paper-figure-to-figma
Agent skill that rebuilds research paper figures as editable Figma vectors — native text, curves and gradients, with SVG/PDF export.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/sidiangongyuan--paper-figure-to-figma)HTML
<a href="/listings/sidiangongyuan--paper-figure-to-figma"><img src="/api/listings/sidiangongyuan--paper-figure-to-figma/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
**Requirements**
- An AI assistant that can view images, load local skills, run scripts and call external tools (verified with Codex). - **Figma output:** a Figma connection with edit access to the target Design file. - **PPT output:** Windows, installed desktop PowerPoint and `pywin32` in the assistant’s Python environment. No Figma connection is needed for PPT. - Python 3.10+. Image preparation, tracing and PDF extraction use optional task-specific dependencies.
**1. Install the skill**
git clone https://github.com/sidiangongyuan/paper-figure-to-figma.git cd paper-figure-to-figma python tools/install_skill.py
This installs to `$CODEX_HOME/skills/paper-figure-to-figma` (default `~/.codex/skills/paper-figure-to-figma`). Use `--update` to upgrade an existing install, or `--dest <skills-dir>/paper-figure-to-figma` for another assistant. To skip installation, open the repository in your assistant and ask it to read `.agents/skills/paper-figure-to-figma/SKILL.md`.
**2. Choose the output**
For Figma, enable its tool connection and authorize your account. For PPT, use Windows with PowerPoint and install its Python bridge: `python -m pip install pywin32`.
**3. Rebuild a figure**
Attach the complete reference image and send:
Use $paper-figure-to-figma to reconstruct this image in the linked Figma canvas, review the whole figure and details, then share the editable frame link. Figma: <your Design file link> Source (optional): <paper link, PDF or original asset location>
For PowerPoint, attach the image and send:
Use $paper-figure-to-figma to reconstruct this image as an editable PPTX. Use native text boxes and shapes, review the actual PowerPoint rendering, and deliver the PPTX with a preview.
Need specific fonts, colors or edits? Compose the request with the [Prompt Builder](https://sidiangongyuan.github.io/paper-figure-to-figma/).
Full installation and connection guide: [docs/CODEX_QUICKSTART.md](docs/CODEX_QUICKSTART.md)
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 · 342 lines
- <div align="center">
- <a href="https://github.com/sidiangongyuan/paper-figure-to-figma">
- <img src="assets/wordmark.svg" alt="Paper Figure to Figma" width="420">
- </a>
- ### Rebuild research figures with high fidelity. Keep every step editable.
- [](LICENSE)
- [](CHANGELOG.md)
- [](https://github.com/sidiangongyuan/paper-figure-to-figma/stargazers)
- [](.agents/skills/paper-figure-to-figma/SKILL.md)
- [](https://www.figma.com/)
- [](#powerpoint)
- [](docs/DEVELOPMENT.md)
- [](https://sidiangongyuan.github.io/paper-figure-to-figma/)
- [](#-demo)
- **English** · [简体中文](README.zh-CN.md)
- [Quick Start](#-quick-start) • [How it works](#-how-it-works) • [Examples](#-examples) • [Demo](#-demo) • [Updates](#recent-updates) • [FAQ](#-faq)
- <br>
- <a href="examples/agentthink/README.md"><img src="assets/agentthink-reconstruction.png" alt="Reference, screenshot reconstruction and source-assisted reconstruction" width="100%"></a>
- <sub>Reference · From a screenshot · With original source assets · <a href="examples/agentthink/README.md">Example and files</a> · <a href="assets/agentthink-reconstruction-details.png">Enlarged details</a></sub>
- </div>
- <br>
- **Paper Figure to Figma** is an agent skill that rebuilds research figures as editable **Figma artwork or PowerPoint files**. Give your assistant a reference image and choose the output. It reconstructs text, shapes and connections, reviews the actual result at whole-figure and detail scales, and corrects differences before delivery.
- Provide a screenshot, or add a paper link, PDF or original asset source. The assistant retrieves accessible matching originals when available and continues from the screenshot when no usable source exists.
- ## Recent updates
- **0.2.5 (V2.5) · November 5, 2026** — [Full changelog](CHANGELOG.md)
- - **Native PowerPoint output:** editable text boxes, shapes and paths; complex illustrations remain independent SVG objects.
- - **Verified in PowerPoint:** save, reopen, render and check text-edit geometry automatically on Windows with installed PowerPoint.
- - **Two downloadable PPTX examples:** Aurora and P-GenRM, with clean previews and real object-selection screenshots. [Explore PowerPoint](#powerpoint)
- - **One skill, two destinations:** request Figma or PPT explicitly. Figma remains the default.
