skills.rest
raja21068
raja21068COMMUNITY
Explore all skills by this author →
WebsiteGitHub

plotting-agent

Render figure_id entries from outline.json into 300-DPI PNGs with captions.

2|1|Updated Apr 19, 2026
Search Tags:#matplotlib#captioning#diagram rendering#figure generation#paper writing#experiment visualization#academic plotting
One-click install
npx skills add https://github.com/raja21068/AutoResearch --skill plotting-agent-raja21068
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: plotting-agent
Source: https://github.com/raja21068/AutoResearch/tree/main/skills/paper-pipeline/plotting-agent
Command: npx skills add https://github.com/raja21068/AutoResearch --skill plotting-agent-raja21068

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill turns an experiment outline and raw experiment notes into publication-ready plots and conceptual diagrams with consistent styling, verified layouts, and captions you can directly place into a paper.

Core Features & Use Cases

  • Figure execution from an outline: Reads workspace/outline.json plotting instructions (per figure_id) and generates one high-resolution PNG per figure entry.
  • Data-grounded rendering: Extracts plot values from workspace/inputs/experimental_log.md (numeric tables) or workspace/inputs/idea.md (conceptual entities) without inventing unplotted trends.
  • Caption generation pipeline: Produces workspace/figures/captions.json using a strict caption prompt so the figure captions are plain text and publication compliant.
  • Optional VLM critique loop: If your host supports vision, iteratively refines the rendered image up to 3 critique iterations based on the figure objective.

Quick Start

Ask the AI to generate the figures for your paper using workspace/outline.json, workspace/inputs/experimental_log.md, and workspace/inputs/idea.md, producing PNGs in workspace/figures/ plus workspace/figures/captions.json.

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 raw experimental logs for a paper?▼

To generate publication-quality figures, this skill reads plotting specifications from an outline.json file and extracts data directly from experimental_log.md to render 300-DPI PNGs with consistent academic styling.

What is the best way to automate diagram rendering and caption generation for academic papers?▼

Automating diagram rendering and caption generation involves reading an outline file to plot conceptual entities from idea.md, then writing strict plain-text captions to a captions.json file keyed by figure_id.

Can I use matplotlib to create paper-ready plots without manually setting aspect ratios?▼

Yes, you can create paper-ready plots using a deterministic matplotlib fallback that automatically resolves aspect ratios via a standard 12 ratio set for consistent figure dimensions.

Does the figure generation pipeline support visual critique loops for refining academic plots?▼

Yes, the figure generation pipeline supports an optional VLM critique loop that iteratively refines rendered academic plot images up to 3 critique iterations based on the figure objective.

How do I ensure my experiment visualization does not invent unplotted data trends?▼

To ensure experiment visualization remains data-grounded, the rendering process strictly extracts plot values from numeric tables in experimental_log.md without inventing any unplotted trends.

Related Skills

Explore More Education & Research Skills→
Ar9avAr9av
635

plotting-agent

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

Community
Advanced
woaijiadanoowoaijiadanoo

academic-polisher

Convert first-person thesis text to passive phrasing and compilable LaTeX.

Community
Intermediate
OpenRaiserOpenRaiser
334

Float Optimizer Skill

Optimize LaTeX figure and table floats to resolve B1–B4 placement defects.

Official
Advanced
AMGrobelnikAMGrobelnik
1

aii_image_gen_nano_banana

Generate research figures and diagrams via the Gemini API with NeurIPS style presets.

Community
Intermediate