SkillWiki: A Living Knowledge Infrastructure for Agent Skills
2026-06-15 • Computation and Language
Computation and Language
AI summaryⓘ
The authors created SkillWiki, a platform that helps organize and improve agent skills in a way similar to how Wikipedia manages knowledge and GitHub manages software. SkillWiki turns different types of information into reusable skills linked to where they came from, making it easier to track and update them. Their demonstration shows how skills are created, managed, explored, and improved over time within this system. This approach aims to help skills, knowledge, and user experience develop together in one shared place.
agent skillsknowledge infrastructureSkillWikiskill lifecycleprovenanceknowledge ingestionskill governanceskill evolutionreusable skill assetsexecution experience
Authors
Dingcheng Huang, Yuda Ding, Bingshuo Liu, Qingbin Liu, Xi Chen, Jiang Bian, Hongliang Sun, Zhiying Tu, Dianhui Chu, Xiaoyan Yu, Dianbo Sui
Abstract
While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki is a living knowledge infrastructure that supports the organization, grounding, and continuous evolution of agent skills by transforming heterogeneous knowledge into reusable skill assets linked to their originating evidence. Our demonstration presents the complete skill lifecycle, from knowledge ingestion and skill production to provenance-aware exploration, governance, and execution-driven evolution. SkillWiki highlights a future in which knowledge, skills, and execution experience co-evolve within a shared infrastructure. The live demonstration and source code are publicly available at https://github.com/Huangdingcheng/SkillWiki.