darwinian-evolver

Name: darwinian-evolver
Availability: InStock
Author: matlee0409

Evolve prompts, regexes, SQL queries, or code snippets with fitness-scored mutations.

Updated Aug 23, 2026

Search Tags:#llm #sql #evolution #regex #openrouter #code #prompt-engineering

Ready to run

npx skills add https://github.com/matlee0409/cronus --skill darwinian-evolver-matlee0409

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: darwinian-evolver
Source: https://github.com/matlee0409/cronus/tree/main/optional-skills/research/darwinian-evolver
Command: npx skills add https://github.com/matlee0409/cronus --skill darwinian-evolver-matlee0409

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jinja2, openai, and includes scripts (resource) components.

What problem does it solve?

Evolve and optimize prompts, regex, SQL queries, and small code snippets using an LLM-driven evolutionary search loop.

Core Features & Use Cases

End-to-end evolution: define Organism, Evaluator, and Mutator; run iterative improvements with fitness scoring and mutation-driven exploration.
OpenRouter/OpenAI integration: supports multiple providers via a built-in parrot driver and custom drivers.
Safe, reusable workflow: leverages trainable and holdout sets to guard against overfitting and provides snapshots for analysis.

Quick Start

Run the parrot_openrouter example to perform an iterative evolution of an artifact.

Frequently Asked Questions about darwinian-evolver

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I optimize prompts and code using an LLM-driven evolutionary loop?▼

You can optimize prompts and code by defining an Organism, Evaluator, and Mutator to run an LLM-driven evolutionary loop. This loop applies a fitness function to score candidates and proposes mutations to iteratively improve performance.

What is evolutionary search for regex and SQL queries?▼

Evolutionary search for regex and SQL queries is a process where an LLM mutates candidate expressions to improve their performance. It uses trainable and holdout sets to score fitness and guard against overfitting during iterative improvements.

Can I use OpenRouter and OpenAI providers to evolve my artifacts?▼

Yes, you can use OpenRouter and OpenAI providers to evolve artifacts. The framework includes a built-in parrot driver and supports custom drivers to integrate multiple LLM providers for the evolutionary search loop.

Do I need Python 3.11 to run an LLM-driven evolution workflow?▼

Yes, Python 3.11 or newer is required to run the LLM-driven evolution workflow. You also need an LLM provider like OpenRouter or OpenAI and the framework repository included in the skill.

How do I prevent overfitting when evolving prompts and regexes?▼

To prevent overfitting when evolving prompts and regexes, the framework leverages separate trainable and holdout sets. This safe workflow ensures candidates generalize well and provides snapshots for later analysis.

What is the best way to start evolving small code snippets with an LLM?▼

The best way to start evolving small code snippets is by running the parrot_openrouter example. This quick start example demonstrates how to perform an iterative evolution of an artifact end-to-end.