darwinian-evolver

Optimize text-based artifacts through an LLM-driven evolutionary search loop.

Updated Jun 25, 2026

Search Tags:#automation #research #optimization #llm #evolution #prompt-engineering

Ready to run

npx skills add https://github.com/Rheasilvia/hermes-desktop --skill darwinian-evolver-rheasilvia

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the challenge of manually tuning prompts, regex patterns, or code snippets by automating the search for high-performing variants through an iterative evolutionary loop.

Core Features & Use Cases

Automated Optimization: Uses an LLM-driven evolutionary loop to mutate and score candidates against a defined fitness function.
Custom Problem Definition: Provides a flexible framework to define organisms, evaluators, and mutators for specific domains like prompt engineering or SQL generation.
Use Case: If you have a prompt that is underperforming, use this skill to evolve it against a set of test cases until it achieves a high success rate on your specific evaluation criteria.

Quick Start

Use the darwinian-evolver skill to optimize the prompt template in custom_problem_template.py by running the evolution loop for 5 iterations.

Frequently Asked Questions about darwinian-evolver

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

FAQPage Schema

How do I automate prompt optimization using an evolutionary loop?▼

Automated prompt optimization uses an LLM-driven evolutionary loop to mutate and score text artifacts against a defined fitness function. This automates the search for high-performing variants, replacing manual tuning with iterative refinement against measurable criteria.

What is the best way to optimize underperforming prompts against test cases?▼

Optimizing underperforming prompts requires defining organisms, evaluators, and mutators for your specific domain. You evolve the prompt template by running the evolution loop for multiple iterations until it achieves a high success rate on your evaluation criteria.

Do I need Python 3.11 and git to run LLM-driven evolutionary search?▼

Yes, executing LLM-driven evolutionary search requires Python 3.11, git, uv, and an LLM provider API key. These dependencies are necessary to run the mutation and evaluation cycles for automated refinement.

Can I use evolutionary search to optimize regex patterns and code snippets?▼

Yes, evolutionary search optimizes text-based artifacts like regex patterns and code snippets. It applies mutators and evaluators to these artifacts, scoring candidates against a fitness function to automate refinement for research and development tasks.

How does an LLM mutate and score candidates in a custom fitness evaluation?▼

An LLM mutates and scores candidates by applying a custom mutator to alter text, then using an evaluator to measure performance against your fitness function. Candidates achieving high scores survive, driving iterative optimization across generations.

What are the limitations of using LLM-driven mutation for SQL generation tasks?▼

LLM-driven mutation for SQL generation requires defining a strict fitness function to evaluate query accuracy. Without measurable evaluation criteria and sufficient API calls for multiple iterations, the evolutionary loop may fail to converge on optimal logic.