Skip to content
Preprint

SkillSeam: Six Principles for Auditing Agent Skill Collections

Sep 2026 · 0 citations · 23 references
Computer Science

TL;DR

SkillSeam is introduced, a method that audits the relationships through which individual skill files become a system, and perturbs six design principles: persistence gradient, system coherence, regime gating, orthogonal coverage, flow, and granularity discipline.

Abstract

A folder of competent skills is not yet a reliable system. Skills rarely fail alone; they fail at the seams of a collection. As an agent's skill library grows, procedures compete for attention, aliases double-load, boundaries blur, and poorly sized skills turn routing errors into task failures. We introduce SkillSeam, a method that audits the relationships through which individual skill files become a system. It maps each collection-level principle to a failure mechanism, its strongest observable, and a controlled perturbation test. From one sealed skill system, SkillSeam perturbs six design principles: persistence gradient, system coherence, regime gating, orthogonal coverage, flow, and granularity discipline. Crucially, each principle is evaluated through the channel its failure mechanism predicts rather than through accuracy alone. Flattening the persistence hierarchy increases loaded-skill tokens by 60%; a dangling anchor raises total tokens by 64% and shifts accuracy by -3.1pp; with skill count and context size held fixed, replacing an unrelated control with a synonymous alias raises noncanonical routes from 0/32 to 15/32 and flips half of matched paraphrase pairs; in a candidate-ownership audit, overlapping lanes raise reported ownership conflicts from 0/16 to 14/16; bland triggers drive routing conflicts from 3/32 to 30/32 and inflate loaded-skill tokens 3.7x; and one granularity mis-mix produces the largest accuracy drop, -12.5pp. These outcomes turn six pieces of authoring advice into testable system properties without treating every probe as confirmation. We release the byte-differenced variants, task slices, rollups, and a one-screen design checklist so that other skill systems can measure the same failure channels.

View source

Similar papers

SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale

Anthropic's Agent Skills package reusable procedural know-how for an LLM agent into SKILL.md directories, and open-source aggregations have grown past 230,000 skills, making selection rather than authoring the bottleneck. The standing answer in the literature outsources selection to the agent itself: an LLM-mediated re...

Guanqun Yang, Wen-Long Zhang, Tian Shi et al. · 3 citations
Preprint Oct 2026

SkillBrowser: Selective Skill Exposure for Scalable Skill-Using Agents

SkillBrowser is proposed, a Meta-Skill-managed framework that enables an agent to identify current capability needs, formulate targeted queries, and selectively load skills on demand, and demonstrates the viability of Meta-Skill-managed SSE for scalable skill repositories.

Jin Ye, Yi-Fan Jiang, Lan-Zhe Guo · 0 citations
Review Sep 2026

Evaluating Agent Skills for Version-Specific Plugin Migration: A Retrospective Study

The study contributes a traceable evaluation that connects aggregate reward to contract-level evidence and judge sensitivity, together with concrete review checks for migration advice, together with concrete review checks for migration advice.

Bei-Ming Liu, Hai-Hao Li, Min-Jie Chen et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance

This work mine the full commit histories of five public AI-skill repositories, a purposive sample of AI-tooling organizations, and a purposive sample of AI-tooling organizations from October 2025 to June 2026, and codes each edit with pre-registered governance, operation, and trigger-evidence codebooks.

Chen Shen, Estevam Hruschka · 0 citations
#artificial intelligence Review Oct 2026

An Empirical Study of Agent Skills'Downstream Utility

Agent Skills package procedural guidance and resources for reuse, but a relevant Skill does not necessarily improve task performance. Existing studies characterize Skill content and evaluate downstream performance, yet provide limited explanations of how utility depends on content, execution configuration, and multi-Sk...

Yu Cheng, De-Hai Zhao, Zhong-Xin Liu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

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

Coding agents are extended with agent skills, directories whose SKILL.md tells the model when and how to perform a task. Because skills come from independent sources (teams, developers, plugins, copied collections), an installed skill can be co-installed with a similar skill doing the same job, and the model picks betw...

Chao-Liang Yan, Zi-Hao Xu, Yue-Kang Li et al. · 1 citation · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.