# SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown

**Published:** October 6, 2026
**Author:** Yuxuan Liu, Haoran Li, Yuhao Zhang, Jiahe Guo, Hongyu Luo, Wenbin Hu, Huihao Jing, Kawai Chung, Junle Chen, Changxuan Fan, Qing Zong, Lingyun Xie, Yangqiu Song
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/skillscriptbench-benchmarking-self-evolution-of-executable-agent-skill-p

Executable Agent Skills combine natural-language instructions and scripts into reusable packages for LLM agents, and revising them requires fixing errors without breaking correct behavior. Existing benchmarks do not systematically distinguish documentation repair, script repair,…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.04008)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*