shinka-run

Launch ShinkaEvolve batch runs via shinka_run CLI with validated task directories.

Updated May 20, 2026
One-click install
npx skills add https://github.com/nhatnguyen1122/shinka --skill shinka-run-nhatnguyen1122
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: shinka-run
Source: https://github.com/nhatnguyen1122/shinka/tree/main/skills/shinka-run
Command: npx skills add https://github.com/nhatnguyen1122/shinka --skill shinka-run-nhatnguyen1122

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Run existing ShinkaEvolve tasks with the shinka_run CLI from a task directory (evaluate.py + initial.<ext>). Use when an agent needs to launch async evolution runs quickly with required --results_dir, generation count, and strict namespaced keyword overrides.

Core Features & Use Cases

  • Batch-run ShinkaEvolve tasks from a directory containing evaluate.py and initial.* to start controlled evolution experiments.
  • Validate task readiness: ensures evaluate.py and initial.* exist before launching.
  • CLI-driven orchestration: configure generations, results path, and overrides with explicit --set properties for reproducible runs.
  • Suitable for agents or developers needing fast, asynchronous evolution runs with clear output directories.

Quick Start

Launch a batch evolution by pointing the CLI to your task directory and desired results directory, e.g., shinka_run --task-dir <task_dir> --results_dir <results_dir> --num_generations 40.

Frequently Asked Questions about shinka-run

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

FAQPage Schema
How do I run ShinkaEvolve tasks from a directory using the command line?

To run ShinkaEvolve tasks, point the shinka_run CLI to your prepared task directory containing evaluate.py and initial.* files, then specify the results directory and generation count to launch asynchronous evolution experiments.

What files are required to launch an evolutionary algorithm batch run?

Launching an evolutionary algorithm batch run requires a task directory containing both an evaluate.py script and an initial.* file, which the system validates before orchestrating the evolution experiment.

Can I configure generation count and output directory for automated evolution runs?

Yes, you can configure generation count and output directory for automated evolution runs by passing explicit parameters like --num_generations and --results_dir to the task runner CLI.

How do I ensure reproducible results when running evolutionary algorithms asynchronously?

You ensure reproducible results by using explicit --set properties for namespaced keyword overrides, defining strict results directories, and specifying generation counts when launching batch evolution runs.

Why does my batch evolution run fail before starting?

Your batch evolution run fails before starting if the task directory lacks the required evaluate.py script or initial.* file, as the system validates task readiness before launching any orchestration.

What is the best way to automate multiple evolutionary algorithm experiments quickly?

The best way to automate multiple evolutionary algorithm experiments quickly is using a CLI task runner that validates directory readiness and orchestrates asynchronous batch runs with explicit configuration overrides.