TypingMindTypingMindThe best frontend for AI
Tidyfactor Design logo

Tidyfactor Design

Organization
TidyFactor
tidyfactor-design

Code-native UI design lifecycle engine (Figma alternative) with Contextual Decision Layer (CDL). Supports all 7 design stages with zero per-page CSS/JS and pluggable CSS foundations (Native, Tailwind, daisyUI, Pico, Hybrid). Trigger on commands 'brief', 'study', 'init', 'brand', 'tokens', 'palette', 'layout', 'components', 'page', 'dashboard', 'motion', 'i18n', 'audit', 'deploy', or design system requests.

Overview

PublisherTidyFactor
RepositoryDesign
Skill nametidyfactor-design
Stars
7
Forks
0
Bundled files
152
Links
Skill sourceRepositoryHomepage
  • 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.

  • 152 bundled files

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

  • Open source

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

Installation

Install the Tidyfactor Design 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/TidyFactor/Design/tree/main
  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/TidyFactor/Design.git \
  .claude/skills/tidyfactor-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tidyfactor 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 Tidyfactor 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 Tidyfactor 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.

TidyFactor Design (Code-Native UI Design Lifecycle Engine)

A command dispatcher supporting the full UI design lifecycle—from discovery through developer handoff—with zero build steps and complete design system consistency.

Commands

User intentCommandWhat it loads
Strategic Discovery & Brief Resolutionreferences/commands/brief.mdworkflows/brief.md + memory/decision-points.md + memory/06-quality-bar.md
Extract design DNA from referencereferences/commands/study.mdcommands/study.md + memory/01-design-schools.md + memory/06-quality-bar.md
Start brand-new design system / prototypereferences/commands/init.mdworkflows/init-prototype.md + memory/architecture.md + memory/foundations.md
Scaffold or manage brand tokens (YAML / JSON)references/commands/brand.mdcommands/brand.md + memory/11-brand-json-v2.md
Mood-routed typography pairingreferences/commands/typography.mdcommands/typography.md + memory/12-typography-matrix.md
Select design school & movementreferences/commands/school.mdcommands/school.md + memory/01-design-schools.md
Design tokens, palette & color extractionreferences/commands/tokens.mdcommands/tokens.md + memory/02-design-tokens.md
Asset hygiene, media & image optimizationreferences/commands/assets.mdcommands/assets.md + memory/10-python-tooling.md
Macrostructure layout archetype selectionreferences/commands/layout.mdcommands/layout.md + memory/13-layout-archetypes.md
Navigation (N1-N9) & Footer (Ft1-Ft8) systemsreferences/commands/nav-footer.mdcommands/nav-footer.md + memory/14-nav-footer-catalog.md
Add content/marketing page or app screenreferences/commands/page.mdworkflows/init-prototype.md + memory/05-component-anatomy.md
Manage shared UI components & 8-state catalogreferences/commands/components.mdcommands/components.md + memory/05-component-anatomy.md
Core Component Matrices (Eyebrow, Hero, Cards, CTA, Seams, Metrics)references/commands/components.mdmemory/21-eyebrow-kicker-matrix.md through 28-shared-motion-primitives.md
Shared animations, scroll & motion recipesreferences/commands/motion.mdcommands/motion.md + memory/04-motion-principles.md + memory/28-shared-motion-primitives.md
Interactive prototype navigation flowreferences/commands/flow.mdcommands/flow.md + memory/09-prototype-flow.md
Arabic/RTL localization & bidirectional UIreferences/commands/i18n.mdcommands/i18n.md + memory/08-arabic-bilingual.md
Asset performance budget & size verificationreferences/commands/perf.mdcommands/perf.md + memory/15-performance-budget.md
Structural consistency audit & quality barreferences/commands/audit.mdworkflows/audit-prototype.md + memory/06-quality-bar.md
Extract design system from external URL/clonereferences/commands/clone.mdworkflows/clone-prototype.md + memory/03-narrative-conversion.md
Unify drifted prototype under design systemreferences/commands/retrofit.mdworkflows/retrofit-prototype.md + memory/07-consistency-contract.md
Developer handoff specs & CSS variable mapreferences/commands/handoff.mdcommands/handoff.md + memory/11-brand-json-v2.md
Local preview and static deploymentreferences/commands/deploy.mdcommands/deploy.md + memory/06-quality-bar.md

Read only the command file that matches the request. Do not load all commands simultaneously.

Non-Negotiable Invariants

  1. Contextual Decision Layer (CDL): Resolve design baselines via /brief or .tidyfactor/design-brief.md before emitting code.
  2. Zero per-page CSS/JS: Every visual token and component style lives inside design-system/. Pages contain markup only.
  3. Single CSS Foundation: Lock Native, Tailwind, daisyUI, Pico, or Hybrid once per project; never mix foundations.
  4. Typography Discipline: Arabic display headings use El Messiri, body copy uses Tajawal. Never use Amiri for headings above 24px.
  5. 7-Axis Pre-Emit Critique: All components and layouts must be evaluated with /* Pre-emit critique: P5 H5 E5 S5 R5 V5 D5 */.

Tooling Scope (Rule 10)

  • Languages: Python 3 (stdlib, Pillow, rembg)
  • Mutations: Read-only audits (audit_design), palette token generation (extract_palette), image optimization (optimize_media)
  • Network: None required (100% offline deterministic execution)

Skill vs MCP Boundary (Rule 12)

  • Inside Skill: Static design tokens, typography pairings, layout archetypes, component matrices (21–28), and zero-build CSS templates.
  • MCP Layer: Companion MCP tools invocable via tidyfactor-brain's run_skill_tool(skill_id="tidyfactor-design", ...); live remote asset scraping and database operations delegate to external MCP servers.

Bundled files

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

and 92 more files.

Frequently asked questions

What does the Tidyfactor Design AI skill do?

Code-native UI design lifecycle engine (Figma alternative) with Contextual Decision Layer (CDL). Supports all 7 design stages with zero per-page CSS/JS and pluggable CSS foundations (Native, Tailwind, daisyUI, Pico, Hybrid). Trigger on commands 'brief', 'study', 'init', 'brand', 'tokens', 'palette', 'layout', 'components', 'page', 'dashboard', 'motion', 'i18n', 'audit', 'deploy', or design system requests.

Why use Tidyfactor Design on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TidyFactor/Design/tree/main. 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 Tidyfactor 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 Tidyfactor Design?

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

Is the Tidyfactor Design AI skill free?

It is published on GitHub by TidyFactor. 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.

Related AI Skills

View all
NousResearch logo

Ip As Logo

NousResearch
OrganizationPopular

Design minimal cute IP mascot marks readable at 32px.

53.5K
250.4K
Instructions
View
NousResearch logo

Mono Color

NousResearch
OrganizationPopular

Generate one- or two-ink editorial print poster images.

53.5K
250.4K
9 files
View
NousResearch logo

Pretext

NousResearch
OrganizationPopular

Build creative browser demos with DOM-free text layout.

53.5K
250.4K
3 files
View
NousResearch logo

Sketch

NousResearch
OrganizationPopular

Throwaway HTML mockups: 2-3 design variants to compare.

53.5K
250.4K
Instructions
View

Set up your own AI workspace now

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