SkillWiki: A Living Knowledge Infrastructure for Agent Skills
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 11 of its 20 references that are in the map. First posted on arXiv 15 Jun 2026.
Builds on
11 of 20 references.
References · 11
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
- 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
- 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 142
- 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 115
- 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 76
- 2026MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluationcited by 27
- 2026WebXSkill: Skill Learning for Autonomous Web Agentscited by 24
- 2026From Context to Skills: Can Language Models Learn from Context Skillfully?cited by 19
- 2026SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolutioncited by 18
- 2026Dynamic Skill Lifecycle Management for Agentic Reinforcement Learningcited by 12
Built on by
Citing papers per year: 2026: 2.
2 papers.