Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Improved description with detailed value proposition and use cases
What This Skill Does
Connects EvoAgentX, an open-source multi-agent framework, to OpenClaw. Workflows built with this skill can automatically improve over time using evolutionary optimization. Supports TextGrad, AFlow, and MIPRO optimization strategies alongside the Genome Evolution Protocol (GEP).
Evolutionary optimization removes the need to manually tune prompts, workflow structure, or tool selection across iterations.
When to use it
- Automatically improving a research automation pipeline across multiple iterations
- Optimizing prompt strategies in a multi-step reasoning workflow
- Migrating a static agent workflow to one that self-improves from task feedback
- Running tool selection optimization across web search and file I/O agents
- Evaluating workflow performance against accuracy metrics without manual tuning
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Create and evolve a research workflow targeting 95% accuracy over 10 iterations
- 1Runs the create-workflow CLI command to scaffold a ResearchWorkflow template
- 2User edits the generated Python file to define workflow logic and agent steps
- 3Initializes EvolutionEngine with iteration count and evaluation criteria
- 4EvoAgentX runs optimization passes using TextGrad, AFlow, or MIPRO algorithms
- 5Returns an optimized workflow object with encoded genome patterns
An evolved workflow meeting the accuracy threshold with optimized prompts and structure