Borrowing it
Nothing to install: this file belongs to ZimoLiao/scholaraio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ZimoLiao/scholaraio/main/.claude/skills/research-gap/SKILL.mdgit clone --depth 1 https://github.com/ZimoLiao/scholaraioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zimoliao/scholaraio/research-gap)<a href="https://agentmods.dev/skills/zimoliao/scholaraio/research-gap"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/research-gap/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zimoliao/scholaraio/research-gap"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/research-gap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01291 |
| Opus 5.5 | $0.00012 | $0.00516 |
| Sonnet 5.5 | $0.00006 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
research-gap scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究空白识别
从工作区文献中系统性地发现研究空白和开放问题。
前提
用户必须指定一个 workspace(--ws NAME),且工作区中应有足够数量的论文(建议 10+ 篇)。
报告语言由用户指定(中文 / English)。
执行逻辑
1. 全局扫描
scholaraio ws show <name> # 论文列表
scholaraio topics # 主题聚类(如已建模)
对工作区论文做 L2 扫描(标题 + 摘要),建立领域地图。show 命令会自动展示已有的 notes.md 历史笔记,优先复用已有发现。
2. 多维度分析
维度 1:主题覆盖度
scholaraio topics # 全库主题分布
scholaraio topics --topic <ID> # 各主题下的论文
工作区论文是否集中在某几个主题?哪些相关主题缺乏覆盖?
维度 2:时间趋势
按年份统计工作区论文分布,识别:
- 哪些方向在近几年论文激增(热点)
- 哪些方向论文渐少(可能已成熟或被放弃)
- 哪些方向有早期工作但近年无跟进(潜在空白)
直接用 Python 读取 configured papers library 下的 */meta.json 做统计分析。
维度 3:方法论对比
扫描工作区论文的方法部分(L3-L4),绘制方法论矩阵:
scholaraio show <paper-id> --layer 3 # 结论中通常提及方法
- 哪些方法被广泛使用?
- 哪些方法组合尚未被尝试?
- 某方法在 A 问题上成功,是否可迁移到 B 问题?
维度 4:引用图谱空洞
scholaraio shared-refs "<id1>" "<id2>" # 共同引用
scholaraio refs "<id>" # 参考文献
scholaraio citing "<id>" # 被引论文
- 哪些论文互相引用但观点矛盾?(未解决的争议)
- 哪些论文被大量引用但缺乏后续验证/复现?
- 哪些关键参考文献不在工作区中?(可能是盲区)
维度 5:论文自述的 Future Work
加载工作区中高引论文的 L3(结论),提取作者自己提出的未来方向:
scholaraio show <paper-id> --layer 3
这些 future work 是否已有人做了?交叉搜索验证:
scholaraio usearch "<future work 关键词>"
3. 输出报告
生成结构化的研究空白报告,保存到 workspace/<name>/research-gaps.md。
对每个发现的空白,按类型分类:
| 空白类型 | 含义 | 示例 |
|---|---|---|
| 知识空白 | 某个现象/问题尚无人研究 | "高 Re 下的 X 效应尚未被测量" |
| 方法空白 | 已有结论但方法存在缺陷或局限 | "现有研究均为 RANS,缺乏 DNS 验证" |
| 矛盾空白 | 不同研究给出矛盾结论 | "A 组报告正效应,B 组报告负效应" |
| 迁移空白 | 某方法/发现尚未被推广到相关领域 | "该方法在 2D 有效,3D 尚未尝试" |
| 规模空白 | 只有小规模/受限条件的结果 | "仅低 Re 数据,工程 Re 下未验证" |
报告结构:
- 领域现状概述(2-3 段)
- 已识别的研究空白(按优先级排序)
- 空白类型 + 描述
- 支撑证据(哪些论文暗示了这个空白)
- 潜在研究问题
- 可行性评估(数据/方法/资源是否可及)
- 未解决的争议(如有)
- 建议的下一步
量化辅助:必要时编写 Python 代码从 meta.json 批量提取数据,做统计图表(年份分布、方法频次、参数范围覆盖等),用可视化支撑空白发现。
分析笔记持久化:对深度分析过的论文,必须通过 CLI 将关键发现写入笔记:
scholaraio show "<paper-id>" --append-notes "## YYYY-MM-DD | <workspace> | research-gap
- 关键发现"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 117 lines · 31 tokens per session scan A 3b482e2763d7
research-gap is a skill published in the GitHub repository ZimoLiao/scholaraio (584 stars, last pushed 10d ago), licensed MIT. It adds 31 tokens to every session and 1,291 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
research-gap compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research-gapZimoLiao/scholaraio | Skill | 584 | 10d ago | MIT | A | 31 | Claude Code |
| infrastructure-validationdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| provenance-dagdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 103 | Claude Code, Codex |
| scientific-connectorsdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 87 | Claude Code, Codex |
| infrastructure-search-literaturedocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 123 | Claude Code, Codex |
| template-academic-paper-reviewerdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 52 | Claude Code, Codex |
| template-reproducibility-auditdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 70 | Claude Code, Codex |