- To upgrade an existing installation, run from your repository folder:
- ```bash
- git pull --ff-only
- python tools/install_skill.py --update
- ```
- The previous installation is backed up automatically. ZIP users can download the updated repository and run the same installer with `--update`.
- ## ✨ Features
- - **Native, editable layers** — labels stay text, shapes and arrows stay vectors. Only input/output photos are kept as image layers.
- - **Details that usually get lost** — gradients, local text backings, transparency, dashed strokes, Bézier curves and stacking order.
- - **Built-in review loop** — checks the whole figure, then enlarged details and editability, and revises only the affected elements.
- - **Revise without starting over** — follow-up requests update the existing Figma frame and leave the elements you protect untouched.
- - **Paper-ready typography** — Times New Roman body text and a clear size hierarchy by default; override any of it.
- - **No extra API key** — runs inside your assistant with the selected drawing tools. No VLM API key or original generation prompt needed.
- - **Figma or PowerPoint** — editable Figma artwork by default, or a native `.pptx` on request. SVG/PDF exports remain optional.
- - **Two reconstruction routes** — source-assisted recovery with version and content checks, or a complete reconstruction from the supplied screenshot.
- - **Appearance-aware artwork** — preserve silhouette, color and recognizable parts through matching SVGs, geometric reconstruction or cleaned local tracing.
- ## 🚀 Quick Start
- **Requirements**
- - An AI assistant that can view images, load local skills, run scripts and call external tools (verified with Codex).
- - **Figma output:** a Figma connection with edit access to the target Design file.
- - **PPT output:** Windows, installed desktop PowerPoint and `pywin32` in the assistant’s Python environment. No Figma connection is needed for PPT.
- - Python 3.10+. Image preparation, tracing and PDF extraction use optional task-specific dependencies.
- **1. Install the skill**
- ```bash
- git clone https://github.com/sidiangongyuan/paper-figure-to-figma.git
- cd paper-figure-to-figma
- python tools/install_skill.py
- ```
- This installs to `$CODEX_HOME/skills/paper-figure-to-figma` (default `~/.codex/skills/paper-figure-to-figma`). Use `--update` to upgrade an existing install, or `--dest <skills-dir>/paper-figure-to-figma` for another assistant. To skip installation, open the repository in your assistant and ask it to read `.agents/skills/paper-figure-to-figma/SKILL.md`.
- **2. Choose the output**
- For Figma, enable its tool connection and authorize your account. For PPT, use Windows with PowerPoint and install its Python bridge: `python -m pip install pywin32`.
- **3. Rebuild a figure**
- Attach the complete reference image and send:
- ```text
- Use $paper-figure-to-figma to reconstruct this image in the linked Figma canvas,
- review the whole figure and details, then share the editable frame link.
- Figma: <your Design file link>
- Source (optional): <paper link, PDF or original asset location>
- ```
- For PowerPoint, attach the image and send:
- ```text
- Use $paper-figure-to-figma to reconstruct this image as an editable PPTX.
- Use native text boxes and shapes, review the actual PowerPoint rendering,
- and deliver the PPTX with a preview.
- ```
- Need specific fonts, colors or edits? Compose the request with the [Prompt Builder](https://sidiangongyuan.github.io/paper-figure-to-figma/).
- Full installation and connection guide: [docs/CODEX_QUICKSTART.md](docs/CODEX_QUICKSTART.md)
- ## 🔄 How it works
- ```mermaid
- flowchart LR
- A[Figure + optional source] --> B{Matching source available?}
- B -->|Yes| C[Retrieve and inspect original assets]
- B -->|No| D[Inspect screenshot features]
- C --> E[Rebuild text, geometry and local contours]
- D --> E
- E --> T{Output destination}
- T --> F[Editable Figma artwork]
- T --> P[Native PowerPoint objects]
- F --> G[Compare whole figure and details]
- P --> G
- G -->|Correct differences| E
- G --> H[Deliver Figma frame or PPTX]
- ```
- **Source-assisted reconstruction:** retrieve accessible assets from a supplied paper, PDF or project source; verify they match the reference, then extract and reconstruct the relevant objects. An extracted bitmap still needs vector reconstruction.
- **Screenshot reconstruction:** preserve visible shapes, colors and component relationships. Rebuild regular parts geometrically, trace irregular contours where useful, and repair noisy results. The method covers the whole figure.
