Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Lex669/LumericalFDTD-skill --skill paper-summarizergit clone --depth 1 https://github.com/Lex669/LumericalFDTD-skillWrote 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/lex669/lumericalfdtd-skill/paper-summarizer)<a href="https://agentmods.dev/skills/lex669/lumericalfdtd-skill/paper-summarizer"><img src="https://agentmods.dev/badge/skills/lex669/lumericalfdtd-skill/paper-summarizer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00132 | $0.01540 |
| Opus 5 | $0.00066 | $0.00770 |
| Sonnet 5 | $0.00026 | $0.00308 |
| Haiku 4.5 | $0.00013 | $0.00154 |
Grade A, and why
paper-summarizer 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 8d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
论文总结与图表详解器
对用户提供的PDF学术论文进行深度总结，核心特色是对论文中每一个图表进行详细解释——不只是描述图表展示什么，更要解释图表背后的物理/工程含义、与论文核心论点的关系、以及图表本身的质量。
输入处理
接受任一形式的论文输入：
- PDF文件路径 — 用 Read 工具直接读取（PDF支持多模态，可同时看到文字和图表）
- Arxiv URL — 用 WebFetch 获取摘要和PDF链接
- DOI — 通过
doi.org解析后用 WebFetch 获取 - 直接粘贴文本 — 用户直接提供的论文内容（此时图表需用户额外提供截图）
扫描版/OCR版PDF提取质量有限，提醒用户并尽力解读可见内容。
Token 预算管理
论文分析可能消耗大量上下文。按论文规模选择策略：
| 论文规模 | 策略 |
|---|---|
| 短论文（≤10页，<15图） | 一次性全量读取，逐个图表精读。无需分批。 |
| 中等论文（11-20页，15-30图） | 分 2 批：方法+实验 → 结果+讨论+图表。每批输出对应章节。 |
| 长论文（>20页，>30图） | 分 3-4 批。先读前 2 页建立全局认知，再按章节分批。每批输出后清空上下文。图表数量超过 30 个时优先保证正文图表完整覆盖，补充材料图表标注"建议手动查阅"。 |
分批信号
遇到以下任一情况时主动切换到分批发：
- PDF 页数 > 20
- 图表编号超过 Figure 15
- 单次 Read 返回内容被截断
- 上下文窗口使用超过 50%（观察系统提示中的 usage 信息）
分批时告知用户当前进度（如"已完成第 1/3 批：方法论章节"）。
阅读策略
读取策略的核心原则是：优先覆盖所有图表，同时对论文结构建立全局认知。
PDF较长的论文（>10页）
分阶段阅读，每阶段有明确目的：
- 先读前2页 — 建立全局认知：标题、作者、摘要、引言开头。确定论文领域和核心问题。
- 浏览全部页面 — 快速扫描定位所有图表位置和章节边界。建立"图表地图"，确保后续不遗漏。
- 精读核心章节 — Methods/Experiment/Results/Discussion 逐段细读。理解每个实验和结论。
- 逐个精读图表 — 每个图表作为独立单元精读。对于多子图（a/b/c/d），每个子图都要单独观察和分析。
PDF较短的论文（≤10页）
一次性全量读取建立全局认知，然后逐个图表回溯精读。
图表识别清单
读取过程中标记所有图表类型，不遗漏任何编号或非编号的视觉元素：
- Figure/Fig/图（含子图 a/b/c/d/e/f）
- Table/表
- 未编号的示意图、流程图、照片
- Supplementary Materials 中的图表
输出结构
按8章节固定结构输出中文报告。完整模板见 references/output-template.md——开始输出前读取该模板，严格按模板结构填充内容。
报告八章分别为：
- 论文基本信息 — 标题/作者/年份/期刊/DOI/领域
- 研究问题与动机 — 要解决什么问题？为什么重要？前人不足？
- 方法与技术路线 — 怎么解决的？核心技术是什么？创新点在哪？
- 实验设计与验证 — 怎么验证的？数据集/装置/基线/指标是什么？
- 图表详解 — 核心章节，每个图表逐一详细解释
- 核心贡献 — 区分真创新 vs 工程优化
- 局限与不足 — 有据可查的局限性分析
- 总结与启发 — 核心信息、领域影响、后续研究方向
图表详解方法
每个图表的解释按5个维度展开，这是本技能区别于泛泛总结的核心：
- 图表类型 — 识别正确是解释正确的前提
- 展示内容 — 横纵坐标、数据序列、标尺等关键元信息
- 关键观察 — 数据趋势、异常点、子图对比，用具体数值说话
- 与论文论点的关系 — 这个图表在论证体系中的角色：支撑了什么结论？证明或反驳了什么？
- 图表质量评价 — 从清晰度、标注完整性、色觉友好性、误差表达、可视化诚实性五个维度评估
详细的各类型图表分析指南和检查清单见 references/chart-analysis.md——在对每个图表做分析前读取该文件。
对于有子图的 Figure，每个子图 (a) (b) (c)... 都单独按5维度分析，不能笼统概括整个 Figure。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 106 lines · 132 tokens per session scan A ddeac43ae43a
paper-summarizer is a skill published in the GitHub repository Lex669/LumericalFDTD-skill (24 stars, last pushed today), licensed MIT. It adds 132 tokens to every session and 1,540 once invoked, about $0.0007 per session on Opus 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.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
pdf-verification-cli
Verify PDF page count and content using command-line tools when Python libraries unavailable.