darwinian-evolver

Automated prompt optimization uses evolutionary search loops to mutate and evaluate candidate prompts against a measurable fitness score. This Skill runs those cycles automatically, ranking mutated prompt versions to improve LLM task success rates without manual trial and error.

Evolutionary search can optimize regex patterns and SQL queries by applying automated mutation and evaluation cycles. This Skill evaluates mutated artifacts against defined fitness scores, automatically searching for better-performing versions of your code snippets and queries.

Evolutionary code improvement involves mutating, evaluating, and ranking candidate artifacts against a measurable fitness score through iterative search loops. This Skill applies this mechanism to automatically refine prompts, code snippets, and queries until performance peaks.

Evolutionary optimization requires a Python execution environment, supported model API credentials, and evolutionary evaluation logic to function. You must also define organisms, evaluators, and mutators using the provided templates for your specific optimization tasks.

Defining a fitness score for evolving prompts requires creating custom evaluators using the provided templates and drivers. This Skill expects you to establish measurable evaluation criteria so the evolutionary loop can automatically rank mutated candidate artifacts by performance.

Evolutionary search for code and prompt optimization requires measurable fitness scores and custom evaluator definitions to function effectively. Artifacts must be small enough for automated Python execution evaluation, and you need supported model API credentials to run the LLM mutation workflows.