- Source information is optional. A title-only lookup is normally limited to about 90 seconds; inaccessible or unmatched sources fall back to the supplied image. Both routes review actual Figma or PowerPoint results at whole-figure and enlarged-detail scales. Content and connection errors are fixed first, then readability, then appearance. [Workflow details](prompts/04-source-routing.md)
- <details>
- <summary><b>What the review checks</b></summary>
- <br>
- | Review | What to check | Result |
- | --- | --- | --- |
- | Whole figure | Missing content, panel arrangement, relative sizes, grouping and cross-panel arrow endpoints | Structural differences located |
- | Enlarged details | Text accuracy and fit, spacing, curves, gradients, backings, repeated elements and layer order | Region, observed difference and correction |
- | Editability | Editable text, independent vector elements, useful groups and protected content | Result can be revised without disturbing protected elements |
- Full instructions: [prompts/02-review.md](prompts/02-review.md)
- </details>
- ## 🎨 Examples
- ### PowerPoint
- Text stays editable. Modules, arrows and curves are native shapes; complex illustrations remain independent SVG objects. The screenshots below show real PowerPoint objects selected on the slide.
- 
- | Aurora | P-GenRM |
- | --- | --- |
- | [**Download PPTX**](examples/aurora/Aurora.pptx) · [Case study](examples/aurora/README.md#powerpoint) | [**Download PPTX**](examples/pgenrm/P-GenRM.pptx) · [Case study](examples/pgenrm/README.md) |
- | 83 text boxes · 64 native shapes · 27 SVG objects | 69 text boxes · 122 native shapes · 13 SVG objects |
- | [Clean PowerPoint preview](examples/aurora/powerpoint.png) · [Selected objects](examples/aurora/powerpoint-selected.png) | [Clean PowerPoint preview](examples/pgenrm/powerpoint.png) · [Selected objects](examples/pgenrm/powerpoint-selected.png) |
- <details>
- <summary><b>Compare the references and native PowerPoint results</b></summary>
- 
- 
- </details>
- PPT generation and verification currently require Windows with desktop PowerPoint. Paper sources and reconstruction conditions are documented beside each example. [PowerPoint setup](docs/CODEX_QUICKSTART.md#powerpoint)
- ### AgentThink
- Rebuild the text, modules, illustrations and connections in a screenshot as editable layers. A matching paper or original asset source can provide additional detail.
- 
- <details>
- <summary><b>Compare details from both reconstruction routes</b></summary>
- 
- The comparison covers training illustrations, maps and vehicles, frozen/trainable symbols, evaluation icons and character contours.
- </details>
- [Example files and attribution](examples/agentthink/README.md) · [Version history comparison](examples/agentthink-v2/README.md)
- <table>
- <tr>
- <th width="50%">AgentThink</th>
- <th width="50%">PlanWAM</th>
- </tr>
- <tr>
- <td><a href="examples/agentthink/README.md"><img src="assets/agentthink-comparison.png" alt="AgentThink reference and reconstruction"></a></td>
- <td><a href="examples/planwam/README.md"><img src="assets/planwam-comparison.png" alt="PlanWAM reference and reconstruction"></a></td>
- </tr>
- <tr>
- <td>Data generation, two-stage training, inference and evaluation pipeline.<br>Editable text, illustrations and connections</td>
- <td>Four-panel comparison of world-model planning approaches.<br><b>43</b> text layers · <b>334</b> vector objects · <b>8</b> gradients</td>
- </tr>
- <tr>
- <td><a href="https://arxiv.org/abs/2505.15298">Paper</a> · <a href="examples/agentthink/reference.png">Reference</a> · <a href="examples/agentthink/reconstruction.svg">SVG</a> · <a href="examples/agentthink/agentthink.scene.json">Scene</a></td>
- <td><a href="https://arxiv.org/abs/2610.11382">Paper</a> · <a href="examples/planwam/reference.png">Reference</a> · <a href="examples/planwam/reconstruction.svg">SVG</a> · <a href="examples/planwam/planwam.scene.json">Scene</a></td>
- </tr>
- </table>
- <details>
- <summary><b>Detail comparisons</b></summary>
- <br>
- **AgentThink** — model blocks, curved branches and reward layers
- 
- **PlanWAM** — curved connections, gradients and text backings
- 
- </details>
- ### Aurora
- The same time-series figure rebuilt from a screenshot and from its matching paper PDF. Compare the curved labels, series strokes, domain illustrations and modality symbols across all three images.
- 
- <details>
- <summary><b>Compare Aurora details</b></summary>
- 
- </details>
- Source: Wu et al., *[Aurora: Towards Universal Generative Multimodal Time Series Forecasting](https://arxiv.org/abs/2509.22295)*, Figure 1, PDF page 2 (arXiv v6). Both results use editable text and vectors, with no image layers. Body text uses Times New Roman.
- [Case study and citation](examples/aurora/README.md) · [Screenshot result](examples/aurora/screenshot.png) · [Source-assisted result](examples/aurora/source-assisted.png)
- Reference figures belong to their original authors; see each example's notes for sources and approximations.
- ## 🎮 Demo
- Download the repository and open **`demo/index.html`** in a browser — no install, works offline. Drag the divider to compare the reference with the reconstruction, edit text, fills and curves, then download the edited SVG.
