Here are my tips for getting the most out of Claude Code, including a custom status line script and Claude Code running itself in a container. Also includes the dx plugin: skills for everyday dev workflows.
📺 Quick demo - See some of these tips in action with a multi-Claude workflow and voice input:
- Tip 0: Customize your status line
- Tip 1: Learn a few essential slash commands
- Tip 2: Talk to Claude Code with your voice
- Tip 3: Break down large problems into smaller ones
- Tip 4: Using Git and GitHub CLI like a pro
- Tip 5: AI context is like milk; it's best served fresh and condensed!
- Tip 6: Getting output out of your terminal
- Tip 7: Set up terminal aliases for quick access
- Tip 8: Proactively compact your context
- Tip 9: Complete the write-test cycle for autonomous tasks
- Tip 10: Cmd+A and Ctrl+A are your friends
- Tip 11: Invest in your own workflow
- Tip 12: Search through your conversation history
- Tip 13: Multitasking with terminal tabs
- Tip 14: Git worktrees for parallel branch work
- Tip 15: Manual exponential backoff for long-running jobs
- Tip 16: Claude Code as a writing assistant
- Tip 17: Markdown is the s**t
- Tip 18: Preserve links when pasting
- Tip 19: Isolated environments for long-running risky tasks
- Tip 20: The best way to get better at using Claude Code is by using it
- Tip 21: Fork and half-clone conversations
- Tip 22: Use realpath to get absolute paths
- Tip 23: Understanding CLAUDE.md vs Skills vs Slash Commands vs Plugins
- Tip 24: Interactive PR reviews
- Tip 25: Claude Code as a research tool
- Tip 26: Mastering different ways of verifying its output
- Tip 27: Claude Code as a DevOps engineer
- Tip 28: Keep CLAUDE.md simple and review it periodically
- Tip 29: Claude Code as the universal interface
- Tip 30: It's all about choosing the right level of abstraction
- Tip 31: Use auto mode
- Tip 32: Control Claude Code from your phone
- Tip 33: Learn to use artifacts
- Tip 34: Write lots of tests (and use TDD)
- Tip 35: Be braver in the unknown; iterative problem solving