KS
Killer-Skills

literature-review-ppt-generator — how to use literature-review-ppt-generator how to use literature-review-ppt-generator, what is literature-review-ppt-generator, literature-review-ppt-generator alternative, literature-review-ppt-generator setup guide, automated PPT generation for academic papers, literature-review-ppt-generator vs manual PPT creation, install literature-review-ppt-generator, literature-review-ppt-generator for researchers, AI agent skills for academic paper summarization

v1.0.0
GitHub

About this Skill

Perfect for Research Agents needing automated PowerPoint generation from academic paper PDFs. literature-review-ppt-generator is an AI agent skill that generates concise PPT content from academic papers, focusing on method innovation and flexible structure

Features

Automatically generates 2-3 page PPTs from academic paper PDFs
Applies core principles like paper abstracts and method innovation
Supports flexible structure adjustment based on paper characteristics
Enforces strict formatting guidelines, including page limits and title requirements
Utilizes specific outline symbols, such as ▶ and ▢, for organization

# Core Topics

Deng-GuiFeng Deng-GuiFeng
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
30
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add Deng-GuiFeng/Paper2PPT/literature-review-ppt-generator

Agent Capability Analysis

The literature-review-ppt-generator MCP Server by Deng-GuiFeng is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use literature-review-ppt-generator, what is literature-review-ppt-generator, literature-review-ppt-generator alternative.

Ideal Agent Persona

Perfect for Research Agents needing automated PowerPoint generation from academic paper PDFs.

Core Value

Empowers agents to convert PDFs into concise 2-3 page PPTs, focusing on method innovations and avoiding performance metrics, using structured content analysis and flexible template adjustments, all while adhering to strict formatting guidelines such as 2-page limits, specific title formats, and English language requirements.

Capabilities Granted for literature-review-ppt-generator MCP Server

Automating literature review presentations for 5-minute shares
Generating PPTs from academic papers with a focus on method innovations
Creating structured and flexible templates for research presentations

! Prerequisites & Limits

  • Requires academic paper PDFs as input
  • Strict 2-page limit for generated PPTs
  • English language only for PPT content
Project
SKILL.md
5.9 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Literature Review PPT Generator

为学术论文生成简洁的组会汇报PPT内容,聚焦方法创新,适合5分钟快速分享。

核心原则

原则说明
论文名片激发兴趣,而非详尽解读
聚焦创新阐述方法创新与启示,避免罗列性能指标
结构灵活根据论文特点调整,不拘泥于固定模板

格式规范

硬性要求

项目要求
页数严格2页,不得超出
标题所有页共用论文完整标题 + 斜体来源(如 ICML 2023
大纲符号一级 ,二级
编号跨页连续,不重置
语言幻灯片内容全英文,讲稿中文

行数限制(布局约束)

必须严格遵守,否则幻灯片内容会溢出边界。

统计规则:仅计算内容行,即以 - 开头的行(不含空行、**配图**:**讲稿**: 等非内容行)。

幻灯片总行数范围说明
Slide 115 ~ 18 行超出 18 行必须删减
Slide 217 ~ 21 行超出 21 行必须删减

超出上限时,优先删减三级 - 行,保留核心论点。

内容组织

每页结构: 2-4个一级论点,每个下设1-3个二级论点

逻辑流程(根据论文类型选择):

  • Background/Motivation → Method → Results → Conclusion
  • Problem → Framework/Architecture → Innovations → Results
  • Inspiration → Dataset → Methods → Results
  • Key Contributions → Training Innovation → Achievements

强调方式: 粗体斜体代码样式 突出关键概念

图表配置

基本要求

  • 位置: 幻灯片右侧或下方
  • 数量: 每页1-4张
  • 内容: 架构图、流程图、关键结果对比图/表

图表引用规范

图表引用需与 extract-pdf-figure skill 的命名格式完全对齐:

