Skip to content
Back to search

paper2anything

An agent skills pack that turns an academic paper PDF into slides, a poster, a webpage, a Xiaohongshu post, or a WeChat article (paper2slides/poster/html/xhs/wechat)

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/quzhan51496--paper2anything/badge.svg)](/listings/quzhan51496--paper2anything)

HTML

<a href="/listings/quzhan51496--paper2anything"><img src="/api/listings/quzhan51496--paper2anything/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

**One-command install with Claude Code (recommended)**:

bash tools/install-linux.sh --create-env --shell-init     # Linux
bash tools/install-macos.sh --create-env --shell-init     # macOS

The install script will: ① symlink the 5 skills into `~/.claude/skills/`; ② bootstrap a `.env` from `.env.example` if you don't have one; ③ check the conda environment, system dependencies, and `MINERU_API_TOKEN` (used for paper extraction). What the two flags do (omit them if you don't need them):

- `--create-env`: `conda env create` (updates per `environment.yml` if it already exists) + installs playwright chromium + runs a pip self-check; - `--shell-init`: (optional) writes the `.env` auto-export into your shell startup file, so a new shell loads the credentials automatically.

After it runs, follow the script's prompts for two more steps:

1. **Fill in `MINERU_API_TOKEN` in `.env`** (required); 2. **Install the missing system-level dependencies it points out** (the script detects each one and gives the install command).

If you need to install manually (e.g. you only use one specific skill), here is the equivalent breakdown.

<details> <summary><b>Manual install</b></summary>

Register a skill

Symlink the skills you want into `~/.claude/skills/` so Claude Code can discover and auto-trigger them:

# From the paper2anything package root; copy the line for whichever skill you want
mkdir -p ~/.claude/skills
ln -sfn "$(pwd)/paper2slides"  ~/.claude/skills/paper2slides
ln -sfn "$(pwd)/paper2poster"  ~/.claude/skills/paper2poster
ln -sfn "$(pwd)/paper2html"    ~/.claude/skills/paper2html
ln -sfn "$(pwd)/paper2xhs"     ~/.claude/skills/paper2xhs
ln -sfn "$(pwd)/paper2wechat"  ~/.claude/skills/paper2wechat

conda environment

All 5 skills share one conda environment, `paper2anything`.

# From the paper2anything package root
conda env create -f environment.yml
conda activate paper2anything

System-level dependencies

| Tool | Purpose | Which skill | Install command | | --- | --- | --- | --- | | poppler-utils (`pdftoppm`) | PDF rendering | paper2slides | `sudo apt install poppler-utils` (Linux) / `brew install poppler` (macOS) | | libreoffice (`soffice`) | visual QA | paper2slides | `sudo apt install libreoffice` (Linux) / `brew install --cask libreoffice` (macOS) | | Node.js | JS runtime | paper2slides | on Linux use NodeSource (the apt default is too old, see the note below) / `brew install node` (macOS) | | pptxgenjs + react-icons/react/react-dom/sharp | PPT rendering | paper2slides | `npm install -g pptxgenjs react-icons react react-dom sharp` (prefix `sudo` on Linux) |

**Node.js (Linux)**: sharp requires Node ≥20.9.0; install it via NodeSource:

curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt install -y nodejs

Credentials

All skills' credentials live in **a single `.env` at the package root** (copy from `.env.example` and fill it in). After copying, just fill in your keys:

cp .env.example .env          # first time: copy, then fill in your keys

Optional: write the `.env` export into your shell startup file. Pass `--shell-init` during install to do this automatically (see Installation), or add this line manually:

