Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
Source
Yongqi Tong, Pan Wang, Hang Wang, Jianshe Li, Xin Zhang, Jiang-Ming Yang, Wei Wu
Author
Yongqi Tong, Pan Wang, Hang Wang, Jianshe Li, Xin Zhang, Jiang-Ming Yang, Wei Wu
Date
Terms in this piece · Glossary
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Code2Skill mines active GitHub repos into a bank of over a million AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → skills groundingTying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.Full definition → in real executable code and verified by reconstruction, giving agents implementation-anchored procedural knowledge without needing prior trajectories.
articleFinSkillBench: Evaluating AI Agents and Domain Skills for Investment ManagementJermyn Zhen Yong Bek, Zhuang Qiang Bok, Zhongtian Sun
articleGrounded Checklist Partial Credit for Agent Skill TrajectoriesSuliu Qin, Lu Yin, Xilu Wang
articleWho Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill MaintenanceChen Shen, Estevam Hruschka