skills.rest
markwang2658
markwang2658COMMUNITY
Explore all skills by this author →
GitHub

darwinian-evolver

Evolve prompts, regex, SQL, or code through iterative Darwinian optimization.

31|3|Updated May 7, 2026
Search Tags:#automation#optimization#llm#evolution#prompt-engineering#evolver
One-click install
npx skills add https://github.com/markwang2658/hermes-windows-native --skill darwinian-evolver-markwang2658
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: darwinian-evolver
Source: https://github.com/markwang2658/hermes-windows-native/tree/main/hermes-agent/optional-skills/research/darwinian-evolver
Command: npx skills add https://github.com/markwang2658/hermes-windows-native --skill darwinian-evolver-markwang2658

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Evolve prompts, regex, SQL, or code using a Darwinian evolution loop to improve artifacts. It provides a self-contained framework with an Organism, Evaluator, and Mutator to drive iterative refinement of candidate artifacts.

Core Features & Use Cases

  • End-to-end evolution loop: evolve artifacts by defining Organism, Evaluator, and Mutator, and run iterative improvements.
  • OpenRouter/parrot integration: execute LLM calls via a replaceable driver to compare and optimize artifacts.
  • Custom problem templates: copy and adapt templates to define new problems and evaluation strategies for domain-specific tasks.

Quick Start

Run the provided driver to start an evolution run using OpenRouter for your custom problem.

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 engineering for iterative optimization?▼

Automate prompt engineering using a Darwinian evolution loop to iteratively refine candidate artifacts. You define an Organism, Evaluator, and Mutator to drive self-contained improvements without manual trial and error.

What's the best way to evolve regex and SQL queries automatically?▼

Evolve regex and SQL queries automatically by applying a Darwinian evolution loop with custom evaluation strategies. The framework mutates candidate artifacts and evaluates them iteratively to improve domain-specific outputs.

Do I need an OpenAI API key to run the evolution loop?▼

Yes, you need an API key for the OpenRouter or OpenAI provider to execute LLM calls within the evolution loop. The driver uses these providers to compare and optimize artifacts during iterative refinement.

Can I use this evolution framework for optimizing small code blocks?▼

Yes, you can optimize small code blocks by defining them as organisms within the evolution framework. The Mutator and Evaluator components drive iterative improvements suited for research and development workflows.

What Python environment is required for running a Darwinian evolver?▼

Running the Darwinian evolver requires Python 3.11 or higher, along with uv and git installed. The skill includes a driver and examples to demonstrate end-to-end artifact evolution within this setup.

How does the evolution mechanism work for improving prompts?▼

The evolution mechanism works by applying a Darwinian loop where an Organism represents the prompt, an Evaluator scores its performance, and a Mutator generates variations. This iterative cycle continuously improves the artifact over generations.

Related Skills

Explore More Software Engineering Skills→
vikrant-projectvikrant-project
2

darwinian-evolver

Evolve prompts, regex patterns, SQL queries, and code snippets via AI-driven search.

Community
Advanced
labs21-devlabs21-dev
28

meta-prompting

Design, repair, or evaluate prompt artifacts with clear structure and constraints.

Official
Intermediate
heysuhasheysuhas
2

darwinian-evolver

Evolve prompt templates, regex patterns, and code snippets via LLM-driven search.

Community
Advanced
nadicodeainadicodeai

darwinian-evolver

Evolve prompts, regex, SQL, and code via mutation and fitness evaluation.

Official
Advanced