Abstract
Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incorporating relevant procedural and domain knowledge. Expert-authored skills are expensive to produce, and the resulting artifacts are not optimized for the specific model that consumes them, whose failure modes can vary with version, scale and training. In addition, emerging tasks may fall outside the scope of existing skill libraries, creating a need to develop new skills before curated training data become available. Recent works have explored automated skill optimization through reflection, but they require a curated, in-distribution training set, which users might not always have. To address these limitations, we present Prompt2Skill, a framework that builds skills from natural-language task description alone. From the prompt, the system derives a task specification, discovers or synthesizes datasets, and refines the skill in a closed loop of reflective editing. Across four domains spanning question answering, reading comprehension, spreadsheet manipulation, and mathematical reasoning, Prompt2Skill consistently outperforms the direct prompting baseline, achieving an average improvement of 10.8 across open-source and frontier models.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Ni, B., Li, L., Rossi, R. A., Dernoncourt, F., & Derr, T. (2026). Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions. https://omanscience.com/en/articles/prompt2skill-unsupervised-skill-optimization-from-natural-language-instructions
MLA 9
Ni, Bo, et al. "Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions." https://omanscience.com/en/articles/prompt2skill-unsupervised-skill-optimization-from-natural-language-instructions.
Chicago (author–date)
Ni, Bo, Li Li, Ryan A. Rossi, Franck Dernoncourt, and Tyler Derr. 2026. "Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions." https://omanscience.com/en/articles/prompt2skill-unsupervised-skill-optimization-from-natural-language-instructions.
Harvard
Ni, B., Li, L., Rossi, R. A., Dernoncourt, F. and Derr, T. (2026) 'Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions', Available at: https://omanscience.com/en/articles/prompt2skill-unsupervised-skill-optimization-from-natural-language-instructions.
Vancouver
Ni B, Li L, Rossi RA, Dernoncourt F, Derr T. Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions. https://omanscience.com/en/articles/prompt2skill-unsupervised-skill-optimization-from-natural-language-instructions
IEEE
B. Ni, L. Li, R. A. Rossi, F. Dernoncourt, and T. Derr, "Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions," https://omanscience.com/en/articles/prompt2skill-unsupervised-skill-optimization-from-natural-language-instructions.