Token导航 LogoToken导航TokenDH.com
研究检索需要联网clawhub未标认证来源可访问clear审计提醒

paper2slidespaper2slides 演示文稿

Agent Skill

paper2slides 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

5,236

周安装

216

GitHub Stars

1

下载量

1,711
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:paper2slides(paper2slides 演示文稿)
来源仓库:https://github.com/zhangguanghao523/paper2slides
安装命令:
openclaw skills install paper2slides
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install paper2slides

简介

端到端的学术论文分析和演示文稿生成工具。

  • 支持 PDF 论文的深度研究和幻灯片制作。
  • 提供内容提取、分析和可视化的一体化服务。
  • 需确认 PDF 处理和图表生成权限。paper2slides 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 建议检查输出幻灯片格式和动画效果支持。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

SKILL.md

name
paper-to-slides
description
End-to-end academic paper analysis and presentation generation. Use when a user provides a PDF paper (local path or arXiv URL) and wants (1) a deep research report (dual-mode Part A + Part B), (2) an HTML slide deck for group meeting / seminar / conference talk, or (3) both. Triggers on "read this paper and make slides", "parse this paper into a presentation", "论文研读+做PPT", "解析论文做成slides", or any request combining paper analysis with presentation output. Supports arXiv links (abs/pdf), DOI URLs, and direct PDF URLs.

Paper to Slides

Two-phase pipeline: Phase 1 deep-reads an academic paper into a structured dual-mode report, Phase 2 transforms the report into a polished, zero-dependency HTML presentation.

Dependencies

  • pdftotext (from poppler) — install via brew install poppler or apt install poppler-utils if missing
  • Google Fonts (loaded via CDN in the generated HTML)

Phase 1: Paper Deep-Read

Step 1.0 — Resolve input source

Determine the input type and obtain a local PDF:

InputAction
Local path (/path/to/paper.pdf)Use directly
arXiv abs URL (https://arxiv.org/abs/2603.02096)Convert to https://arxiv.org/pdf/2603.02096 and download
arXiv PDF URL (https://arxiv.org/pdf/2603.02096)Download directly
Other PDF URLDownload directly

Download command:

curl -L -o /tmp/paper.pdf "<pdf_url>"

Use the arXiv ID or paper title as the filename when possible (e.g., /tmp/2603.02096_FluxMem.pdf).

Step 1.1 — Extract full text

pdftotext "<paper.pdf>" /tmp/paper_text.txt

Read the extracted text completely. For papers with critical figures, try extracting key pages as images via pdftoppm and analyzing them with the image tool.

Step 1.2 — Comprehensive analysis

Create temp_analysis.md extracting:

  • Research question, hypotheses, methodology, data sources
  • Core findings with key quantitative results
  • Theoretical contributions and practical implications
  • The paper's fundamental contradiction/gap, novel angle, and method innovation

This step is mandatory — it ensures report quality through structured thinking.

Step 1.3 — Write dual-mode report

Generate [PaperName]_研读报告.md containing both parts separated by ---:

  • Part A — Read part-a-template.md before writing. Deep academic report: structured abstract → introduction → methodology → results → discussion → conclusion → core references.
  • Part B — Read part-b-template.md before writing. Core logic extraction: four key elements table → method formula → one-line summary (expert + layperson versions).

Writing standards: Use complete paragraphs over bullet lists. Provide bilingual terms (中英) on first mention. Support every claim with specific data from the paper.

Step 1.4 — Deliver report

Present the report file and briefly summarize the paper's core innovation, key findings, and theoretical value.

Phase 2: Slides Generation

If the user only requested a report, stop after Phase 1.

Step 2.0 — Confirm parameters

Ask the user (all at once):

  1. Purpose: 组会汇报 / 学术会议 / 教学 / 其他
  2. Length: Short (5-10) / Medium (10-20) / Long (20+)
  3. Theme: 亮色 / 暗色 / 偏好的风格
  4. Editing: 是否需要浏览器内编辑功能

If the user already specified these in the initial request, skip asking and proceed.

Step 2.1 — Choose style

Select an appropriate style based on user preferences. Read slide-styles.md for available presets and CSS specifications. Academic presentations generally suit Swiss Modern (light), Notebook Tabs (light), or Bold Signal (dark).

Step 2.2 — Plan slide outline

Map the report content to a slide structure. Typical academic paper outline (15-19 slides):

SectionSlidesContent
Title1Paper title, authors, affiliations, date
Problem1-2Background, existing gaps, key insight
Method (divider)1Section divider slide
Method details3-5Core modules, formulas, architecture
Results (divider)1Section divider slide
Quantitative results2-3Main results tables, metrics, comparisons
Efficiency / Ablation1-2Efficiency gains, ablation studies
Discussion (divider)1Section divider slide
Advantages & Limitations1-2Key properties, future directions
Summary1One-line takeaway
Thanks1Links, navigation hints

Step 2.3 — Generate HTML

Read slide-template.md for the mandatory HTML architecture, viewport CSS, JS controller, and inline editing implementation.

Non-negotiable rules:

  • Single self-contained HTML file, all CSS/JS inline
  • Every .slide must have height: 100vh; height: 100dvh; overflow: hidden
  • ALL font sizes and spacing must use clamp() — never fixed px/rem
  • Load fonts from Google Fonts or Fontshare — never system fonts
  • Include prefers-reduced-motion support
  • Max content per slide: 1 heading + 4-6 bullets OR 1 heading + 2 paragraphs. Overflow → split slides.

If inline editing is enabled, implement via contentEditable API + localStorage persistence. Use JS-based hover with 400ms delay for the edit button (not CSS ~ sibling selector — it breaks due to pointer-events). See the template for the complete implementation.

Step 2.4 — Open and deliver

open [filename].html

Tell the user: file location, slide count, navigation (arrow keys / space / dots), and editing instructions (press E) if enabled.

Both Phases Together

When the user requests both report and slides, run Phase 1 fully first, then Phase 2. The report serves as the structured source for slide content — do not re-analyze the paper.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

73.38%
按下载量换算1,256

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills