DSH Plugins Marketplace

DSH Plugins

Plugins

/

Tools & Capabilities

/

dsh-group-meeting-slides

d

dsh-group-meeting-slides

Manifest valid

Turns an English paper PDF into a Chinese group-meeting .pptx whose figures and tables are the paper's own cropped pixels.

hasBundlePatch

dsh-group-meeting-slides

version license DeepSeek Harness

English · 中文

把一篇英文论文 PDF 变成中文组会汇报 PPT的 DeepSeek Harness 技能。 论文里的每张图、每个表都用原文自己的像素,不重画、不臆造数字。

An agent skill for DeepSeek Harness that turns an English paper PDF into a Chinese group-meeting (组会 / 文献汇报) slide deck. Every figure and table keeps the paper's own pixels — nothing is redrawn, no number is invented.


效果

封面正文
coverbullets
图(原图 + 英文 caption)表(带结论条)
figuretable

以上四页由本技能从 Attention Is All You Need(Vaswani et al., NeurIPS 2017) 直接生成,未做手工修图。

安装

本仓库是一个 DSH 插件包,package.json 里声明了 dsh.bundle,所以两种装法都行。

插件方式(会出现在技能目录里,之后可随插件一起升级):

dsh plugin add wld12314/dsh-group-meeting-slides

手动方式(不想装插件就拷文件夹):

# Windows
git clone https://github.com/wld12314/dsh-group-meeting-slides.git
Copy-Item -Recurse dsh-group-meeting-slides\group-meeting-slides "$env:USERPROFILE\.dsh\skills\"
# macOS / Linux
git clone https://github.com/wld12314/dsh-group-meeting-slides.git
cp -r dsh-group-meeting-slides/group-meeting-slides ~/.dsh/skills/

装好后重启 DSH(或新开一个会话),对 agent 说「把这篇论文做成组会 PPT」 并给出 PDF 路径即可。

依赖

脚本需要 Python 与三个库,由 agent 通过 load_workspace_dependencies 取到解释器后调用,你不必手动装到系统 Python 里:

库用途
PyMuPDF解析 PDF 版面、按真实 bbox 裁剪图片
python-pptx生成 .pptx
Pillow图片尺寸与宽高比处理

若 agent 报告缺少这些库,把上面的列表发它,让它装到工作区依赖里。

它怎么工作

技能刻意把机械活和判断活分开:

谁干什么
scripts/extract.pyPDF 几何、图注定位、按 bbox 抠图、整页渲染兜底
scripts/build_pptx.py版式、字体、图片等比放置(13.333×7.5 宽屏,academic / dark 双主题)
Agent读论文、定叙事、写中文文案、逐张核对图片
extract.py  →  paper.md + figures.json + figures/ + tables/ + pages/
                       ↓
              agent 逐张看图、读论文、写 deck.json
                       ↓
build_pptx.py  →  <课题>_组会汇报.pptx  +  讲稿.md

关键设计:先看图,再写字

SKILL.md 里有一条硬性流程:写任何一页之前,必须先把 figures/ 和 tables/ 里每张图打开看一遍,并且做语义核对——图注说的是 Table 2, 图里真的是 Table 2 吗?两个 crop 是否字节相同(说明两个图注指到了同一个 对象,至少一个是错的)?

裁剪是几何启发式,它一定会出错。这一步是唯一能抓住「框得很漂亮但框错了表」 的地方。

目录结构

dsh-group-meeting-slides/
├── package.json                    # dsh.bundle 清单
├── cordis.patch.yml                # 挂载技能提供器
├── lib/index.js                    # 技能提供器(把 SKILL.md 交给技能目录)
├── README.md
├── LICENSE
├── assets/preview/                 # README 预览图
└── group-meeting-slides/           # 技能本体,也可整个拷进 ~/.dsh/skills/
    ├── SKILL.md                    # 触发词、工作流、硬规则
    ├── references/
    │   ├── deck-schema.md          # deck.json 的完整契约
    │   └── storyline.md            # 12–18 页的组会叙事与中文写作规范
    └── scripts/
        ├── extract.py
        └── build_pptx.py

