Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents

K-Dense AI released Scientific Agent Skills, an open library of 163 procedural skills across 16 scientific areas including genomics, cheminformatics, and medical imaging, designed to help language-model agents perform defensible analyses by loading versioned instruction files on demand. The library, available at https://github.com/K-Dense-AI/scientific-agent-skills, includes reference material and runnable scripts but reports no task-level evaluation or host selection rate.

arXiv:2609.00065v1 Announce Type: new Abstract: A language-model agent asked to analyse an experiment will usually return working code. Whether the analysis is defensible is a different question. A defensible analysis depends on procedural choices: which test the field accepts, which identifier namespace is authoritative, and which caveats must accompany a result. We present Scientific Agent Skills, an open library of 163 such procedures in 16 areas of practice, including genomics, cheminformatics, medical imaging, study design and scientific communication. Each skill is a directory built around a versioned, human-readable instruction file. An agent loads the file only when a task calls for it; the directory often also contains reference material and runnable scripts. We report no task-level evaluation and no host selection rate. Openly licensed and available at https://github.com/K-Dense-AI/scientific-agent-skills.