Tesseract Design

Organization

mirage-hq

tesseract-design

Create and revise static visual designs as editable Tesseract compositions and rendered PNGs, including posters, social graphics, slide layouts, diagrams, and web/UI mockups. Use when the requested deliverable is a design image.

Overview

Publisher	mirage-hq
Repository	`Tesseract`
Skill name	`tesseract-design`
Stars	156
Forks	13
Bundled files	8
Links	Skill source Repository

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.
8 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by mirage-hq on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/mirage-hq/Tesseract/tree/main/skills/tesseract-design
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.

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/mirage-hq/Tesseract.git /tmp/Tesseract
mkdir -p .claude/skills
cp -r /tmp/Tesseract/skills/tesseract-design .claude/skills/tesseract-design

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tesseract Design 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 Tesseract Design 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 Tesseract Design 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.

Design with Tesseract

For converting files to or from other editing tools, such as Premiere Pro or After Effects, read conversion. When opening shared or older .tsrct files, updating tools, or investigating load/render differences, read versions and compatibility.

Turn the user's brief into static visual designs rendered with tsrct preview. Deliver the PNGs as the primary result and keep their editable .tsrct sources for revisions. Match the format to the request: a poster, social graphic, slide, diagram, interface mockup, or another composition.

The CLI may send basic usage telemetry for some commands. Read telemetry for collected data and opt-out; never enable telemetry on the user's behalf.

Establish the design

Use the context already provided: the design’s purpose, audience, message or action, intended medium, copy, brand assets, visual references, and requested dimensions or variants. Inspect supplied references and assets. Ask only for missing information that materially changes the design; state reasonable assumptions for open choices and continue. For revisions, preserve the existing direction and scope.

Choose a visual direction tied to the brief and content: type hierarchy, spacing, grid, color, and imagery. Use realistic copy and supplied assets; identify placeholder content rather than inventing customer evidence or claims. Adapt composition and type to each requested format. For web/UI mockups with responsive variants, reflow content for each width instead of shrinking the desktop image.

Author and preview

Resolve this skill's root from the directory containing this SKILL.md. Follow installation, check the required CLI version once per session, and use its resolved executable path throughout.
Follow static authoring to create or revise the portable document, set its actual canvas dimensions, import fonts/images, and save editable layers. Query the installed schemas for the fields needed; never invent APIs or assume browser/CSS behavior.
Keep text, shapes, diagram elements, and layout geometry as native editable layers. Use images for photography, logos, and other supplied raster assets. Do not flatten the entire layout into one image. Use named groups where useful for related elements or components.
Render a PNG early, open it, and revise the saved composition. Review hierarchy, alignment, spacing, line breaks, clipping, image crops, contrast, and text legibility at the intended viewing size. Inspect large or detailed designs in close-up as well as at an overview scale. A successful render alone does not establish a good design.

Deliver designs

Render each final design or requested variant with preview from its saved source. Use clear names such as Poster.png, Social-square.png, or Home-mobile.png, and show the images inline when supported. Include a clearly labeled link to each final PNG alongside its matching editable .tsrct source, even when displaying the PNG inline. Use absolute local paths for these links and state the actual image dimensions. Keep working JSON and useful assets with the project for continuation.

The PNGs are the finished deliverable; no video export, sound pass, or animation is needed. Explain any missing assets, unreviewed output, or renderer limits. For web/UI mockups, distinguish the static design from an implemented website or working interaction. Slides are PNG layouts with editable Tesseract sources; do not imply a PowerPoint or print-production file was delivered.

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 Tesseract Design AI skill do?

Why use Tesseract Design on TypingMind?

Because you install it once and use it with any model. Tesseract Design 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 Tesseract Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mirage-hq/Tesseract/tree/main/skills/tesseract-design. 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 Tesseract Design?

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 Tesseract Design?

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

Is the Tesseract Design AI skill free?

It is published on GitHub by mirage-hq. 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

Tldraw Offline

NousResearch

OrganizationPopular

Drive and script tldraw offline canvases with an agent.

Brand Guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual…

Solid

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

Canvas

Present hosted widget documents on a connected macOS panel and control panel visibility or navigation.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Design with Tesseract

Establish the design

Author and preview

Deliver designs

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now