stitch-ui-design-variants

stitch-ui-design-variants is a skill for Claude Code from gabelul/stitch-kit. It costs 37 tokens per session (1,158 once invoked), scanned A, original, Apache-2.0.

A guide for generating three alternative Stitch prompts for the same app screen, while keeping its basic information structure consistent. The alternatives can change layout, visual style, or content.

In plain words
What is it for?
It is for creating subtle, exploratory, or radically different screen concepts and presenting options to stakeholders.
Why use it?
It helps explore several design directions before choosing one and supports comparisons such as A/B testing.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the stitch-kit plugin — 36 skills, 1 agent, 2 hooks shipped together

Good fit It is for creating subtle, exploratory, or radically different screen concepts and presenting options to stakeholders.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gabelul/stitch-kit/stitch-ui-design-variants
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add gabelul/stitch-kit --skill stitch-ui-design-variants
Clone the repo
git clone --depth 1 https://github.com/gabelul/stitch-kit

Made for: Claude Code.

Or install stitch-kit, the plugin that ships this one along with the rest of its 36 skills, 1 agent, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for stitch-ui-design-variants

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-ui-design-variants/github.svg)](https://agentmods.dev/skills/gabelul/stitch-kit/stitch-ui-design-variants)
Your own site
<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-ui-design-variants"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-ui-design-variants/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for stitch-ui-design-variants

Your own site · 80×15
<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-ui-design-variants"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-ui-design-variants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,158 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.01158
Opus 5 $0.00018 $0.00579
Sonnet 5 $0.00007 $0.00232
Haiku 4.5 $0.00004 $0.00116

Measured 9d ago against content hash 971fea80ee03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

stitch-ui-design-variants scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/stitch-ui-design-variants/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stitch UI Design Variants

You are a Variant Generator. Given a base design spec or prompt, you produce 3 distinct alternative prompts for exploring different design directions before committing to one.

When to use this skill

  • User asks for "variations", "alternatives", "A/B options", "different styles", or "other versions"
  • Before a major design decision where the right direction is unclear
  • When the user wants to present multiple options to stakeholders

Detection: Native API vs text-prompt fallback

Before generating variants, check which path is available:

Native path — if generate_variants MCP tool is available AND you have a screenId:

  1. Use stitch-mcp-generate-variants (1 API call, more control)
  2. Map user language to creativeRange:
    • "subtle", "minor tweaks", "polish" → REFINE
    • "alternatives", "different options", "explore" → EXPLORE
    • "radical", "completely different", "reimagine" → REIMAGINE
  3. Map focus to aspects:
    • "layouts", "arrangement" → [LAYOUT]
    • "colors", "palette" → [COLOR_SCHEME]
    • "images", "photos" → [IMAGES]
    • "fonts", "typography" → [TEXT_FONT]
    • "copy", "text content" → [TEXT_CONTENT]

Text-prompt fallback — if no MCP tools OR no existing screen:

  1. Fall back to the text-prompt approach below (generate 3 prompt variants)
  2. Each variant still needs to be generated separately via generate_screen_from_text

The native path is preferred when available — it's 1 API call instead of 3, and produces more controlled variations.

Input

  • Base spec — a Design Spec JSON from stitch-ui-design-spec-generator, or an existing Stitch prompt
  • Variant type — LAYOUT, STYLE, or CONTENT (infer from user request if not stated)

Variant types

LAYOUT variants

Keep visual style constant. Vary the structural arrangement.

Variant Layout change
A — Standard Conventional layout for the device type (e.g., top nav + content)
B — Alternative Inverted or non-standard (e.g., sidebar primary nav, split-screen)
C — Minimal Stripped-back, single-column, maximum focus

Read the full file on GitHub · 128 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 128 lines · 37 tokens per session scan A 971fea80ee03

Subscribe to this mod's changes

stitch-ui-design-variants is a skill published in the GitHub repository gabelul/stitch-kit (44 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,158 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

design-to-code

Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…

yonatangross/orchestkit · 86 tokens

kit-montar

Monta um site novo combinando peças já validadas do acervo pessoal do usuário — templates, design systems, componentes, animações, menus, prompts e receitas — em vez de gerar tudo do zero. Acervo vazio: constrói do zero e oferece guardar. Recebe o briefing, decide cor e tipografia antes da identidade, pergunta que…

harebeats/cannonball · 245 tokens

kit-buscar

Consulta o acervo pessoal de sites do usuário — o que ele já guardou: templates rodáveis, design systems com paleta e tipografia, componentes de UI e de IA, animações de scroll, texto e menu, efeitos WebGL, prompts de página inteira e receitas de composição que já deram certo. Responde "o que eu já tenho pronto pra…

harebeats/cannonball · 228 tokens

kit-cor

Define a paleta do site como decisão, não como consequência de ter escolhido um design system. Faz as perguntas que determinam cor (o que a marca promete, o que o setor já usa, para onde o olho tem que ir, o que ela NÃO pode parecer), monta a paleta por papel — fundo, tinta, superfície, acento — mede o contraste de…

harebeats/cannonball · 193 tokens

kit-tipo

Define a tipografia do site como decisão — e, principalmente, resolve se dá para ENTREGAR. Confere licença (site de marca paga por tipo, e acervo montado a partir de site de marca vem cheio de fonte comercial que não se pode servir), propõe substituto livre com critério de desenho, monta o par display + corpo, gera a…

harebeats/cannonball · 199 tokens

stitch-react-native

Convert Stitch HTML designs into React Native screens, or sync existing native components to updated Stitch designs, using native primitives, StyleSheet rules, and mobile platform checks.

PracticalSwan/agent-skills · 37 tokens