硬规则

这些不是建议,是技能运行时强制执行的:

  • 绝不臆造数字。幻灯片里出现的每个数都要能追到论文正文或某张已裁的表。
  • 绝不用 python-pptx 重画图表。宁可少一页,也不给一张错的图。
  • 保持宽高比。build_pptx.py 强制,不允许绕过它直接 add_picture。
  • 每张图下方保留英文原图注,方便听众回原文核对。
  • 文案用中文,术语首次出现保留英文,例如 「缩放点积注意力(scaled dot-product attention)」。

兼容性

宿主状态
DeepSeek Harness 桌面版已验证
DeepSeek Harness Web 版应当可用——技能层由宿主统一加载,不依赖桌面独有 API

技能本体是纯 Markdown + Python;仓库根上的 package.json → cordis.patch.yml → lib/index.js 只是把 group-meeting-slides/SKILL.md 挂进技能目录的一层壳, 运行时不联网、不装依赖,也不改宿主行为。

许可

Apache-2.0 © 2026 海龟饲料 (@wld12314)


English

An agent skill for DeepSeek Harness. Give it an English paper PDF; it produces a Chinese group-meeting .pptx plus speaker notes, where every figure and table is the paper's own pixels cropped at the real bounding box — never redrawn, never estimated.

Install: dsh plugin add wld12314/dsh-group-meeting-slides, or copy group-meeting-slides/ into ~/.dsh/skills/ if you would rather install it as a plain skill folder.

Requires: Python with PyMuPDF, python-pptx, Pillow (resolved by the host's load_workspace_dependencies, not your system Python).

Why it is split this way: the scripts own everything mechanical and reproducible — PDF geometry, figure cropping, typography, aspect-ratio-safe placement. The agent owns what needs judgement — reading the paper, deciding the argument, writing the copy. Before writing a single slide the agent must open and semantically verify every extracted image, because geometric cropping fails in ways geometry cannot detect.

Licensed under Apache-2.0.

Comments

Loading…

Similar plugins

dsh-ppt-master

by pn1024

AI-driven presentation workflow packaged as a dsh skill: generates editable PPTX decks and SVG snapshots from PDF, DOCX, URLs or Markdown, fills native PPTX templates, and enhances finished presentati

Tools & CapabilitiesManifest valid

★ 3

↓ 599/wk

MIT

Python

Sep 1, 2026

dsh plugin --profile web add dsh-ppt-master

by OMSociety

DSH (DeepSeek Harness) presentation skill: PPT/演示文稿生成与导出,含 DSH 内纯本地导出 (python-pptx) 与本地预览渲染 (Pillow)。

Design & slidesManifest valid

★ 7

MIT

Python

Sep 24, 2026

dsh plugin --profile web add dsh-kimi-ppt-skill

by SuperstructureJH

Generates editable PPTX decks in DSH with a bundled authoring Skill, deterministic PPTD scene checks, native PowerPoint objects, and local PPTD source-project delivery.

Workflow & AutomationDevelopment & InfrastructureManifest valid

★ 2

MIT

JavaScript

Aug 28, 2026

dsh plugin --profile web add dsh-workbuddy-ppt

by jetformat

DeepSeek Harness plugin for Jetformat: Office to PDF and PDF tools via the local CLI

Development & InfrastructureManifest valid

★ 2

MIT

TypeScript

Sep 27, 2026

dsh plugin --profile web add @jetformat/dsh-plugin

by 17897693

DSH 办公文档插件:docx/xlsx/pptx/pdf/odf/csv/html 读写改与互转 + 离线 OCR(自用为主,不承诺维护)

Tools & CapabilitiesManifest valid

★ 3

↓ 147/wk

MIT

JavaScript

Oct 9, 2026

dsh plugin --profile web add dsh-wen

by Bingtang1019

Build PowerPoint decks from a brief: plan and storyboard gates, per-page authoring through pptwise and ppt-master, a design-profile pass, page-image snapshots with a render audit, and a tool that hand

Tools & CapabilitiesManifest valid

★ 9

↓ 1.1k/wk

TypeScript

Oct 8, 2026

dsh plugin --profile web add dsh-ppt-flashmade