glm-5-3-flash-vision-rag
基于智谱GLM-5.3-Flash视觉大模型的PDF深度问答与检索(vision RAG)。当用户提到 PDF、文档、资料、报告、论文、电子书、手册、说明书,并想提问、查找、搜索、总结或理解其内容,或问"在哪一页"、"引用原文"、要页面截图时,使用本skill。支持扫描版、图表、表格、代码的视觉理解;回答带物理页码引用,并把命中页原图展示给用户。(GLM 版本;DeepSeek 版为 deepseek-v4-flash-vision-rag)
Source facts
- Repository
- liangdabiao/glm-5.3-flash-vision-rag
- Last source activity
- August 26, 2026 at 17:16
- Detected SKILL.md language
- Chinese
- Stars
- 16
- Forks
- 1
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.