set -a; source <paper2anything package root>/.env; set +a

</details>

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 269 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <!-- This README has English and Chinese versions; keep them in sync: when changing content, edit both README.md (English, default) and README.zh-CN.md (Chinese). -->
  2. <div align="center">
  3. <img src="assets/logo.png" alt="paper2anything logo" width="140" />
  4. # paper2anything
  5. [![Project Page](https://img.shields.io/badge/Project_Page-Live-2ea44f?logo=githubpages&logoColor=white)](https://quzhan51496.github.io/paper2anything/) [![Claude Code Skill](https://img.shields.io/badge/Claude_Code-Skill-blue?logo=anthropic&logoColor=white)](https://docs.anthropic.com/en/docs/claude-code) [![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
  6. **English** | [简体中文](README.zh-CN.md)
  7. [Showcase](#showcase) · [Installation](#installation) · [Usage](#usage) · [Output locations](#output-locations) · [Directory structure](#directory-structure) · [Contributors](#contributors) · [Acknowledgements](#acknowledgements)
  8. </div>
  9. <div align="center">
  10. <img src="assets/marquee.webp" alt="A marquee of real artifacts produced by paper2anything — slide decks, posters, project homepages, Xiaohongshu and WeChat covers" width="100%" />
  11. </div>
  12. A skills pack that turns an academic paper PDF into any of several promotional artifacts, covering the main forms of paper dissemination:
  13. | Skill | Turns the paper into | Output | Trigger phrases (examples) |
  14. | --- | --- | --- | --- |
  15. | **paper2slides** | a presentation deck | `.pptx` | "make slides from this paper", "generate a deck from this PDF", "deck this paper" |
  16. | **paper2poster** | a conference poster | `poster.html` + `poster.png` | "make a poster from this paper", "turn this paper into a poster" |
  17. | **paper2html** | a single-page project homepage | `index.html` | "turn this paper into a webpage", "generate a project page / landing page" |
  18. | **paper2xhs** | a Xiaohongshu (rednote) multi-image post | `xhs_post.json/md` + cover + figure images | "post this paper to Xiaohongshu", "turn this paper into a rednote post" |
  19. | **paper2wechat** | a WeChat Official Account article | `wechat_article.md/html` + cover | "write this paper as a WeChat article", "turn this paper into a WeChat post" |
  20. Each subdirectory is an independent, auto-triggerable skill (each has its own `SKILL.md`).
  21. ---
  22. ## Showcase
  23. ### paper2slides
  24. A sample of **paper2slides** output — eight decks across diverse research fields (HCI / VR, computer vision, drug discovery, security & provenance, multimodal agents, quantum computing, optimization, and ML theory):
  25. <div align="center">
  26. <img src="assets/showcase/paper2slides/SHOWCASE_decks.png" alt="Eight slide decks generated by paper2slides from paper PDFs, across diverse research fields" width="100%" />
  27. </div>
  28. ### paper2poster
  29. A sample of **paper2poster** output — nine posters, spanning nine research fields (drug design, graphics, HCI, materials science, X-ray inspection, NLP / LLM safety, optics & photonics, statistical ML, and computer vision):
  30. <div align="center">
  31. <img src="assets/showcase/paper2poster/SHOWCASE_3x3.png" alt="Nine conference posters generated by paper2poster from paper PDFs, across nine research fields" width="100%" />
  32. </div>
  33. ### paper2html
  34. A sample of **paper2html** output — eight project homepages across diverse research fields (HCI / VR, drug discovery, machine writing, robotics, security, software engineering, agent skills, and financial trading):
  35. <div align="center">
  36. <img src="assets/showcase/paper2html/SHOWCASE_pages.png" alt="Eight project homepages generated by paper2html from paper PDFs, across diverse research fields" width="100%" />
  37. </div>
  38. ### paper2xhs
  39. A sample of **paper2xhs** output — ten Xiaohongshu (rednote) posts across diverse research fields (world models, LLM agent societies, AI supply-chain security, LLM evaluation, robotic manipulation, CS education, machine translation, climate simulation, medical diagnosis, and causal inference):
  40. <div align="center">
  41. <img src="assets/showcase/paper2xhs/SHOWCASE_tenpapers.png" alt="Ten Xiaohongshu posts generated by paper2xhs from paper PDFs, across diverse research fields" width="100%" />
  42. </div>
  43. ### paper2wechat
