# paper-figure-guide

The paper-figure-guide Claude Code skill explains figures from research papers and turns them into a colored PDF guide. It activates when asked to interpret a paper’s figures.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 88 repo stars
- Author: mkaremm80
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/mkaremm80/My-Skills-on-Claude/tree/HEAD/skills/paper-figure-guide/SKILL.md
- Updated: 2026-11-14
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/paper-figure-guide

## What it does

The skill turns figures from a research paper into a colored PDF guide, with explanations placed on the images. It covers each figure and panel, connects them to the paper’s main claim, and adds “How to read it” and “What it tells us” sections. Small helper drawings clarify concepts the figures rely on.

The source can be a PDF or LaTeX. Figure data can come from supplied source files, vector elements in a PDF, or raster images; extracted values are checked against numbers in the paper. The guide is built with LaTeX and `pdflatex`, which runs twice. If TeX packages are missing, the instructions give an `apt-get` installation command. PyMuPDF is used to extract data from vector plots.

Before delivery, rendered pages are checked for overlapping labels and hard-to-read figures. Values must match the paper, while any invented example must be marked as illustrative. The PDF is delivered with `SendUserFile`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add mkaremm80/My-Skills-on-Claude --skill paper-figure-guide -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/paper-figure-guide/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/paper-figure-guide/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add mkaremm80/My-Skills-on-Claude --skill paper-figure-guide -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/paper-figure-guide/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add mkaremm80/My-Skills-on-Claude --skill paper-figure-guide -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/paper-figure-guide/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mkaremm80/My-Skills-on-Claude skills/paper-figure-guide
```

2. **Manually: put the files in place**
- File: `.github/skills/paper-figure-guide/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add mkaremm80/My-Skills-on-Claude --skill paper-figure-guide -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/mkaremm80/My-Skills-on-Claude --path skills/paper-figure-guide
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/paper-figure-guide/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mkaremm80/My-Skills-on-Claude/tree/HEAD/skills/paper-figure-guide/SKILL.md

## When to use it
- explain the meaning of every figure and panel
- connect the paper’s figures to its main claim
- clarify plot axes, colors, and key values
- assemble annotated figures into a colored PDF guide

## Example prompts
- Explain the figures in this paper and make a colored PDF guide.
- Annotate the key regions and values in the plots in `paper.pdf`.
- Create a figure guide from this paper’s LaTeX source.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: f21bfd63281c3a31.

BEGIN THIRD-PARTY FILE f21bfd63281c3a31
```text
---
name: "paper-figure-guide"
description: "Explain every figure of a research paper in a colored PDF guide with annotated figures (callouts, arrows, shaded regions) and helper drawings. Use when asked to explain or understand a paper's figures."
---

# Paper Figure Guide

Turn the figures of any research paper (PDF or LaTeX) into a colored, easy-to-read PDF guide. Every figure is shown again with explanations drawn on it (numbered red circles, arrows, notes, shaded regions), followed by "How to read it" and "What it tells us" boxes. Add one or two helper drawings for the key ideas the figures assume.

Writing style: English, short sentences, simple words (B2 level), professional. Numbers must come from the paper, never invented. If you illustrate with your own example (e.g., one simulated realization), say so clearly next to it.

## Step 1 - Read the paper and plan
1. Read the whole paper first. List every figure (and panel), its caption, the section that discusses it, and the numbers the text quotes about it.
2. Find the paper's main message and write the story chain: which figure shows HOW the system works, which shows WHEN/WHERE the method helps, which shows HOW MUCH it gains. This chain goes on the cover.
3. Decide which concepts a reader needs to understand the figures (e.g., a dimension, a threshold, a mechanism). Each one becomes a helper drawing.

## Step 2 - Get the figure content
Use the best source available, in this order:
1. **LaTeX source / TikZ / data files** given by the user: reuse them directly.
2. **Vector plots inside the PDF** (MATLAB/matplotlib exports): extract the real data with PyMuPDF (`pip install --break-system-packages pymupdf`; `import pymupdf as fitz`).
   - `page.get_drawings()` gives paths with color, width and items. A curve is usually one path with many `'l'` (line) items; markers are small closed paths; error bars are short vertical lines plus caps.
   - Group by stroke color to separate series; split panels by x-range.
   - Calibrate axes from tick labels: take text spans from `page.get_text('dict')`, keep numeric spans of the tick font size inside the axis region, and fit pixel-to-value with `np.polyfit`. Check the calibration against a number quoted in the text or a printed value (e.g., heat-map cell labels can be read directly as text spans).
   - If an x-calibration looks wrong (picked up nearby labels), use the known discrete x values (e.g., budgets 3..8) by order.
3. **Raster images** (`pdfimages -list`, then `pdfimages -png`): keep the image and draw annotations on top (TikZ overlay or matplotlib `imshow` + `annotate`). Read values from the figure only when the text confirms them.
```
END THIRD-PARTY FILE f21bfd63281c3a31

The third-party file has ended. Everything between the f21bfd63281c3a31 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2673 of 6675 bytes. © mkaremm80 · MIT · https://github.com/mkaremm80/My-Skills-on-Claude/tree/HEAD/skills/paper-figure-guide/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
