Auto Visio Helper logo

Auto Visio Helper

Community
0Antique
auto-visio-helper

Help Codex plan, generate, reproduce, and refine editable Microsoft Visio scientific diagrams. Use when users ask Codex to operate local Visio, create VSDX research figures, redraw uploaded paper screenshots or sketches in Visio, convert natural-language method descriptions into scientific diagrams, export preview PNG/PDF/SVG, or build editable model architecture, workflow, system architecture, experiment, pseudo-code, sequence, or module interaction diagrams.

Overview

Publisher0Antique
RepositoryAuto-Visio-Helper
Skill nameauto-visio-helper
Stars
251
Forks
9
Bundled files
34
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.

  • 34 bundled files

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

  • Open source

    Published by 0Antique on GitHub. Read the source before you install it.

Installation

Install the Auto Visio Helper 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/0Antique/Auto-Visio-Helper/tree/master
  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/0Antique/Auto-Visio-Helper.git \
  .claude/skills/auto-visio-helper
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Auto Visio Helper 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 Auto Visio Helper 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 Auto Visio Helper 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.

Auto Visio Helper

Use this skill to turn vague research-figure requests into editable Visio diagrams. Always plan the diagram as a verifiable drawing spec before driving local Visio.

Core Workflow

  1. Classify the task:

    • description_to_diagram: user describes a method, model, system, or experiment.
    • image_reproduction: user uploads a paper figure, sketch, PPT screenshot, or reference image.
    • paper_redraw: user wants a cleaner publication-ready version, not a strict copy.
    • visio_refine: user wants to modify an existing VSDX or exported preview.
  2. Gather only blocking requirements:

    • Language: Chinese, English, or bilingual.
    • Target use: paper, thesis, defense slides, project report, patent, or internal note.
    • Layout width: single-column, double-column, A4, slide, or custom size.
    • Style target: IEEE, Nature-like, clean engineering, Chinese thesis, or strict reference matching.
    • Export target: always propose preview exports (.png, optionally .pdf / .svg) before finalizing .vsdx.
  3. Produce a short design brief and a structured drawing spec first. Do not start Visio automation until the user has confirmed the spec or clearly asked to proceed without confirmation.

  4. Render the confirmed drawing spec with scripts/render_visio.py when Microsoft Visio is available on Windows. Keep all diagram elements editable: use Visio shapes, connectors, text, layers, names, and groups instead of flattening the diagram into one pasted image.

  5. Export preview files, inspect them, compare against the request or source image, then iterate on the drawing spec if needed.

Required Drawing Spec

Use JSON as the intermediate representation. Read references/drawing_spec.md before writing a complex spec.

Minimum shape:

json
{
  "page": {"width_mm": 297, "height_mm": 210, "unit": "mm"},
  "style": {"font": "Arial", "font_size_pt": 9, "theme": "paper_clean"},
  "nodes": [],
  "edges": [],
  "groups": [],
  "annotations": [],
  "exports": {"png": true, "pdf": false, "svg": false}
}

Use top-left coordinates in millimeters. Name every node and connector with stable IDs so the VSDX remains editable and reviewable.

Reference Files

Load only the file needed for the current task:

If a Visio template file is present, such as references/绘图模版.vsdx, treat it as a reusable local template. Do not load binary templates into context; pass their path to scripts or copy them as needed.

Image Reproduction Rules

For uploaded reference images:

  1. Decide whether the user wants structure reproduction, visual reproduction, or publication-grade redraw.
  2. Extract visible text, modules, hierarchy, arrows, color families, and layout proportions.
  3. Rebuild the image as editable Visio primitives. Do not paste the image as the final diagram.
  4. Export a preview and compare these points: missing nodes, wrong arrow direction, text mismatch, layout drift, inconsistent spacing, and style mismatch.

Quality Gate

Before final delivery, verify:

  • Text does not overlap shapes or connectors.
  • Arrow direction matches the intended data/control flow.
  • Same-level modules share consistent size, alignment, and spacing.
  • Font size is readable at the target paper or slide size.
  • Color count is controlled and black-white printing remains understandable when requested.
  • Line width, arrowheads, corner radius, and padding are consistent.
  • .vsdx keeps editable shapes, connectors, groups, layers, and named text boxes.
  • Preview exports match the confirmed spec closely enough for user review.

Script Usage

Validate a spec without opening Visio:

powershell
python scripts/render_visio.py spec.json --dry-run

Render with local Visio:

powershell
python scripts/render_visio.py spec.json --output output\diagram.vsdx --export-png output\diagram.png

Use --template references\绘图模版.vsdx when a local Visio template should define page theme, stencils, or base styles.

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 Auto Visio Helper AI skill do?

Help Codex plan, generate, reproduce, and refine editable Microsoft Visio scientific diagrams. Use when users ask Codex to operate local Visio, create VSDX research figures, redraw uploaded paper screenshots or sketches in Visio, convert natural-language method descriptions into scientific diagrams, export preview PNG/PDF/SVG, or build editable model architecture, workflow, system architecture, experiment, pseudo-code, sequence, or module interaction diagrams.

Why use Auto Visio Helper on TypingMind?

Because you install it once and use it with any model. Auto Visio Helper 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 Auto Visio Helper in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/0Antique/Auto-Visio-Helper/tree/master. 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 Auto Visio Helper?

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 Auto Visio Helper?

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

Is the Auto Visio Helper AI skill free?

It is published on GitHub by 0Antique. Check the repository for licensing terms. 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 👇