Engineering Figure Agent logo

Engineering Figure Agent

Community
heyu-233
engineering-figure-agent

Create engineering and CS paper figures from local paper context, method notes, code, data tables, or existing drafts. Use for figure briefs, conceptual diagrams, architecture figures, algorithm workflows, exact publication plots, prompt refinement, and light figure critique.

Overview

Publisherheyu-233
Repositoryengineering-figure-agent
Skill nameengineering-figure-agent
Stars
310
Forks
14
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by heyu-233 on GitHub. Read the source before you install it.

Installation

Install the Engineering Figure Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/heyu-233/engineering-figure-agent/tree/main/adapters/claude-code/skills/engineering-figure-agent
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/heyu-233/engineering-figure-agent.git /tmp/engineering-figure-agent
mkdir -p .claude/skills
cp -r /tmp/engineering-figure-agent/adapters/claude-code/skills/engineering-figure-agent .claude/skills/engineering-figure-agent
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Engineering Figure Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Engineering Figure Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Engineering Figure Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Engineering Figure Agent For Claude Code

Use this skill for the figure-production layer after the figure goal is reasonably clear.

If the figure claim, panel logic, or caption argument is still unclear, first use a research-writing or paper-analysis workflow to settle the scientific message.

Core Decision

  • Use image mode for conceptual figures: system architecture, algorithm workflow, graphical abstract, hardware block diagram, or reference-inspired redraw.
  • Use plot mode for exact values: benchmark bars, ablation plots, trend curves, heatmaps, scatter plots, or multi-panel quantitative figures.
  • Use mixed when exact plot panels should be rendered locally and conceptual panels should be generated or described separately.

Workflow

  1. Inspect the user's paper context, data, caption draft, or figure brief.
  2. Create or normalize a figure brief with figure_goal, paper_claim, figure_type, mode, panels, must_keep_labels, data, style_constraints, output_formats, and verification_checklist.
  3. If numeric truth matters and data is missing, ask for values instead of inventing them.
  4. For image mode, produce a final prompt using concise labels, white background, publication style, and faithful technical terms.
  5. For plot mode, produce a concise plot-request JSON. Use data.series[] for multi-series scatter plots, and use outside or dedicated legends for dense annotated charts.
  6. Keep real API keys outside the repository.
  7. Require explicit user opt-in before sending API keys, prompts, or files to third-party provider endpoints.
  8. For high-resolution or final-export requests, fail closed if the configured high-resolution path is unavailable instead of silently downgrading.
  9. Treat generated diagrams as drafts until labels, scientific claims, and numeric values are verified.

Output Files

Prefer these files when writing to disk:

text
figure-brief.md
prompt.txt
plot-request.json
output/

Quality Rules

  • Do not fabricate measurements, benchmark improvements, device values, or unsupported causal claims.
  • Keep labels readable at paper width.
  • Preserve standard English symbols and formulas in Chinese figures when they improve clarity.
  • Never use image generation for exact numeric chart geometry.
  • Do not present light figure critique as a full reviewer-style paper-figure audit.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Engineering Figure Agent AI skill do?

Create engineering and CS paper figures from local paper context, method notes, code, data tables, or existing drafts. Use for figure briefs, conceptual diagrams, architecture figures, algorithm workflows, exact publication plots, prompt refinement, and light figure critique.

Why use Engineering Figure Agent on TypingMind?

Because you install it once and use it with any model. Engineering Figure Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Engineering Figure Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/heyu-233/engineering-figure-agent/tree/main/adapters/claude-code/skills/engineering-figure-agent. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Engineering Figure Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Engineering Figure Agent?

As many as you like. As long as a model supports skills, you can use Engineering Figure Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Engineering Figure Agent AI skill free?

Yes. It is published on GitHub by heyu-233 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