Web Design Enhancer

Community

Steph-ux

web-design-enhancer

Use when building, redesigning, or validating web/UI with WDE V3 evidence orchestration; when AI agents must follow authorized next steps and cannot forge delivery. Not for pure backend or non-UI work.

Overview

Publisher	Steph-ux
Repository	`web-design-enhancer`
Skill name	`web-design-enhancer`
Stars	14
Forks	2
Bundled files	244
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.
244 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Steph-ux on GitHub. Read the source before you install it.

Installation

Install the Web Design Enhancer 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/Steph-ux/web-design-enhancer/tree/main
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/Steph-ux/web-design-enhancer.git \
  .claude/skills/web-design-enhancer

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

Use it in TypingMind

Enable Web Design Enhancer 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 Web Design Enhancer 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 Web Design Enhancer 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.

Web Design Enhancer V3

The model proposes and implements. The orchestrator authorizes, verifies, and blocks.

This file is the thin skill adapter. Do not invent gates — drive the CLI.

Bootstrap

Prefer the short CLI (wde after pip install -e ., else python -m wde):

bash
wde init --root <project>
# Vague request → Creative Discovery (receipts + 3 territories + contracts)
wde discover --root <project> --request "modern premium site for an agency"
wde status --json --root <project>
wde next --root <project>

Follow only next_action. Deeper refs:

Need	Path
Full adapter rules	`adapters/generic/ADAPTER.md`
V3 docs	`docs/V3.md`
Plan	`docs/superpowers/specs/2026-07-10-wde-v3-plan.md`
Brief / UX / design templates	`templates/`
Craft (V2 arsenal)	`references/`
Eyes / Playwright protocol	`references/vision-playwright.md` + `wde review`
Scripts (V2 checks)	`scripts/` via `wde run`

Core loop

bash
wde validate intent|research|experience|design|lock --root <project>
wde run static --root <project>
wde deliver-check --root <project>
wde review --emit-package --url <url> --root <project>
# judge → aesthetic-verdict.json (reviewer: independent|human — not self;
# independent-clone is declared-only unless WDE_ALLOW_DECLARED_INDEPENDENCE=1)
wde review --url <url> --root <project>
wde report --root <project>

Forbidden

Hand-edit .wde/state.json / write .wde/evidence/ as the model
Use wde transition (removed — always errors)
Claim READY without verified independent review evidence
Invent metrics, testimonials, trusted-by
Skip pillars (use fresh search.py --persist + npx getdesign, then wde validate research)

Benchmark / migrate

bash
wde benchmark --corpus
wde migrate-v2 --root <project>

V2 scripts remain under scripts/ — invoked only through trusted wde-core checks.

Bundled files

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

adapters/claude-code/ADAPTER.md1 KB
adapters/codex/ADAPTER.md1 KB
adapters/generic/ADAPTER.md2 KB
assets/cryptoverse-architecture.png240 KB
assets/cryptoverse-closing.png205 KB
assets/cryptoverse-developers.png271 KB
assets/cryptoverse-hero.png205 KB
assets/cryptoverse-platform.png285 KB
assets/football-hero.png50 KB
assets/football-match.png40 KB
assets/football-players.png44 KB
assets/noire-collection.png529 KB
assets/noire-hero.png173 KB
assets/noire-ritual.png186 KB
benchmark/tasks/catalog.json3 KB
CHANGELOG.md12 KB
data/app-interface.csv10 KB
data/apple-hig-patterns.csv14 KB
data/charts.csv19 KB
data/colors.csv32 KB
data/design.csv104 KB
data/draft.csv104 KB
data/getdesign-references.csv5 KB
data/google-fonts.csv726 KB
data/icons.csv20 KB
data/landing.csv16 KB
data/material-design-3-patterns.csv26 KB
data/page-flows-patterns.csv19 KB
data/products.csv57 KB
data/pttrns-patterns.csv5 KB
data/react-performance.csv14 KB
data/stacks/angular.csv18 KB
data/stacks/astro.csv12 KB
data/stacks/flutter.csv10 KB
data/stacks/html-tailwind.csv11 KB
data/stacks/jetpack-compose.csv8 KB
data/stacks/laravel.csv18 KB
data/stacks/nextjs.csv12 KB
data/stacks/nuxt-ui.csv14 KB
data/stacks/nuxtjs.csv16 KB
data/stacks/react-native.csv10 KB
data/stacks/react.csv13 KB
data/stacks/shadcn.csv16 KB
data/stacks/svelte.csv11 KB
data/stacks/swiftui.csv11 KB
data/stacks/threejs.csv44 KB
data/stacks/vue.csv11 KB
data/styles.csv139 KB
data/typography.csv49 KB
data/ui-reasoning.csv52 KB
data/ux-guidelines.csv18 KB
DESIGN.md36 KB
docs/index.html15 KB
docs/superpowers/plans/2026-07-10-wde-c-playwright-implementation.md35 KB
docs/superpowers/specs/2026-07-10-wde-c-playwright-design.md21 KB
docs/superpowers/specs/2026-07-10-wde-v3-plan.md43 KB
docs/V3.md8 KB
examples/dataflow-saas/DESIGN.md5 KB
examples/manus-demo/DESIGN.md5 KB
examples/v3-fixture/CREATIVE-BRIEF.md1 KB

and 140 more files.

Frequently asked questions

What does the Web Design Enhancer AI skill do?

Why use Web Design Enhancer on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Steph-ux/web-design-enhancer/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 Web Design Enhancer?

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 Web Design Enhancer?

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

Is the Web Design Enhancer AI skill free?

It is published on GitHub by Steph-ux. 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

Discrawl

openclaw

OrganizationPopular

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Gitcrawl

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Graincrawl

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Web Design Enhancer V3

Bootstrap

Core loop

Forbidden

Benchmark / migrate

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now