REPOGEO 报告 · LITE
sheldonresearch/ProG
默认分支 main · commit cc59eb9b · 扫描时间 2026/5/30 19:46:43
星标 584 · Fork 74
行动计划告诉你下一步要做什么——按影响力排序、可直接复制粘贴的修改。品类可见性是真正的 GEO 测试:当用户向 AI 提一个不带品牌、本应让 sheldonresearch/ProG 浮出水面的问题时,AI 是真的推荐了你,还是推荐了你的竞品?客观检查验证 AI 引擎最先权衡的那些元数据信号。自指检查判断 AI 是否还认识你的名字。
行动计划 — 可复制粘贴的修复
3 条由 gemini-2.5-flash 生成、按优先级排序的修改。修完后请把对应条目标记为完成。
- highreadme#1Add a 'Why ProG-V2?' section to the README
原因:
复制粘贴的修复Add a new section titled 'Why ProG-V2?' after the introduction, explicitly stating its unique value proposition for graph prompting and benchmarking compared to general GNN libraries. For example: 'While general GNN libraries like PyTorch Geometric and DGL provide foundational graph operations, ProG-V2 is purpose-built as a unified Python library and reproducible benchmark specifically for graph prompt learning. It offers a modular architecture for prompt strategies, comprehensive coverage, and standardized benchmarking utilities that are not found in general-purpose GNN frameworks.'
- mediumabout#2Add a homepage URL to the repository's About section
原因:
复制粘贴的修复Add a relevant URL (e.g., project documentation, official website, or the GitHub repo itself) to the 'homepage' field in the repository's About section.
- lowreadme#3Enhance README with a quick start or examples section
原因:
复制粘贴的修复Add a 'Quick Start' or 'Getting Started' section immediately after the 'What's New' or 'Architecture' section, demonstrating a minimal working example of implementing a graph prompt learning workflow. This could include a simple code snippet for defining a prompt strategy and running a benchmark.
本次扫描解析到的品类 GEO 通道:google/gemini-2.5-flash, deepseek/deepseek-v4-flash
品类可见性 — 真正的 GEO 测试
向 google/gemini-2.5-flash 提出的不带品牌问题。AI 推荐了你,还是推荐了别人?
各模型使用同一组问题 — 切换标签对比回答与排名。
- PyTorch Geometric (PyG) · 被推荐 2 次
- Deep Graph Library (DGL) · 被推荐 2 次
- Spektral · 被推荐 2 次
- Graph Neural Network Library (GNN-Lib) · 被推荐 1 次
- NetworkX · 被推荐 1 次
- 品类问题What Python libraries are available for implementing graph prompt learning workflows?你:未被推荐AI 推荐顺序:
- PyTorch Geometric (PyG)
- Deep Graph Library (DGL)
- Spektral
- Graph Neural Network Library (GNN-Lib)
- NetworkX
AI 推荐了 5 个替代方案,却始终没点名 sheldonresearch/ProG。这就是要补上的差距。
查看 AI 完整回答
- 品类问题Seeking a robust framework for benchmarking different graph neural network prompting strategies.你:未被推荐AI 推荐顺序:
- PyTorch Geometric (PyG)
- Deep Graph Library (DGL)
- Spektral
- Graph Neural Network Library (GNNA)
- GraphGym
AI 推荐了 5 个替代方案,却始终没点名 sheldonresearch/ProG。这就是要补上的差距。
查看 AI 完整回答
客观检查
针对 AI 引擎最看重的元数据信号的规则审计。
- Metadata completenesswarn
建议:
- README presencepass
自指检查
当被直接问到你时,AI 是否还知道你的仓库存在?
- Compared to common alternatives in this category, what is the core differentiator of sheldonresearch/ProG?passAI 明确点名了 sheldonresearch/ProG
AI 的回答可能信誓旦旦却是错的。请按事实核对:技术栈、目标人群、差异化点是不是和你实际的对得上?
- If a team adopts sheldonresearch/ProG in production, what risks or prerequisites should they evaluate first?passAI 明确点名了 sheldonresearch/ProG
AI 的回答可能信誓旦旦却是错的。请按事实核对:技术栈、目标人群、差异化点是不是和你实际的对得上?
- In one sentence, what problem does the repo sheldonresearch/ProG solve, and who is the primary audience?passAI 明确点名了 sheldonresearch/ProG
AI 的回答可能信誓旦旦却是错的。请按事实核对:技术栈、目标人群、差异化点是不是和你实际的对得上?
嵌入你的 GEO 徽章
把这个徽章贴进 sheldonresearch/ProG 的 README。每次重新扫描都会自动更新,并跳到最新报告——是「我在乎 AI 可发现性」最简单的公开证明。
[](https://repogeo.com/zh/r/sheldonresearch/ProG)<a href="https://repogeo.com/zh/r/sheldonresearch/ProG"><img src="https://repogeo.com/badge/sheldonresearch/ProG.svg" alt="RepoGEO" /></a>订阅 Pro,解锁深度诊断
sheldonresearch/ProG — 轻量扫描仍免费;本卡列出 Pro 相对轻量的深度额度。
- 深度报告每月 10 次
- 无品牌品类查询5,轻量 2
- 优先行动项8,轻量 3