Academic Plotting for ML Papers
Skill Verifiziert AktivGenerates 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.
Automate the creation of publication-quality figures for ML/AI conference papers, saving researchers significant time and ensuring visual consistency and correctness.
Funktionen
- Generate architecture diagrams via Gemini AI
- Auto-select chart types based on data
- Create data-driven figures with matplotlib/seaborn
- Apply venue-specific styling (color palettes, fonts, sizes)
- Highlight 'our method' in data visualizations
Anwendungsfälle
- Creating system architecture diagrams for a conference paper.
- Generating plots for experimental results (e.g., training curves, ablation studies).
- Ensuring figures meet the visual and formatting standards of top ML venues.
- Quickly producing multiple figures for a paper using descriptive text or data.
Nicht-Ziele
- Writing the entire ML paper (though it complements the 'ML Paper Writing' skill).
- Generating interactive plots or web-based visualizations.
- Performing complex statistical analysis beyond basic plotting.
- Replacing manual plot customization for highly niche or artistic requirements.
Workflow
- User provides research context or data.
- Skill extracts relevant entities, relationships, or data dimensions.
- Skill selects appropriate figure type (diagram or data chart) and style.
- Skill generates figure using Gemini or matplotlib/seaborn.
- Skill saves figure as PDF and PNG with appropriate naming conventions.
Praktiken
- Visualization Best Practices
- Diagram Generation
- Data Visualization
- Publication Standards
Voraussetzungen
- Python 3.8+
- Matplotlib >= 3.8.0
- Seaborn >= 0.13.0
- Numpy
- google-genai >= 1.0.0
- GEMINI_API_KEY environment variable set
Execution
- info:Pinned dependenciesThe SKILL.md lists dependencies (matplotlib>=3.8.0, etc.) but does not include a lockfile or explicit pinning for the Python environment, which could lead to versioning issues.
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skillsQualitätspunktzahl
VerifiziertVertrauenssignale
Ähnliche Erweiterungen
Scientific Visualization
98Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.
Baoyu Diagram
98Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.
Seaborn Statistical Visualization
98Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.
Matplotlib
97Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.
Alterlab Seaborn
95Part of the AlterLab Academic Skills suite. Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.
Alterlab Matplotlib
95Part of the AlterLab Academic Skills suite. Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.