattered across each project.

10. Write Skills, and after each work session, ask Claude to "consolidate what has been learned into Skills"—it can do this automatically.

11. If possible, use ultracode to trigger dynamic workflows for complex tasks. Although it's expensive and slow, the results are guaranteed.

12. Accumulate skills along the way, and continuously reconstruct skills. Skills need to be stored in git.

13. Use the documentation from git as the output of the previous task and the input for the next task. Ensure there are clear handover documents between agents, rather than relying on context for continuity.

14. Treat Claude Code as a horse (or a person), not as a vehicle. A vehicle turns under your command, while a horse has its own ideas; we just need to set goals and boundaries. Its autonomous pathfinding feature is a characteristic, not a bug.

Does anyone have anything to add?