darwinian-evolver

You can optimize prompts automatically by running an LLM-driven evolution loop that applies a fitness evaluator and mutator across multiple iterations to iteratively improve your text. This Skill automates that process using OpenRouter or OpenAI models.

Yes, LLM evolution can tune regex patterns and SQL queries by defining an Evaluator and Mutator to guide optimization. The loop iteratively mutates and evaluates your patterns or queries to maximize fitness.

The evolution loop works by defining an Organism, Evaluator, and Mutator, then driving optimization across iterations. The LLM generates mutations, the Evaluator scores fitness, and the best candidates survive to the next generation.

Yes, you need a provider API key from OpenRouter or OpenAI to run LLM-based prompt evolution, along with Python 3.11+ and the upstream darwinian_evolver tool. The Skill ships a parrot_openrouter driver to connect.

The best way to improve small code snippets is using an LLM-guided evolution loop that scores code fitness and applies mutations across iterations. This Skill provides custom problem templates to tailor the evolutionary process to your domain.

Yes, you can experiment with different models for the evaluator and mutator by running the upstream darwinian_evolver tool via the OpenRouter driver. This allows testing various models to find the optimal configuration for your evolution task.