Posted on :: Updated on ::

Potential use cases

  • Implement features
  • Refactor this subsystem
  • Research this library
  • Set up this service
  • Write tests, run them, fix failures
  • Compare approaches , and propose a plan
  • Troubleshoot issues and fix them

Tips

  • Always use better model for planing: Opus > Sonnet.
  • If you’re working with some data, first run do some data sanity runs (with ai) and resolve inconsistencies before proceeding with plan.

Skills/Tools

  • Caveman
  • spec-kit
  • For larger features, enable CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
    • 1 reviewer agent
    • 1 QE agent writes tests
  • diffity

Sources

  • [[]]