Design Mixer Prototyping

Q: Why use Design Mixer Prototyping on TypingMind?

Because you install it once and use it with any model. Design Mixer Prototyping 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.

Q: How do I install Design Mixer Prototyping in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Sahil-SS9/agent-personas/tree/main/skills/design-mixer-prototyping. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Q: Which AI models can use Design Mixer Prototyping?

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.

Q: How many AI models can I use with Design Mixer Prototyping?

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

Q: Is the Design Mixer Prototyping AI skill free?

Yes. It is published on GitHub by Sahil-SS9 under the MIT license. You only pay your own AI provider for the tokens you use.

Q: 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.

Q: 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.

Community

Sahil-SS9

design-mixer-prototyping

Give people live design-token controls on a delivered prototype: faders/knobs that retheme instantly, export cleanly, and remove without residue.

Overview

Publisher	Sahil-SS9
Repository	`agent-personas`
Skill name	`design-mixer-prototyping`
Stars	67
Forks	4
Bundled files	1
License	MIT
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.
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 Sahil-SS9 on GitHub. Read the source before you install it.

Installation

Install the Design Mixer Prototyping 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/Sahil-SS9/agent-personas/tree/main/skills/design-mixer-prototyping
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/Sahil-SS9/agent-personas.git /tmp/agent-personas
mkdir -p .claude/skills
cp -r /tmp/agent-personas/skills/design-mixer-prototyping .claude/skills/design-mixer-prototyping

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

Use it in TypingMind

Enable Design Mixer Prototyping 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 Design Mixer Prototyping 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 Design Mixer Prototyping 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 mixer prototyping

A portable controls layer for delivered prototypes: the recipient adjusts tokens and sees the design retheme instantly — no model call, no tooling, no dependency left behind.

When to use

A design/prototype is delivered and the recipient should be able to explore variants (density, accent, type, motion). Attachable to any token-driven page; never required for viewing the design.

Controls (each maps to real properties)

Typography: scale step, display weight, letter-spacing, line-height.
Spacing/density: base space value and its scale multiplier; density presets (compact/comfy/editorial).
Colour: accent hue/chroma (perceptual colour space; derived hover/tint variants recompute automatically), light/dark scheme, surface tint strength.
Shape/depth: corner-radius scale, shadow strength.
Motion: intensity (0 = none), one-authored-moment toggle.

Rules: expose only controls the current composition uses, advanced controls tucked away; every control is direct-manipulation plus a keyboard/numeric-entry alternative; a11y (roles, labels, contrast) is re-checked automatically at every change and violations are surfaced, not silently accepted.

Scope and behaviour

Select target: whole page (default) or a named component subtree.
Every fader move applies locally and instantly (CSS custom properties — no inference call); changes are staged until applied.
Presets: named snapshots; undo/redo stack; reset returns to shipped tokens.
Export: token values as JSON + stylesheet, schema-validated; import round-trips exactly.
Bake-in: accepted settings are written into the design's stylesheet as its own tokens; after removal the design is byte-matched to the mixed state. Removal is a deletion, not a toggle: no scripts, no classes, no placeholder markup remain.

Integrity rules

The mixer is always removable: it edits tokens; it never edits component structure.
It never bypasses the accessibility floor: mixing may change tokens, never below contrast minimums (the mixer corrects derived text colours and reports the correction).
Performance budget: control feedback <50ms, no layout thrash, no scroll jank while open.
The delivered design loads and looks right with the mixer blocked or absent.

Done

Mixer attached with stated controls; a11y re-checks pass across the sampled token range; export round-trip verified; removal produces a working design identical to the applied mixed state.

Bundled files

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

NOTICE1 KB

Frequently asked questions

What does the Design Mixer Prototyping AI skill do?

Give people live design-token controls on a delivered prototype: faders/knobs that retheme instantly, export cleanly, and remove without residue.

Why use Design Mixer Prototyping on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Sahil-SS9/agent-personas/tree/main/skills/design-mixer-prototyping. 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 Design Mixer Prototyping?

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 Design Mixer Prototyping?

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

Is the Design Mixer Prototyping AI skill free?

Yes. It is published on GitHub by Sahil-SS9 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

Brand Guidelines

anthropics

OrganizationPopular

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.

Diagram Maker

Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Design mixer prototyping

When to use

Controls (each maps to real properties)

Scope and behaviour

Integrity rules

Done

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now