plotting-agent

Render 300-DPI publication figures from outline-based plotting plans.

32|1|Updated May 19, 2026
One-click install
npx skills add https://github.com/woodfishhhh/EZ_math_model --skill plotting-agent-woodfishhhh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plotting-agent
Source: https://github.com/woodfishhhh/EZ_math_model/tree/main/skills/ez-math-model/external/paper-orchestra/skills/plotting-agent
Command: npx skills add https://github.com/woodfishhhh/EZ_math_model --skill plotting-agent-woodfishhhh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill turns a plotting plan into publication-ready figures by rendering plots/diagrams at the required size and DPI, then generating accurate, caption-ready descriptions.

Core Features & Use Cases

  • Figure rendering from a plan: Builds each figure from workspace/outline.json (plotting_plan) and produces one 300-DPI PNG per figure_id.
  • Data-grounded figure generation: Extracts numeric values or conceptual entities from workspace/inputs/experimental_log.md and/or workspace/inputs/idea.md, avoiding fabrication beyond the provided sources.
  • Optional vision-based refinement: Uses an iterative critique/redraw loop when vision is available to catch mislabeled axes, unreadable text, and layout artifacts.
  • Caption generation for LaTeX templates: Produces plain-text captions saved to workspace/figures/captions.json keyed by figure_id (no “Figure N:” prefixes).

Quick Start

Generate the paper figures by running step 2 plotting with your workspace/outline.json, workspace/inputs/idea.md, and workspace/inputs/experimental_log.md so the Skill writes the 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-ready paper figures from an outline?

To generate publication-ready paper figures, provide a plotting plan in `workspace/outline.json` along with input logs, and the Skill renders one 300-DPI PNG per `figure_id` while extracting data to avoid fabrication.

Can I automatically generate LaTeX captions for matplotlib diagrams?

Yes, you can automatically generate LaTeX captions for matplotlib diagrams by rendering the plots from your outline, which outputs plain-text descriptions keyed by `figure_id` to `workspace/figures/captions.json` without figure prefixes.

How does vision-assisted critique refinement work for academic style figure rendering?

Vision-assisted critique refinement works by running an iterative critique and redraw loop to catch mislabeled axes, unreadable text, and layout artifacts when vision capabilities are available during academic style figure rendering.

Does plotting-agent support extracting experimental data for conceptual diagrams?

Yes, plotting-agent supports extracting experimental data for conceptual diagrams by pulling numeric values or conceptual entities directly from `workspace/inputs/experimental_log.md` and `workspace/inputs/idea.md` to ground the figures.

What are the strict requirements for DPI and aspect ratio in paper automation figure rendering?

The strict requirements for paper automation figure rendering are a fixed 300 DPI output and exact aspect-ratio enforcement for every generated PNG, ensuring the plots meet publication standards.

Can I reuse pre-existing figures when rendering plots from a plotting plan?

Yes, you can reuse pre-existing figures when rendering plots from a plotting plan, as the Skill supports optional pre-existing figure reuse alongside generating new conceptual diagrams and plots.