  44. A sample of **paper2wechat** output — twelve WeChat Official Account articles across diverse research fields (world models, LLM agent societies, AI supply-chain security, LLM evaluation, robotic manipulation, CS education, machine translation, climate simulation, medical diagnosis, causal inference, efficient inference, and NLP):
  45. <div align="center">
  46. <img src="assets/showcase/paper2wechat/SHOWCASE_cover.jpg" alt="Twelve WeChat Official Account covers generated by paper2wechat from paper PDFs, across diverse research fields" width="100%" />
  47. </div>
  48. ---
  49. ## Installation
  50. **One-command install with Claude Code (recommended)**:
  51. ```bash
  52. bash tools/install-linux.sh --create-env --shell-init # Linux
  53. bash tools/install-macos.sh --create-env --shell-init # macOS
  54. ```
  55. The install script will: ① symlink the 5 skills into `~/.claude/skills/`; ② bootstrap a `.env` from `.env.example` if you don't have one; ③ check the conda environment, system dependencies, and `MINERU_API_TOKEN` (used for paper extraction). What the two flags do (omit them if you don't need them):
  56. - `--create-env`: `conda env create` (updates per `environment.yml` if it already exists) + installs playwright chromium + runs a pip self-check;
  57. - `--shell-init`: (optional) writes the `.env` auto-export into your shell startup file, so a new shell loads the credentials automatically.
  58. After it runs, follow the script's prompts for two more steps:
  59. 1. **Fill in `MINERU_API_TOKEN` in `.env`** (required);
  60. 2. **Install the missing system-level dependencies it points out** (the script detects each one and gives the install command).
  61. If you need to install manually (e.g. you only use one specific skill), here is the equivalent breakdown.
  62. <details>
  63. <summary><b>Manual install</b></summary>
  64. ### Register a skill
  65. Symlink the skills you want into `~/.claude/skills/` so Claude Code can discover and auto-trigger them:
  66. ```bash
  67. # From the paper2anything package root; copy the line for whichever skill you want
  68. mkdir -p ~/.claude/skills
  69. ln -sfn "$(pwd)/paper2slides" ~/.claude/skills/paper2slides
  70. ln -sfn "$(pwd)/paper2poster" ~/.claude/skills/paper2poster
  71. ln -sfn "$(pwd)/paper2html" ~/.claude/skills/paper2html
  72. ln -sfn "$(pwd)/paper2xhs" ~/.claude/skills/paper2xhs
  73. ln -sfn "$(pwd)/paper2wechat" ~/.claude/skills/paper2wechat
  74. ```
  75. ### conda environment
  76. All 5 skills share one conda environment, `paper2anything`.
  77. ```bash
  78. # From the paper2anything package root
  79. conda env create -f environment.yml
  80. conda activate paper2anything
  81. ```
  82. ### System-level dependencies
  83. | Tool | Purpose | Which skill | Install command |
  84. | --- | --- | --- | --- |
  85. | poppler-utils (`pdftoppm`) | PDF rendering | paper2slides | `sudo apt install poppler-utils` (Linux) / `brew install poppler` (macOS) |
  86. | libreoffice (`soffice`) | visual QA | paper2slides | `sudo apt install libreoffice` (Linux) / `brew install --cask libreoffice` (macOS) |
  87. | Node.js | JS runtime | paper2slides | on Linux use NodeSource (the apt default is too old, see the note below) / `brew install node` (macOS) |
  88. | pptxgenjs + react-icons/react/react-dom/sharp | PPT rendering | paper2slides | `npm install -g pptxgenjs react-icons react react-dom sharp` (prefix `sudo` on Linux) |
  89. **Node.js (Linux)**: sharp requires Node ≥20.9.0; install it via NodeSource:
  90. ```bash
  91. curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt install -y nodejs
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 138 on GitHub
  92. ```
  93. ### Credentials
  94. All skills' credentials live in **a single `.env` at the package root** (copy from `.env.example` and fill it in). After copying, just fill in your keys:
  95. ```bash
  96. cp .env.example .env # first time: copy, then fill in your keys
  97. ```
  98. Optional: write the `.env` export into your shell startup file. Pass `--shell-init` during install to do this automatically (see Installation), or add this line manually:
  99. ```bash
  100. set -a; source <paper2anything package root>/.env; set +a
  101. ```
  102. </details>
  103. ---
  104. ## Usage
  105. Just state your intent and the matching skill auto-triggers, e.g.:
  106. - "make `path/to/paper.pdf` into slides" → **paper2slides**
  107. - "make a conference poster from this paper" → **paper2poster**
