evor-run

Automate machine learning model evolution setup and testing via GoalContracts.

1|Updated Jul 6, 2026
One-click install
npx skills add https://github.com/it-dainb/oh-my-evor --skill evor-run
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evor-run
Source: https://github.com/it-dainb/oh-my-evor/tree/main/skills/evor-run
Command: npx skills add https://github.com/it-dainb/oh-my-evor --skill evor-run

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Evor-run resolves and launches the AI-evolved ML model generation and testing processes without manual intervention.

Core Features & Use Cases

  • Launch Evolution Mission: Validates GoalContract, sets up active run state, and initiates the AI model evolution loop.
  • GoalContract Handling: Checks for existence and validates GoalContract before initiating a new run.
  • Autonomous Execution: Delegates to evor skill for model evolution without human-in-the-loop.
  • Run-Watch Mode: Offers Attended and Scheduled run-watch modes to manage interactive sessions and unattended runs.

Quick Start

Use the evor-run skill to initiate an evolution run for the mission with the given mission-id or run-id: /evor-run [mission-id or run-id].

Frequently Asked Questions about evor-run

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

FAQPage Schema
How do I automate machine learning model evolution without manual intervention?

To automate machine learning model evolution, you can use a skill that validates GoalContracts and initiates an autonomous AI model evolution loop. This resolves and launches ML model generation and testing processes without human-in-the-loop interaction.

What is a GoalContract in autonomous ML model evolution?

A GoalContract in autonomous ML model evolution is a specified requirement file that must exist and pass validation before initiating a new run. It defines the objectives for the AI-evolved model generation and testing processes.

How do I start an autonomous ML run using a mission ID?

To start an autonomous ML run, execute the command with your specific mission-id or run-id. The system validates the GoalContract, sets up the active run state, and delegates to the core evolution skill to begin.

Can I run unattended ML model evolution sessions on a schedule?

Yes, you can run unattended ML model evolution sessions using the Scheduled run-watch mode. This mode manages autonomous runs without interactive sessions, alongside an Attended mode for interactive sessions.

What happens if the GoalContract validation fails before an ML run?

If the GoalContract validation fails, the ML run will not initiate. The system checks for existence and validates the GoalContract before setting up the active run state to ensure robust integrity checks.

Does autonomous model evolution require environment variables for setup?

Yes, autonomous model evolution utilizes environment variables for setup and configuration. These variables are used to configure the run environment before delegating to the core model evolution skill.