skills.rest
2233admin
2233adminCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

shinka-run

Orchestrate ShinkaEvolve CLI batch evolution runs with configurable generations and overrides.

Updated Apr 10, 2026
Search Tags:#automation#cli#evolutionary-algorithms#task-dir#batch-run#shinka-evolve#results-dir
One-click install
npx skills add https://github.com/2233admin/ShinkaEvolve-fork --skill shinka-run-2233admin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: shinka-run
Source: https://github.com/2233admin/ShinkaEvolve-fork/tree/main/skills/shinka-run
Command: npx skills add https://github.com/2233admin/ShinkaEvolve-fork --skill shinka-run-2233admin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Run a batch of program mutations using ShinkaEvolve's CLI interface from a task directory that contains evaluate.py and initial.* files, enabling rapid async evolution experiments with explicit results directories and parameter overrides.

Core Features & Use Cases

  • Orchestrates CLI runs for batch evolution against a task directory.
  • Validates task structure (evaluate.py and initial.*) and preflight CLI arguments.
  • Supports configurable generations, results directory, and per-run overrides for automation and agent workflows.
  • Useful when agents need to launch quick evolution runs without scaffolding from scratch or managing low-level CLI plumbing.

Quick Start

Execute a batch with shinka_run using your task directory, a dedicated results directory, and generation/config overrides.

Frequently Asked Questions about shinka-run

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

FAQPage Schema
How do I automate batch evolutionary algorithm runs from the command line?▼

Batch evolution experiments require a task directory containing evaluate.py and initial.* files. This Skill validates that structure, orchestrates ShinkaEvolve CLI runs with configurable generations, and writes structured outputs to a specified results directory.

What do I need in my task directory to start batch evolution experiments?▼

To start batch evolution experiments, your task directory must contain evaluate.py and initial.* files. The Skill validates this structure during preflight checks before orchestrating asynchronous CLI runs with configurable generation counts.

Can I override CLI parameters for asynchronous evolution runs?▼

Yes, you can override CLI parameters for asynchronous evolution runs. The Skill supports configurable generation counts, custom results directories, and explicit per-run parameter overrides without requiring manual low-level CLI plumbing.

Does this approach validate environment settings before launching evolution batches?▼

Yes, environment checks and CLI option validation are performed before launching evolution batches. The Skill also requests user confirmations between batches to ensure preflight arguments and task structures meet requirements before asynchronous execution.

What is the best way to run quick program mutations without scaffolding from scratch?▼

The best way to run quick program mutations without scaffolding is launching ShinkaEvolve batch runs via CLI. This Skill orchestrates validation, environment checks, and asynchronous execution against your task directory to produce structured outputs automatically.

Related Skills

Explore More Software Engineering Skills→
SakanaAISakanaAI
1.3k

shinka-run

Execute batch evolution tasks via the ShinkaEvolve CLI with explicit run arguments.

Official
Intermediate
tbroadleytbroadley

read-inspect-eval

Extract samples, messages, events, and metrics from Inspect AI .eval logs.

Community
Intermediate
qdzshqdzsh
12

gsd-headless

Orchestrate GSD project workflows via headless CLI commands with JSON events.

Community
Advanced
haitao2016haitao2016

evolutionary-game-systems

Implement genetic algorithms for game content generation and NPC AI evolution.

Community
Advanced