skills.rest
Ar9av
Ar9avCOMMUNITY
Explore all skills by this author →
Website𝕏@_ar9avGitHub

plotting-agent

Render publication-ready PNG figures and captions from plotting plans and experimental logs.

635|88|Updated Apr 9, 2026
Search Tags:#visualization#plotting#matplotlib#captioning#academic-writing#paperbanana#figure-generation
One-click install
npx skills add https://github.com/Ar9av/PaperOrchestra --skill plotting-agent-ar9av
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: plotting-agent
Source: https://github.com/Ar9av/PaperOrchestra/tree/main/skills/plotting-agent
Command: npx skills add https://github.com/Ar9av/PaperOrchestra --skill plotting-agent-ar9av

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires matplotlib, numpy, pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

The plotting-agent automates the tedious, error-prone process of turning a structured plotting plan and experiment notes into publication-ready figures and captions, ensuring consistent styling, exact aspect ratios, and 300 DPI output required by LaTeX conference templates.

Core Features & Use Cases

  • Plan-driven rendering: Read plotting_plan entries from workspace/outline.json and render one PNG per figure_id using data in workspace/inputs/idea.md or workspace/inputs/experimental_log.md.
  • Deterministic fallback + optional backbone: Prefer PaperBanana when configured via PAPERBANANA_PATH, otherwise generate matplotlib scripts and call deterministic helpers to render plots and diagrams.
  • Closed-loop refinement: Optionally run a VLM-guided critique loop (host vision required) with up to three redraw iterations and produce context-aware captions saved to workspace/figures/captions.json.
  • Hard validation rules: Enforce the repository's 12 allowed aspect ratios, 300 DPI, muted academic palette, hidden top/right spines, and caption existence to avoid downstream LaTeX compile failures.
  • Use Case: Convert an experiment log and outline into a set of figures and captions ready to be included in a submission PDF.

Quick Start

Render all figures from the outline and save produced PNGs and captions into workspace/figures.

Frequently Asked Questions about plotting-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate publication-quality figures from experimental logs?▼

Generate publication-ready figures by reading a structured plotting plan and experimental logs to render 300 DPI PNGs with exact aspect ratios and context-aware captions, saving outputs directly to your workspace.

Can I create matplotlib plots automatically for academic papers?▼

Yes, you can create matplotlib plots automatically by generating matplotlib scripts from your plotting plan and experimental data, using deterministic renderers to produce styled plots and conceptual diagrams.

Does the figure generation process enforce specific DPI and aspect ratios for LaTeX templates?▼

Yes, the figure generation process enforces 12 allowed aspect ratios, 300 DPI output, muted academic palettes, and hidden top and right spines to prevent downstream LaTeX compile failures.

What is the best way to automate captioning for paper figures?▼

Automate captioning for paper figures by using a closed-loop VLM-guided critique to produce context-aware captions, which are saved as a JSON file alongside the generated PNG figures.

Do I need a PaperBanana backend to render plots and diagrams?▼

No, you do not need a PaperBanana backend to render plots and diagrams; the system falls back to deterministic matplotlib renderers automatically when PaperBanana is unavailable.

How many redraw iterations are supported during VLM critique?▼

The VLM-guided critique loop supports up to three redraw iterations to refine publication-quality figures when host vision is available.

Related Skills

Explore More Education & Research Skills→
woodfishhhhwoodfishhhh
32

outline-agent

Generate a schema-validated JSON paper outline from methodology and experimental logs.

Community
Intermediate
nahisahonahisaho
3

scientific-publication-figures

Generate publication-quality multi-panel figures with matplotlib/seaborn and export to PNG, SVG, or PDF.

Community
Advanced
leonardodalinkyleonardodalinky
87

plotting-agent

Generate publication-ready PNG figures from outline.json specifications using matplotlib.

Community
Advanced
ovachieverovachiever
52

scientific-visualization

Generate publication-ready scientific figures with matplotlib, seaborn, and plotly.

Community
Advanced