academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.
npx skills add OpenRaiser/NanoResearch --skill academic-plotting --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Generates publication-quality figures for ML papers by transforming research context into two types of visuals: architecture diagrams using Gemini and data-driven figures using matplotlib/seaborn. It guides when to use each workflow and provides a structured process for extracting entities and relationships or data, then producing diagrams or charts accordingly.
How it works
- For diagrams (Workflow 1): reads the research context (paper section, description) to identify components and relationships, then uses Gemini to generate architecture/system diagrams. It prescribes a multistep prompt structure with sections like FRAMING, VISUAL STYLE, COLOR PALETTE, LAYOUT, CONNECTIONS, and CONSTRAINTS, and includes a generation script template that handles Gemini API interaction, prompts, and three attempts.
- For data charts (Workflow 2): reads experiment results or data, determines chart type automatically, and generates data-driven figures with matplotlib/seaborn. It provides a publication-styled template, a chart-type decision guide, and a workflow to prepare data, apply styling, highlight the paper’s method, and export outputs (PDF and PNG). It also specifies a saving convention for scripts and emphasizes reproducibility.
- It enforces dependency requirements (matplotlib>=3.8.0, seaborn>=0.13.0, numpy, google-genai>=1.0.0) and directs to save generation scripts under a figures directory with naming like gen_fig_<name>.py.
When to use it
- Use the Diagram workflow when the figure is an architecture, system design, or workflow diagram requiring boxes, arrows, and labeled components.
- Use the Data Figures workflow when the figure conveys numerical results such as training curves, ablations, or comparisons, where axes and precise data presentation are required.
What it can touch
- Tools: claude-code (declared tool)
- Libraries and formats referenced: matplotlib, seaborn, numpy, google-genai, Gemini (via API key GEMINI_API_KEY), and Python script templates for figure generation.
Caveats
- License: MIT
- Declared dependencies and environment setup required (e.g., GEMINI_API_KEY) to generate Gemini diagrams.
- The workflow emphasizes adherence to specific prompt structure for Gemini and requires three generation attempts for diagrams, with explicit prompts and layout constraints.
# Academic Plotting for ML Papers Generate publication-quality figures for ML/AI conference papers. Two distinct workflows: 1. **Diagram figures** (architecture, system design, workflows, pipelines) — AI image generation via Gemini 2. **Data figures** (line charts, bar charts, scatter plots, heatmaps, ablations) — matplotlib/seaborn ## When to Use Which Workflow | Figure Type | Tool | Why | |-------------|------|-----| | Architecture / system diagram | Gemini (Workflow 1) | Complex spatial layouts with boxes, arrows, labels | | Workflow / pipeline / lifecycle | Gemini (Workflow 1) | Multi-step processes with connections | | Bar chart, line plot, scatter | matplotlib (Workflow 2) | Precise numerical data, reproducible | | Heatmap, confusion matrix | matplotlib/seaborn (Workflow 2) | Structured grid data | | Ablation table as chart | matplotlib (Workflow 2) | Grouped bars or line comparisons | | Pie / donut chart | matplotlib (Workflow 2) | Proportional data (use sparingly in ML papers) | | Training curves | matplotlib (Workflow 2) | Loss/accuracy over steps/epochs | **Rule of thumb**: If the figure has numerical axes, use matplotlib. If the figure has boxes and arrows, use Gemini. -
- When to Use Which Workflow
- Step 0: Context Analysis & Extraction
- Extraction Workflow
- Auto-Detection Examples
- Workflow 1: Architecture & System Diagrams (AI Image Generation)
- Visual Styles
- Curated Color Palettes
- Checklist
- Prompt Structure (6 Sections)
- Generation Script Template
- Key Rules
- Workflow 2: Data-Driven Charts (matplotlib/seaborn)
- Chart Type Decision Guide
- Publication Styling Template
What does the academic-plotting skill do?
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.
How do I install it?
Run `npx skills add OpenRaiser/NanoResearch --skill academic-plotting --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From OpenRaiser/NanoResearch, a repository with 1,480 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.