evor

Orchestrate machine learning model evolution through specialized sub-agents with integrity checks.

1|Updated Jul 6, 2026

Search Tags:#machine learning #Claude Code #evolution #autonomous #integrity check

Ready to run

npx skills add https://github.com/it-dainb/oh-my-evor --skill evor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: evor
Source: https://github.com/it-dainb/oh-my-evor/tree/main/skills/evor
Command: npx skills add https://github.com/it-dainb/oh-my-evor --skill evor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Task, and includes scripts (resource) components.

What problem does it solve?

Evor addresses the challenge of manually evolving machine learning models, providing an automated, secure, and verifiable process that reduces human error and ensures the integrity of results.

Core Features & Use Cases

Automated Machine Learning Evolution: Evor autonomously evolves machine learning models through an iterative process, proposing, critiquing, implementing, and evaluating candidates.
Integrity Checks: Ensures all reported gains are provably real, with no test-set leakage, reward hacking, or irreproducible flukes.
Use Case: Evor can be used to automatically optimize a machine learning model for a specific dataset, ensuring the best results are achieved with maximum transparency and reliability.

Quick Start

Start running the evor skill with the command /evor.

Frequently Asked Questions about evor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate machine learning model evolution and prevent test-set leakage?▼

Automated machine learning model evolution uses specialized sub-agents to iteratively propose, critique, and evaluate model candidates. Built-in integrity checks verify results to prevent test-set leakage, reward hacking, and irreproducible outcomes.

What is the best way to ensure reproducibility during autonomous ML model optimization?▼

Ensuring reproducibility during autonomous ML optimization requires orchestrating iterative evolution with strict data integrity checks. This verifies that reported performance gains are provably real and securely tracked throughout the process.

Do I need a Claude Code environment to run autonomous machine learning evolution tasks?▼

Yes, autonomous machine learning evolution requires a Claude Code environment. This environment is necessary for task spawning and artifact management, enabling the orchestration of specialized sub-agents during the evolutionary process.

How do I start running automated machine learning evolution with Claude Code?▼

To start running automated machine learning evolution, execute the `/evor` command in your Claude Code environment. This initiates the orchestration of sub-agents to propose, critique, and evaluate model candidates automatically.

Does automated model evolution work with Python libraries for integrity checks?▼

Yes, automated model evolution utilizes Python libraries to execute ML tasks and perform integrity checks. This ensures all reported gains are verified and reproducible within the orchestration workflow.

Why does autonomous ML evolution require task spawning and artifact management?▼

Autonomous ML evolution requires task spawning and artifact management to coordinate specialized sub-agents across iterative cycles. This orchestration ensures data integrity, tracks model candidates, and maintains reproducibility.