shinka-convert

Convert a codebase into a ShinkaEvolve task directory with evaluation and runner artifacts.

Updated May 20, 2026

Search Tags:#automation #codebase #convert #snapshot #task #evolve #shinka

Ready to run

npx skills add https://github.com/nhatnguyen1122/shinka --skill shinka-convert-nhatnguyen1122

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: shinka-convert
Source: https://github.com/nhatnguyen1122/shinka/tree/main/skills/shinka-convert
Command: npx skills add https://github.com/nhatnguyen1122/shinka --skill shinka-convert-nhatnguyen1122

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts an existing codebase in the current working directory into a ShinkaEvolve task directory by snapshotting relevant code, adding evolve blocks, and generating evaluate.py plus Shinka runner/config files. This enables turning a live project into a reproducible, evolvable task without starting from scratch.

Core Features & Use Cases

Snapshot and scaffold: captures the minimal runnable subset of the project and creates initial.py (or initial.<ext>), evaluate.py, run_evo.py, and shinka.yaml.
Sidecar task directory: places all artifacts in a dedicated folder (default shinka_task) for easy isolation.
Reusable evaluation: provides a stable evaluation entry point and configuration for the ShinkaEvolve pipeline.

Quick Start

Snapshot your current codebase and run the convert flow to generate the initial task artifacts in a new shinka_task directory.

Frequently Asked Questions about shinka-convert

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

FAQPage Schema

How do I convert an existing codebase into an evolvable task?▼

To convert an existing codebase into an evolvable task, snapshot your current working directory to generate a sidecar task directory containing initial.py, evaluate.py, run_evo.py, and shinka.yaml. This scaffolds a minimal runnable subset of your project for evolution.

What is a Shinka task directory and when do I need it?▼

A Shinka task directory is an isolated sidecar folder containing evaluation and runner artifacts for the ShinkaEvolve pipeline. You need it when you want to optimize legacy scripts or repositories through evolution instead of building a task from scratch.

Can I use Shinka to optimize legacy scripts without starting from scratch?▼

Yes, you can use Shinka to optimize legacy scripts without starting from scratch by snapshotting your current codebase. The conversion process creates a sidecar task directory with initial artifacts, enabling reproducible evolution of your existing project.

What files are generated when I snapshot a project for ShinkaEvolve?▼

Snapshotting a project for ShinkaEvolve generates evaluate.py, run_evo.py, shinka.yaml, initial.py, and a default shinka_task directory. These files provide a stable evaluation entry point and configuration for the evolution pipeline.

Do I need Shinka and PyYAML installed to scaffold a task directory?▼

Yes, you need Shinka and PyYAML installed as dependencies to scaffold a task directory. These packages enable the conversion script to snapshot code and generate the required YAML configuration and Python evaluation artifacts.

What are the limitations of converting a codebase snapshot for evolution?▼

A limitation of converting a codebase snapshot for evolution is that it only captures a minimal runnable subset of your project. Complex repositories may require manual adjustments to the generated evaluate.py and initial.py to ensure the evaluation pipeline runs correctly.