One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents

The paper investigates how co-installed coding‑agent skills can conflict, causing the model to choose a similar skill over the intended one based solely on name and description. An empirical study of 20,947 repositories uncovered 822,109 candidate skill pairs, with 312 confirmed conflicts tested across three models, revealing that nearly one in four installed skills is overridden by a similar skill. Key findings include that conflicts often involve normative skills, that the installed skill loses core functions in about one‑fifth of runs, and that the first skill read determines the outcome, suggesting benchmarks should evaluate exclusive core functions and platforms should guard the initial read.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• benchmarks