Experiment Iterative Coder

This is a structured code quality loop: plan, implement, run lint and tests, score the results, then refine based on what actually broke. It decomposes complex tasks into phases and iterates up to 3 times per phase with a 10 iteration global limit. The scoring combines objective signals (ruff, pytest exit codes) with self-assessment, using hard caps to prevent inflated scores when tests or lint fail. Use it when the main agent delegates with "MODE: MORE_EFFORT" or you need verified correctness over speed. The core insight is sound: fast feedback beats careful first attempts, and you can't predict import errors or edge cases by thinking alone.

Install to Claude Code

npx -y skills add evoscientist/evoskills --skill experiment-iterative-coder --agent claude-code