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.

skills.sh installs: 301
GitHub stars: 488
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Iterative Coder

Iterative code refinement through structured plan → code → evaluate → refine cycles. Each cycle runs objective checks (lint, tests) and self-evaluation, then diagnoses failures and plans targeted improvements. Reaches production quality in 3-8 iterations.

When to Use This Skill

Main agent delegates a code task prefixed with "MODE: MORE_EFFORT"
User selected "More Effort" mode for code generation
Task requires high code quality with verified correctness
Task involves complex implementation (5+ files, multiple modules)
You want to iterate on code quality rather than submit first-pass code
You mention "iterative refinement", "code quality loop", "plan-code-evaluate"

The Iteration Mindset

Code quality comes from fast feedback loops, not careful first attempts. A fast plan → code → evaluate → fix cycle beats spending 30 minutes on a "perfect" first implementation. The evaluate step reveals problems you cannot predict by thinking alone — lint errors, import failures, test regressions, and missing edge cases all surface immediately when you actually run the code.