Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
ScienceClaw is an agent system for scientific work that completes tasks as typed, executable workflows and turns replay-verified improvements into reusable skills and operators. It is intended for AI-assisted research across natural and social science disciplines. The catalogue entries are its skills and instruction for use with the system.
1 file for GitHub Copilot: ScienceClaw copilot.instructions.md — 574 tokens loaded in every session.
.github/instructions/copilot.instructions.md A 574 tok These files are beita6969/ScienceClaw's own configuration — they tell GitHub Copilot how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.