Human Optimized Frontend logo

Human Optimized Frontend

Community
viralcode
human-optimized-frontend

Generates a frontend interface that is visually pleasing and experientially sound by jointly optimizing aesthetics, motion graphics, and user experience (UX) using quantified evaluation. Use only when the user explicitly invokes this skill by name to redesign a frontend. Trigger keywords: use human-optimized-frontend, redesign frontend, redesign interface.

Overview

Publisherviralcode
Repositoryopenwhale
Skill namehuman-optimized-frontend
Stars
65
Forks
11
Bundled files
1
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 viralcode on GitHub. Read the source before you install it.

Installation

Install the Human Optimized Frontend 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.
  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/viralcode/openwhale.git /tmp/openwhale
mkdir -p .claude/skills
cp -r /tmp/openwhale/skills/human-optimized-frontend .claude/skills/human-optimized-frontend
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Human Optimized Frontend 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 Human Optimized Frontend 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 Human Optimized Frontend 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.

Activation Criteria

Activate this skill only when the user explicitly instructs the agent to redesign a frontend and references this skill by name.

Do not activate for:

  • Conceptual discussion or critique only
  • Coding or implementation tasks
  • Inspiration, references, or visual examples
  • Partial or component-level design requests

Execution Steps

1. Context Intake

  • Consume all provided information about the interface.
  • If context is missing, assume a neutral functional product with general-purpose usage.
  • Do not assume branding, audience psychology, or business goals unless explicitly stated.

2. Direction Lock (Aesthetic + UX)

  • Select exactly one aesthetic direction.
  • Select exactly one UX interaction philosophy (e.g. clarity-first, flow-driven, exploration-led).
  • All visual, motion, and interaction decisions must reinforce both.
  • Do not mix stylistic or interaction paradigms.

3. Initial Design Generation

Typography
  • Body text baseline: 15–18px equivalent
  • Heading scale:
    • H1 = body × 2.2–2.6
    • H2 = body × 1.6–1.9
    • H3 = body × 1.3–1.5
  • Line height:
    • Body: 1.45–1.6
    • Headings: 1.15–1.3
  • Font rule:
    • Serif + sans-serif pairing OR single family with ≥ 4 weights
  • Letter spacing:
    • Headings: -1% to -3%
    • Body: 0% to +1%
  • Prohibited fonts: system defaults, Inter, Roboto, Arial.
Color & Theme
  • Palette:
    • 1 dominant
    • 1 secondary
    • 1 accent
    • 1 neutral base
  • Contrast:
    • Text ≥ 4.5:1
    • Interactive elements ≥ 3:1
  • Accent usage ≤ 10% of visible area
  • Only one saturated color allowed
  • Gradients allowed only as background fields
Layout & Composition
  • Single spacing base unit (8px or 10px)
  • Visual weight distribution:
    • Primary: 40–55%
    • Secondary: 25–35%
    • Tertiary: ≤ 20%
  • Maximum two alignment axes per view
  • Symmetry allowed only with counterbalancing contrast
Background & Depth
  • Background type:
    • Textured neutral OR
    • Low-contrast geometry OR
    • Layered planes
  • Max depth layers: 3
  • Foreground contrast must exceed background by ≥ 20%
Motion Graphics (Mandatory)
  • Required motion categories:
    • Entry motion
    • Hierarchy reinforcement
    • Interaction feedback
  • Timing: 180–420ms
  • Easing:
    • Primary: ease-out
    • Secondary: subtle cubic or linear
  • Max simultaneous moving elements per viewport: 3
  • Motion must encode hierarchy, state, or spatial relation
  • Prohibited: decorative loops, idle animations, novelty motion
UX Structure (Mandatory)
  • Define a primary user goal per view.
  • All visual and motion emphasis must support this goal.
  • Interaction rules:
    • One primary action per screen
    • Secondary actions visually subordinate
  • Navigation clarity:
    • Entry point must be obvious within 1 second
    • Next available action must be discoverable without exploration
  • Cognitive load:
    • No more than 3 competing focal points per view
  • Feedback:
    • All user actions must produce immediate visual or motion feedback
  • Error tolerance:
    • Interfaces must be forgiving; destructive actions must be visually distinguished

4. Quantitative Evaluation Loop

Score each dimension from 0–10:

Typography

  • ≥ 8: hierarchy instantly readable
  • ≤ 6: scale or spacing feels inconsistent

Color

  • ≥ 8: dominance and emphasis are unambiguous
  • ≤ 6: accents compete or contrast is weak

Layout

  • ≥ 8: eye flow resolves within 1–2 seconds
  • ≤ 6: multiple regions compete equally

Background

  • ≥ 7: depth supports hierarchy
  • ≤ 5: background distracts or feels empty

Motion

  • ≥ 8: motion improves comprehension and flow
  • ≤ 6: motion distracts or delays intent

UX

  • ≥ 8: user intent is obvious, actions feel effortless
  • ≤ 6: hesitation, ambiguity, or friction introduced

Cross-Dimensional Harmony

  • ≥ 8: visuals, motion, and UX reinforce the same hierarchy and intent
  • ≤ 6: any dimension contradicts another

Weighted Total Score

  • Typography: 20%
  • Color: 20%
  • Layout: 20%
  • Motion: 15%
  • UX: 15%
  • Background: 10%
  • Harmony: mandatory ≥ 8

5. Iteration Rules

  • Adjust lowest-scoring dimension first.
  • UX adjustments take priority if UX score < 8.
  • Never adjust more than two dimensions per iteration.
  • Maximum iterations: 5.
  • If harmony score drops, revert the last change.

6. Final Output

Produce a single declarative frontend specification including:

  • Typography system
  • Color palette with roles
  • Layout structure and visual weights
  • Background and depth treatment
  • Motion graphics definitions
  • UX flow and interaction rules

No alternatives. No explanations. No theory.

Ambiguity Handling

  • Missing context defaults to neutral functional usage.
  • Defaults must still satisfy aesthetic, motion, and UX thresholds.
  • Never infer branding, emotional tone, or audience psychology.

Constraints & Non-Goals

  • Do not generate code, assets, or mockups.
  • Do not critique existing designs unless redesign context requires it.
  • Do not reference trends, competitors, or popular products.
  • Do not provide multiple options.
  • Do not justify decisions.

Failure Behavior

If activation conditions are not met, output a minimal statement indicating the skill cannot be activated.

If after maximum iterations UX or harmony thresholds are not met, output a minimal statement indicating that a satisfactory frontend cannot be generated under the given constraints and terminate.

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 Human Optimized Frontend AI skill do?

Generates a frontend interface that is visually pleasing and experientially sound by jointly optimizing aesthetics, motion graphics, and user experience (UX) using quantified evaluation. Use only when the user explicitly invokes this skill by name to redesign a frontend. Trigger keywords: use human-optimized-frontend, redesign frontend, redesign interface.

Why use Human Optimized Frontend on TypingMind?

Because you install it once and use it with any model. Human Optimized Frontend 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 Human Optimized Frontend in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/viralcode/openwhale/tree/main/skills/human-optimized-frontend. 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 Human Optimized Frontend?

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 Human Optimized Frontend?

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

Is the Human Optimized Frontend AI skill free?

It is published on GitHub by viralcode. 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 👇