  108. - "turn this PDF into a project homepage" → **paper2html**
  109. - "post this paper to Xiaohongshu for me" → **paper2xhs**
  110. - "write this paper as a WeChat article" → **paper2wechat**
  111. Or call them explicitly with a slash command, followed by the PDF path:
  112. ```
  113. /paper2slides path/to/paper.pdf
  114. /paper2poster path/to/paper.pdf
  115. /paper2html path/to/paper.pdf
  116. /paper2xhs path/to/paper.pdf
  117. /paper2wechat path/to/paper.pdf
  118. ```
  119. ---
  120. ## Output locations
  121. Each skill's final deliverable lands in the same directory as the paper; all intermediate artifacts are kept under `.paper2anything/<skill>/<paper-name>/` in that same directory:
  122. | Skill | Final deliverable | Intermediate artifacts |
  123. | --- | --- | --- |
  124. | paper2slides | `<paper-name>_slides/` (`<paper-name>.pptx`) | `.paper2anything/slides/<paper-name>/` |
  125. | paper2poster | `<paper-name>_poster/` (`poster.png` + `poster.html` + `images/`) | `.paper2anything/poster/<paper-name>/` |
  126. | paper2html | `<paper-name>_html/` (`index.html` + `images/`) | `.paper2anything/html/<paper-name>/` |
  127. | paper2xhs | `<paper-name>_xhs/` (`xhs_post.md` + `.json` + `cover.png` + `post_images/`) | `.paper2anything/xhs/<paper-name>/` |
  128. | paper2wechat | `<paper-name>_wechat/` (`wechat_article.md` + `.json` + `cover.jpg` + `figures/`) | `.paper2anything/wechat/<paper-name>/` |
  129. ---
  130. ## Directory structure
  131. ```
  132. paper2anything/
  133. ├── environment.yml # python environment
  134. ├── .env.example # credentials template (copy to .env and fill in)
  135. ├── .gitignore # ignores .env / __pycache__ etc.
  136. ├── LICENSE # Apache-2.0
  137. ├── README.md # this file (English, default)
  138. ├── README.zh-CN.md # Chinese version
  139. ├── tools/ # install scripts
  140. ├── assets/ # static files
  141. │ └── showcase/ # per-skill output samples (assets/showcase/<skill>/)
  142. ├── paper2slides/ # paper → slides
  143. │ ├── SKILL.md
  144. │ ├── references/ # design style, outline heuristics, pipeline, schema, pptxgenjs
  145. │ └── scripts/ # parse_pdf / render_pptx / page_screenshot / workdir + lib/
  146. ├── paper2poster/ # paper → poster HTML/PNG
  147. │ ├── SKILL.md
  148. │ ├── references/ # poster examples, color palettes, layout guide
  149. │ └── scripts/ # parse_pdf / auto_outline / geom_check / collect_figures / screenshot / check_env
  150. ├── paper2html/ # paper → single-page project homepage
  151. │ ├── SKILL.md
  152. │ ├── references/ # design languages, HTML authoring spec, QA checklist
  153. │ └── scripts/ # parse_pdf / validate / render_check etc. + lib/ (parse/extract/QA, no renderer)
  154. ├── paper2xhs/ # paper → Xiaohongshu
  155. │ ├── SKILL.md
  156. │ ├── references/ # publish guide
  157. │ └── scripts/ # parse_pdf / cover / post_images / publish / xhs_login + utils
  158. └── paper2wechat/ # paper → WeChat
  159. ├── SKILL.md
  160. └── scripts/ # parse_pdf / cover / publish + utils
  161. ```
  162. ---
  163. ## Contributors
  164. Skill design leads at the **[AI4GC Lab](https://ai4gc.org/)**:
  165. <table>
  166. <tr>
  167. <td align="center">
  168. <a href="https://github.com/melonthrower">
  169. <img src="https://github.com/melonthrower.png" width="80" alt="Honghui Sheng"/><br/>
  170. <sub><b>Honghui Sheng</b></sub>
  171. </a><br/>
  172. <sub>paper2poster</sub>
  173. </td>
  174. <td align="center">
  175. <a href="https://github.com/YuanDaoze">
  176. <img src="https://github.com/YuanDaoze.png" width="80" alt="Tao Xiong"/><br/>
  177. <sub><b>Tao Xiong</b></sub>
  178. </a><br/>
  179. <sub>paper2html</sub>
  180. </td>
  181. <td align="center">
  182. <a href="https://github.com/b7277">
  183. <img src="https://github.com/b7277.png" width="80" alt="Xinchen Xu"/><br/>
  184. <sub><b>Xinchen Xu</b></sub>
  185. </a><br/>
  186. <sub>paper2xhs &amp; paper2wechat</sub>
  187. </td>
  188. </tr>
  189. </table>
  190. ---
  191. ## Acknowledgements
  192. paper2anything is developed by the **[AI4GC Lab](https://ai4gc.org/)** at Zhejiang University.
  193. - Paper PDF parsing is powered by **[MinerU](https://github.com/opendatalab/MinerU)**.
  194. - Xiaohongshu publishing is powered by **[xiaohongshu-mcp](https://github.com/xpzouying/xiaohongshu-mcp)**.
  195. - WeChat publishing and formatting are powered by **[md2wechat](https://pypi.org/project/md2wechat/)**.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.