From claude-evolve
Runs autonomous evolutionary optimization on code blocks marked in seed programs using Claude models for mutations and user-defined evaluators for fitness scoring. Use for performance tuning.
npx claudepluginhub samuelzxu/claude-evolve --plugin claude-evolveThis skill uses the workspace's default tool permissions.
Launch an evolution run that optimizes code using Claude Code models as mutation operators.
Conducts Socratic interview with ambiguity scoring across goal, program, evaluation, and constraints to generate initial.py, evaluate.py, config.json for evolution tasks.
Runs propose-evaluate-iterate loop to optimize and evolve AI agent performance using LangSmith evaluations and git worktrees for isolation. Requires .evolver.json setup.
Starts, monitors, or rewinds evolutionary development loops that iteratively refine ontologies and criteria using Ouroboros MCP tools until convergence. For evolving complex project specs.
Share bugs, ideas, or general feedback.
Launch an evolution run that optimizes code using Claude Code models as mutation operators.
/evolve [config.json]
/evolve --init initial.py --eval evaluate.py --generations 50
initial.py: Seed program with # EVOLVE-BLOCK-START / # EVOLVE-BLOCK-END markersevaluate.py: Evaluator script that returns metrics and correctnessThe run is autonomous -- it proceeds without interaction until complete or stopped.