Academic Figure Prompt skill
A skill that turns a research paper into detailed English prompts for image generators to produce top-conference-quality figures
- 2,939 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Reads the paper files from the project through the bash tool
- The full web platform in the repository sends paper content to external APIs and requires keys
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/academic-figure-promptDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Reads the paper files from the project through the bash tool
- The full web platform in the repository sends paper content to external APIs and requires keys
This is third-party code. Review the repository files before installing.
What it does
The academic-figure-prompt skill helps the agent generate detailed English prompts for image tools so you get professional figures for a research paper. First the agent reads the paper in PDF, LaTeX or Word, extracts key concepts, model architecture, data flows and notation, and identifies where figures are needed. Then, if the user has not set colors, the skill shows eight ready academic palettes, including colorblind-friendly options, and links to color tools. After a palette is chosen it assembles the prompt from a four-layer template: a global description, a section-by-section breakdown, global annotations with tensor dimensions, and a precise style specification with color values. It covers framework diagrams, network architectures, pipelines, module details, and comparison and ablation figures.
Who it is for. For research paper authors and teachers who need precise figures without hand-tuning prompts for image generators.
Good fit when
- You need to prepare figure prompts from a paper at top-conference quality
- You need a network architecture, pipeline or module detail diagram with dimensions and annotations
- You need a consistent academic palette, including a colorblind-safe one
Not a fit when
- You want the image itself, not the prompt text; you still need an image generator separately
- The figure is not academic but promotional or everyday graphics
Example request
Review this paper and build a prompt for a network architecture diagram in the Teal and Amber paletteLimitations
The standalone skill outputs only the prompt text: you get the final image by pasting the prompt into a separate generator such as NanoBanana, Gemini, DALL-E or Midjourney. The skill reads the paper files from the project through the bash tool. Besides the skill the repository ships a full web platform on FastAPI and React that automates the whole cycle from upload to generation, but it needs Anthropic and NanoBanana or Gemini API keys, which are unavailable from Russia without a VPN, and a local backend and frontend. The skill comes in two color variants: academic-figure-prompt and academic-figure-prompt-pastel.
How to disable. Remove the academic-figure-prompt folder from the agent's skills directory, for example from .claude/skills/ or .gemini/skills/.
FAQ
Do I need to deploy the whole platform?
No. The academic-figure-prompt skill is standalone and works in Claude Code, Gemini CLI or Cursor without installing the backend and frontend. The full platform is only needed if you want to automate the whole cycle with image generation inside one web app.
Does the skill draw the images itself?
No. It prepares a detailed English prompt, and you generate the image in a separate tool where you paste that prompt.
Discussion
No questions or reviews yet.
Related
SkillsA skill that draws paper figures as vectors: architecture, mechanism and overview figures exported to SVG, PDF and PPTX
Skill for publication figures: matplotlib charts for papers in one house style, with vector and raster export from sample scripts.
A skill that prepares and audits figures for Elsevier-style papers: size, fonts, lines, resolution and export from Python and R
Skill with 30 prompt templates for research papers in English and Chinese, from literature review to grant proposals
Three skills for paper figures: fig-analyze reads material, fig-draw picks a style and renders, fig-pptx builds an editable PPT.
Codex and Claude Code skill that turns a research paper into a literature report deck with real figures and an evidence check
README in short
The README describes a local platform for generating figures for research papers: upload a paper, analyze it via the Claude Agent SDK, and generate the prompt and image via the NanoBanana or Gemini API. The backend is FastAPI with SQLite and the frontend is React and Vite; the platform needs API keys and a local run. Separately the README highlights the standalone academic-figure-prompt skill, compatible with Claude Code, Gemini CLI and Cursor, which provides prompt generation without deploying the platform. The skill installs through npx skills add or by copying the folder into the agent's skills directory. It ships eight ready academic palettes and a detailed four-layer prompt template. MIT licensed.
README badge
Original SKILL.md
--- id: academic-figure-prompt name: Academic Figure Prompt version: 1.0.0 description: Use this skill whenever the user wants to generate detailed English prompts for AI image tools (NanoBanana / Gemini / DALL-E / Midjourney) to produce top-conference-quality academic figures—including framework diagrams, network architecture diagrams, pipeline flowcharts, module detail diagrams, comparison/ablation figures, and data pattern grids—especially when the user says "论文配图提示词", "生成论文配图", "学术论文生图", "架构图提示词", "框架图提示词", "顶会风格配图", "CVPR 风格图", "NeurIPS 风格图", "paper figure prompt", "academic diagram prompt", or provides a LaTeX/PDF/Word paper and asks for figure prompts. If the user has not specified a color scheme, present the 8 preset palette options and color tool links before generating any prompt. stages: [writing, research, review] tools: [bash] --- # Academic Figure Prompt Generate extremely detailed English prompts for a research paper, for AI image tools to produce top-conference-quality academic figures.