Iterative Code Evolution

Replaces ad-hoc trial-and-error fixing with an ANALYZE-PLAN-MUTATE-VERIFY-SCORE-ARCHIVE loop logged to .evolution/log.json.

Tested · Works

Test report

Verdict
Tested · Works
Score
8.4/10
Tested
Jul 16, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 20, 2026 · e6d5f9d

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 16, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Real A/B on a crashing CSV-row parser: the ad-hoc baseline and the skill-guided fix landed on the same 3/5-passing code, but the skill's archived .evolution/log.json correctly diagnosed the 2 remaining failures as valid-per-spec (missing email, empty row) rather than bugs -- a concrete process win even though the code diff itself tied.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 6/10
  • Docs & honesty 5/5

What Iterative Code Evolution does

A prompting methodology (no bundled scripts) that disciplines multi-round code improvement: label each component Working/Fragile/Broken/Redundant/Missing, cap changes at 3 per cycle, link every change to an observed failure, score against the parent variant, and archive lessons learned so later cycles don't repeat dead ends. Triggers when code needs iterative optimization, persistent-bug debugging, or multi-round design evolution -- not for one-shot generation or mechanical refactors.

How to install Iterative Code Evolution

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Iterative Code Evolution

  • /iterative-code-evolution Replaces ad-hoc trial-and-error fixing with an ANALYZE-PLAN-MUTATE-VERIFY-SCORE-ARCHIVE loop logged to .evolution/log.json.

It also activates on plain-language prompts like these:

  • Keep improving this CSV parser through scored iterative fix cycles
  • This bug keeps recurring, let's log each fix attempt and its result
  • Iterate on this function with a capped, verified improvement loop

Frequently asked questions

Is the Iterative Code Evolution skill free?
Yes. The skill itself is free from aaronjmars/iterative-code-evolution. SkillProof publishes the install command and an independent test verdict at no cost.
Does Iterative Code Evolution work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Real A/B on a crashing CSV-row parser: the ad-hoc baseline and the skill-guided fix landed on the same 3/5-passing code, but the skill's archived .evolution/log.json correctly diagnosed the 2 remaining failures as valid-per-spec (missing email, empty row) rather than bugs -- a concrete process win even though the code diff itself tied.
What is the Iterative Code Evolution SkillProof Score?
8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.
How do I install Iterative Code Evolution?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Iterative Code Evolution with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.