paper-illustration-image2

Generate paper-ready academic figures with CVPR/ICLR/NeurIPS style constraints.

2|1|Updated Apr 19, 2026
One-click install
npx skills add https://github.com/raja21068/AutoResearch --skill paper-illustration-image2-raja21068
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper-illustration-image2
Source: https://github.com/raja21068/AutoResearch/tree/main/skills/aris/paper-illustration-image2
Command: npx skills add https://github.com/raja21068/AutoResearch --skill paper-illustration-image2-raja21068

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you generate publication-quality academic illustration images with correct layout, styling, and readable labels, avoiding the trial-and-error that usually makes diagram-generation unusable for papers.

Core Features & Use Cases

  • Execution-grounded, multi-stage generation: plans the figure, optimizes layout, verifies CVPR/ICLR/NeurIPS-style constraints, generates a native raster via an MCP bridge, and then strictly reviews it.
  • Strict acceptance criteria with iterative refinement: scores outputs (target score ≥ 9), rejects unclear or non-paper-ready figures, and loops with specific improvement instructions up to a capped number of iterations.
  • Canonical integration artifacts: runs a required preflight step, finalizes to standardized outputs (including LaTeX include snippet and verification receipts), and verifies before reporting success.
  • Use Case: turn a paper method description like an end-to-end pipeline into a clean architecture/workflow figure with correct arrow direction, hierarchy, and print-friendly typography.

Quick Start

Ask for a paper-ready workflow diagram and run the Skill’s required preflight, then generate the figure through the Codex image2 bridge and finalize with verification.

Frequently Asked Questions about paper-illustration-image2

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

FAQPage Schema
How do I generate publication-quality academic figures for CVPR or NeurIPS papers?

To generate publication-quality academic figures, provide a figure request to trigger structured prompt planning, enforce CVPR/ICLR/NeurIPS style constraints, and render native raster images through an MCP bridge with iterative visual scoring.

What's the best way to turn a paper method description into a clean workflow diagram?

Turning a paper method description into a workflow diagram involves planning the figure layout, optimizing hierarchy and arrow direction, verifying print-friendly typography, and rendering the output through an iterative refinement loop.

How does iterative refinement work when generating academic diagrams?

Iterative refinement for academic diagrams works by scoring generated outputs against a target score of 9 or higher, rejecting unclear figures, and looping with specific improvement instructions up to a capped number of iterations until visual constraints pass.

Can I use Codex image generation to create LaTeX-ready illustrations?

Yes, you can use the Codex image2 MCP bridge to create LaTeX-ready illustrations by running a required preflight step, generating the native raster image, and finalizing to standardized outputs including a LaTeX include snippet and verification receipts.

Why does my generated paper diagram fail the visual acceptance check?

A generated paper diagram fails the visual acceptance check when it scores below the target score of 9, contains unclear labels, violates CVPR style constraints, or lacks print-friendly typography, triggering specific improvement instructions for another iteration.