ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬
ShinkaEvolve is a framework that combines large language models with evolutionary algorithms to improve scientific programs through repeated code variation and evaluation. Researchers and developers use it to explore and optimize code for scientific discovery. Its catalogue skills guide coding agents through setup, conversion, evolution, and result inspection.
Skill Claude CodeCodex
Convert an existing codebase in the current working directory into a ShinkaEvolve task directory by snapshotting the relevant code, adding evolve blocks, and generating evaluate.py plus Shinka runner/config files. Use when the user wants to optimize existing code with Shinka instead of creating a brand-new task from a…
Skill Claude CodeCodex
Load top-performing Shinka programs into agent context using shinka.utils.loadprogramstodf, and emit a compact Markdown bundle for iteration planning.
Skill Claude CodeCodex
Run existing ShinkaEvolve tasks with the shinkarun CLI from a task directory (evaluate.py + initial. ). Use when an agent needs to launch async evolution runs quickly with required --resultsdir, generation count, and strict namespaced keyword overrides.
Skill Claude CodeCodex
Create ShinkaEvolve task scaffolds from a target directory and task description, producing evaluate.py and initial. (multi-language). Use when asked to set up new ShinkaEvolve tasks, evaluation harnesses, or baseline programs for ShinkaEvolve.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: