Do Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Histories
Source
Shuyan Huang, Kai Du, Andrew Lan
Author
Shuyan Huang, Kai Du, Andrew Lan
Published
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
Why it matters
Anyone investing in per-developer AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → memory or personalized agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → files should see evidence that pooling beats personalization on the same data.
articleRethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple RoundsYuxuan Liu, Zhaochen Su, Yuhao Zhang, Jiahe Guo, Zhongwei Xie, Huihao Jing, Lingyun Xie, Qing Zong, Yauwai Yim, Zhixiong Zhang, Haoran Li, Yangqiu Song
articleTowards a Risk Assessment of Malicious Skill Files in Coding AgentsRui Yang, Michael Fu, Kla Tantithamthavorn, Chetan Arora, Joey Chua
videoSkills as the Interface to Agentic ProductsAI Engineer