In Agent-related practice, I found that blindly piling on a large number of skills does not improve agent performance, and the number of skills cannot be equated with execution quality. Therefore, I integrated high-quality Skill resources recognized by the industry and built this repository for my own research projects and experimental development.
Latest release 2.0.0 — hello-scholar-2 v2.0.0版本更新 · 6 Aug 2026
2 files for Codex, OpenCode and Claude Code: hello-scholar AGENTS.md, hello-scholar CLAUDE.md — 2,363 tokens loaded in every session.
AGENTS.md A 2,360 tok CLAUDE.md A 3 tok These files are Tx1207/hello-scholar's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.