引用类型格式示例说明
完整图表Figure 1, Table 2提取整个图表(含所有子图)
子图Figure 1(a), Figure 1(b)仅提取复合图中的特定子图
简写形式Fig. 1, Fig 1等同于 Figure 1
子表Table 1(a)仅提取特定子表

提取模式选择

每个图表引用需指定提取模式:

模式语法图片内容适用场景
完整模式Figure 1包含标题、图例、注释、说明文字图表自解释,无需额外说明
主体模式Figure 1 [content-only]仅图表主体,不含标题和说明PPT中需添加中文说明时

选择原则:

  • 若 PPT 讲稿会详细解释图表 → 使用 [content-only] 避免信息重复
  • 若图表需要保留原文说明以便读者理解 → 使用完整模式
  • 子图通常使用完整模式(因为子图标签如 "(a)" 是必要的)

工作流程

1. 研读论文

识别核心贡献:解决什么问题?提出什么新方法?关键结果?启发意义?

2. 设计大纲

选择合适的逻辑流程,规划严格2页内容,撰写精炼的英文描述。草稿写完后,统计每页内容行数,超出上限则删减低价值内容。

3. 挑选配图

选取最能支撑论点的图表,明确是否需要子图,决定提取模式。

4. 生成交付物

创建两个文件:

paper_summary.md — 详尽客观的论文总结,为论文汇报者详细介绍讲解论文内容,使用中文语言。

ppt_content.md — PPT内容,严格遵循以下格式:

markdown
1# [论文完整标题] 2*[经过检索的精准论文来源(期刊/会议),如:ICML 2023, Nature Communications 2026, IEEE Journal of ...]* 3 4--- 5 6## Slide 1 7 8**1. 一级论点** 9 10▢ 1.1 二级论点 11 - 具体描述... 12 - 具体描述... 13 14▢ 1.2 二级论点 15 - 具体描述... 16 17**2. 一级论点** 18 19▢ 2.1 二级论点 20 - 具体描述... 21 22**配图**: 23- Figure 1 [content-only] 24- Table 2 25 26**讲稿**: 27(中文讲稿...) 28 29--- 30 31## Slide 2 32 33**3. 一级论点** 34 35▢ 3.1 二级论点 36 - 具体描述... 37 38**配图**: 39- Figure 3(a) 40- Figure 3(b) [content-only] 41 42**讲稿**: 43(中文讲稿...)

配图列表格式说明

配图列表采用 YAML 友好格式,便于下游流程解析:

markdown
1**配图**: 2- Figure 1 # 完整模式 3- Figure 2 [content-only] # 主体模式 4- Table 1 # 完整模式 5- Figure 3(a) # 子图,完整模式 6- Figure 3(b) [content-only] # 子图,主体模式

解析规则:

  • 每个图表占一行,以 - 开头
  • 图表名称支持:Figure N, Fig. N, Table N, Figure N(x)
  • [content-only] 标记表示使用主体模式(对应 --no-extras 参数)
  • 无标记默认为完整模式

特殊情况处理

情况处理方式
论文内容单薄保持2页,适当扩展背景介绍或讨论启示意义
图表质量差/缺失在配图位置注明 [建议重绘: Figure X][无合适配图]
综述类论文聚焦分类框架和关键洞见,而非单一方法
多个并列贡献优先选择最具创新性的1-2个深入介绍
复合图表需部分展示使用子图引用如 Figure 1(a) 而非整个 Figure 1
图表已含完整说明使用完整模式,讲稿可简化
需中文详解图表使用 [content-only] 模式,避免中英文说明重复

与图表提取的协作

本 skill 生成的 ppt_content.md 中的配图列表,将由 extract-pdf-figure skill 自动解析和提取。确保:

  1. 命名一致: 图表名称与论文原文完全一致(大小写、空格、括号)
  2. 模式明确: 每个图表都应考虑是否需要 [content-only]
  3. 子图精确: 如只需部分子图,使用 Figure N(x) 而非 Figure N

Related Skills

Looking for an alternative to literature-review-ppt-generator or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication