Modular Code

This teaches Claude to organize Python code into maintainable modules, with a practical heuristic that 150-500 lines is the sweet spot for both human comprehension and AI context windows. It's opinionated about when to split (anything over 1000 lines is too large, 2000+ causes real tooling problems) and gives concrete patterns like splitting by domain concept or I/O boundary. The guidance is sensible but not dogmatic. It acknowledges that some domain-specific modules like scipy internals might reasonably exceed these limits, and warns against over-modularizing into "package hell." Useful if you're working on a codebase that's grown organically and you need clear criteria for when refactoring is worth the effort.

Install to Claude Code

npx -y skills add parcadei/continuous-claude-v3 --skill modular-code --agent claude-code