Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SkillNet: Create, Evaluate, and Connect AI Skills

Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Xin Xu, Tongtong Wu, Kun Wang, Yang Liu, Zhen Bi, Jungang Lou, Yuchen Eleanor Jiang, Hangcheng Zhu, Gang Yu, Haiwen Hong, Longtao Huang, Hui Xue, Chenxi Wang, Yijun Wang, Zifei Shan, Xi Chen, Zhaopeng Tu, Feiyu Xiong, Xin Xie, Peng Zhang, Zhengke Gui, Lei Liang, Jun Zhou, Chiyu Wu, Jin Shang, Yu Gong, Junyu Lin, Changliang Xu, Hongjie Deng, Wen Zhang, Keyan Ding, Qiang Zhang, Fei Huang, Ningyu Zhang, Jeff Z. Pan, Guilin Qi, Haofen Wang, Huajun Chen

TL;DR

SkillNet is introduced, an open infrastructure designed to create, evaluate, and organize AI skills at scale that formalizes skills as evolving, composable assets and provides a robust foundation for agents to move from transient experience to durable mastery.

Abstract

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To overcome this limitation, we introduce SkillNet, an open infrastructure designed to create, evaluate, and organize AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit. Experimental evaluations on ALFWorld, WebShop, and ScienceWorld demonstrate that SkillNet significantly enhances agent performance, improving average rewards by 40% and reducing execution steps by 30% across multiple backbone models. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.

SkillNet: Create, Evaluate, and Connect AI Skills

TL;DR

SkillNet is introduced, an open infrastructure designed to create, evaluate, and organize AI skills at scale that formalizes skills as evolving, composable assets and provides a robust foundation for agents to move from transient experience to durable mastery.

Abstract

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To overcome this limitation, we introduce SkillNet, an open infrastructure designed to create, evaluate, and organize AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit. Experimental evaluations on ALFWorld, WebShop, and ScienceWorld demonstrate that SkillNet significantly enhances agent performance, improving average rewards by 40% and reducing execution steps by 30% across multiple backbone models. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.
Paper Structure (37 sections, 5 figures, 2 tables)

This paper contains 37 sections, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Agent Skills
  3. SkillNet
  4. Overview
  5. Skill Creation.
  6. Skill Evaluation.
  7. Skill Analysis.
  8. Open Resources.
  9. Skill Ontology
  10. Skill Taxonomy.
  11. Skill Relation Graph.
  12. Skill Package Library.
  13. Skill Creation
  14. From Human Experience to Skill Abstraction
  15. Data-Driven Skill Filtering and Consolidation
  16. ...and 22 more sections

Figures (5)

  • Figure 1: Overview of SkillNet. SkillNet organizes large-scale agent skills into a structured skill network, modeling rich relations (e.g., similarity, composition, and dependency), supporting multi-dimensional evaluation, and providing unified interfaces for skill discovery, creation, and analysis.
  • Figure 2: End-to-end Pipeline of SkillNet. SkillNet transforms heterogeneous user inputs and open internet resources into executable skills through automated skill creation and multi-dimensional evaluation, and organizes high-quality skills into a structured network to support search, download, analysis, and contribution.
  • Figure 3: The Skill Ontology for SkillNet. It consists of three levels: the Skill Taxonomy (top) defines functional categories; the Skill Relation Graph (middle) models inter-skill dependencies and semantic associations; and the Skill Package Library (bottom) organizes skills into modular, task-oriented bundles.
  • Figure 6: Performance comparison across diverse methods and models. The results illustrate that SkillNet consistently outperforms React and Few-shot baselines, achieving significantly higher average rewards (top) and reduced average steps (bottom) across ALFWorld, WebShop, and ScienceWorld.
  • Figure 7: Example of SkillNet application scenarios. The framework decomposes user task into actionable steps (top), with representative skill acquisition and multi-dimensional evaluations for Science and Coding scenarios (bottom).