Tencent/SkillHone

107 stars · Last commit 2026-07-09

Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.

README preview

<h1 align="center">
  <img src="docs/assets/skillhone-logo-64.png" alt="SkillHone Logo" width="36" style="vertical-align: middle;">
  &nbsp;SkillHone-Skills
</h1>

<h3 align="center">
  Continual Agent Skill Evolution<br>
  Through Persistent Decision History
</h3>

<p align="center">
  <a href="https://arxiv.org/abs/2606.08671"><img src="https://img.shields.io/badge/arXiv-2606.08671-b31b1b?style=flat-square&logo=arxiv&logoColor=white" alt="arXiv"></a>
  <img src="https://img.shields.io/badge/Runtime-Claude%20Code%20%7C%20Codex%20%7C%20OpenClaw%20%7C%20Hermes-21b998?style=flat-square" alt="Runtimes">
</p>

<p align="center">
  <strong>English</strong> &bull;
  <a href="./docs/README.zh.md">简体中文</a>
</p>

View full repository on GitHub →