- 
- The demo uses a pre-built PlanWAM reconstruction to show the editable result; it does not run the AI reconstruction. [Demo controls](docs/SHOWCASE.md)
- ## 🧭 Roadmap
- - [x] Agent skill with connected Figma drawing, review and export
- - [x] PlanWAM and AgentThink examples with editable files and visual comparisons
- - [x] ~~Aurora screenshot and source-assisted reconstructions with whole-figure and detail comparisons~~
- - [x] Prompt Builder and offline demo
- - [x] ~~Source-assisted retrieval, PDF image extraction and screenshot reconstruction~~
- - [x] ~~Complete AgentThink redraw with whole-figure and multi-region detail comparisons~~
- - [x] ~~Offline SVG catalog with colored and outline assets, provenance and licenses~~
- - [ ] Improve low-resolution character contours, small accessories and background cleanup
- - [ ] Extract reusable native vector and text objects from source PDFs
- - [ ] Check font size, line width and spacing at the final paper dimensions
- - [ ] Better selective updates that preserve manual Figma edits
- - [ ] Better mathematical notation and formula reconstruction
- - [ ] Style transfer for colors, typography and appearance while keeping content and structure
- - [x] ~~Native PowerPoint figures with automatic rendering and editability checks~~
- - [x] ~~Aurora and P-GenRM PPTX examples with selected-object screenshots~~
- - [ ] PowerPoint generation and verification on additional platforms
- - [ ] Editable import/export with draw.io and other drawing tools
- - [ ] More examples and reproducible fidelity evaluations
- - [ ] Compatibility testing across more assistants and operating systems
- ## 🚧 Limitations
- - **Not pixel-identical.** Fidelity is judged through the whole-figure and detail review, not a universal accuracy score.
- - **Small illustrations are approximations.** Library substitutions and local tracing can differ from the reference; unreadable source text is flagged rather than guessed.
- - **Photo crops follow the reference resolution.** Use original dataset images for final layouts when available.
- - **Full reimports can overwrite manual edits** to managed layers. Duplicate hand-edited artwork before a full rebuild.
- - **Verified with Codex** using connected Figma tools, and on Windows with desktop PowerPoint. Other assistants and PPT platforms are not yet fully tested.
- - **PPT illustrations remain SVG objects.** They can be moved, resized and replaced; internal path conversion is not guaranteed.
- - **Check readability at the final paper size** once the physical dimensions are known.
- ## ❓ FAQ
- <details>
- <summary><b>Do I need an API key or the original generation prompt?</b></summary>
- No. The skill runs inside your AI assistant and works from the image alone. A paper link, PDF or original source is optional and can help recover clearer assets.
- </details>
- <details>
- <summary><b>Which AI assistants are supported?</b></summary>
- It is verified with Codex. Other assistants need image input, local skill and script execution, and external tool calls; install with `--dest` pointing to their skill directory.
- </details>
- <details>
- <summary><b>Do I need a Figma plugin?</b></summary>
- No custom plugin is required. The skill uses the Figma tools connected to your assistant and needs edit access to the target Design file.
- </details>
- <details>
- <summary><b>What happens if Figma is not connected?</b></summary>
- The skill prepares the scene file and SVG locally, tells you which step is missing — no connection, expired authorization, read-only access or no file access — and continues writing to Figma once it is fixed.
- </details>
- <details>
- <summary><b>Can I keep editing after the first version?</b></summary>
- Yes. Edit directly in Figma, or send the assistant the same Figma link with your changes and list the elements that must stay unchanged.
- </details>
- ## 🤝 Contributing
- Issues, ideas and new examples are welcome.
- - **Bug or unexpected result** — open an issue with the reference image (if shareable), your request and the assistant you used.
- - **New example** — include the source paper, a reference image you may redistribute, the `.scene.json` and the exported SVG.
- - **Code changes** — run the checks in [docs/DEVELOPMENT.md](docs/DEVELOPMENT.md) before opening a pull request.
- ## 🙏 Acknowledgements
- **This open-source project acknowledges and links to the [LINUX DO community](https://linux.do/).** Thank you to the community for sharing ideas and practical experience with AI and design workflows.
- The workflow draws on [Image To Slice](https://github.com/50kg/image-to-slice) and the [Linux.do discussion on AI and design workflows](https://linux.do/t/topic/2314994/53). Local-tracing guidance also draws on [ScanSci SVG](https://github.com/Rimagination/scansci-svg); icon sources and licenses are recorded in the [asset catalog](assets/icons/catalog.json).
- ## 📄 License
- Code is released under the [MIT License](LICENSE). Reference figures, paper content and figure-derived example assets retain their original rights; see the source attribution in each example. Bundled icons retain the source licenses recorded in the [asset catalog](assets/icons/catalog.json).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.