seikaikyo/tgd-sketch

Sketch

Overview

Generate 2-3 disposable HTML mockups to compare design directions before committing to implementation. Each variant is a self-contained HTML file with realistic content, inline CSS, and basic interactivity. The goal is visual comparison, not production code.

Use this skill when the user wants to see a design direction before committing to one — exploring a UI/UX idea as disposable HTML mockups. The point is to generate 2-3 interactive variants so the user can compare visual directions side-by-side, not to produce shippable code.

When to Use

• User wants to explore UI/UX directions before building
• User says "sketch this screen", "show me what X could look like", "compare layout A vs B"
• User wants 2-3 takes on a UI to compare visual directions
• User wants a quick mockup before committing to design
• Early-stage design exploration where speed matters more than polish

Trigger phrases: "sketch this screen", "show me what X could look like", "compare layout A vs B", "give me 2-3 takes on this UI", "let me see some variants", "mockup this before I build".

Common Rationalizations

• "I'll just build one version" — Without comparison, you're guessing at the best direction. Two variants take 2x effort but eliminate 80% of redesign risk.
• "I'll skip the README" — The README captures why each variant makes its choices. Without it, you're comparing pixels, not principles.
• "One variant is enough" — One variant is a prototype, not a comparison. The skill's value is in the head-to-head evaluation.

Red Flags

• Variants that differ only in color/accent — these aren't real alternatives, just recolors
• No interactivity — a static screenshot is worse than a wireframe you can click
• Skipping the intake questions — generating without understanding feel/references/core action produces generic output
• More than 3 variants — diminishing returns; the user can't compare meaningfully
• Production-quality code — sketches are disposable; don't over-invest

Verification

• Open each variant in a browser and verify it renders correctly
• Check that each variant has a different design stance (not just different colors)
• Verify basic interactivity works (clicks, hovers, state transitions)
• Confirm the comparison table is opinionated — state which variant is strongest and why
• Ensure READMEs explain the trade-offs, not just list features

When NOT to use this

• User wants a production component — use claude-design or build it properly
• User wants a polished one-off HTML artifact (landing page, deck) — claude-design
• User wants a diagram — excalidraw, architecture-diagram
• The design is already locked — just build it

Where variants live

• Inside the tGD lifecycle (called from /tgd-define's UI Design Gate): save variants to $TGD_DIR/<feature-name>/prototype/ — this is the directory the define/plan verification gates check. Name the three variants after the mandated stances: conservative/, strong-fit/, divergent/ (see tgd-spec-driven-development Phase 1.5).
• Ad-hoc sketching (user just wants mockups, no feature in flight): ask where to put them, defaulting to a scratch location. Never write into the code repo root — sketches are throwaway artifacts, not source.

If the user has the full GSD system installed

Outside the tGD lifecycle only: if gsd-sketch is installed (npx get-shit-done-cc), it offers persistent sketch state, MANIFEST, and consistency audits. Inside /tgd-define, always use THIS skill — the gates check $TGD_DIR/<feature-name>/prototype/, not GSD's .planning/sketches/.

Core method

intake  →  variants  →  head-to-head  →  pick winner (or iterate)

1. Intake (skip if the user already gave you enough)

Before generating variants, get three things — one question at a time, not all at once:

1. Feel. "What should this feel like? Adjectives, emotions, a vibe." — "calm, editorial, like Linear" tells you more than "minimal".
2. References. "What apps, sites, or products capture the feel you're imagining?" — actual references beat abstract descriptions.
3. Core action. "What's the single most important thing a user does on this screen?" — the variants should all serve this well; if they don't, they're just decoration.

Reflect each answer briefly before the next question. If the user already gave you all three upfront, skip straight to variants.

2. Variants (2-3, never 1, rarely 4+)

Produce 2-3 variants in one go. Each variant is a complete, standalone HTML file. Don't describe variants — build them. The point is comparison.

Each variant should take a different design stance, not different pixel values. Three good variant axes:

• Density: compact / airy / ultra-dense (pick two contrasting poles)
• Emphasis: content-first / action-first / tool-first
• Aesthetic: editorial / utilitarian / playful
• Layout: single-column / sidebar / split-pane
• Grounding: card-based / bare-content / document-style

Pick one axis and pull apart from it. Two variants that differ only in accent color are wasted effort — the user can't distinguish them.

Variant naming: in the tGD lifecycle, use the mandated stance names; ad-hoc, describe the stance, not the number.

$TGD_DIR/<feature-name>/prototype/
├── conservative/
│   ├── index.html
│   └── README.md
├── strong-fit/
│   ├── index.html
│   └── README.md
└── divergent/
    ├── index.html
    └── README.md

3. Make them real HTML

Each variant is a single self-contained HTML file:

• Inline <style> — no build step, no external CSS
• System fonts or one Google Font via <link>
• Tailwind via CDN (<script src="https://cdn.tailwindcss.com"></script>) is fine
• Realistic fake content — actual sentences, actual names, not "Lorem ipsum"
• Interactive: links clickable, hovers real, at least one state transition (open/close, filter, toggle). A frozen static image is a worse spike than a sloppy animated one.

Open it in a browser. If it looks broken, fix it before showing the user.

Verify variants visually — use the tgd-agent-browser skill (or your platform's browser tooling). Don't just write HTML and hope it renders; open each variant over file://, take a screenshot, and look at it. This catches layout bugs that pure source inspection misses (a font import that silently failed, a flex container that collapsed). Fix and re-check until each variant looks right.

Default CSS reset + system font stack for fast starts:

<style>
  * { box-sizing: border-box; margin: 0; padding: 0; }
  body {
    font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto,
                 "Helvetica Neue", Arial, sans-serif;
    -webkit-font-smoothing: antialiased;
    color: #1a1a1a;
    background: #fafafa;
    line-height: 1.5;
  }
</style>

4. Variant README

Each variant's README.md answers:

## Variant: {stance name}

### Design stance
One sentence on the principle driving this variant.

### Key choices
- Layout: ...
- Typography: ...
- Color: ...
- Interaction: ...

### Trade-offs
- Strong at: ...
- Weak at: ...

### Best for
- The kind of user or use case this variant actually serves

5. Head-to-head

After all variants are built, present them as a comparison. Don't just list — opinionate:

## Three takes on the home screen

| Dimension | Calm editorial | Utilitarian dense | Playful split |
|-----------|----------------|-------------------|---------------|
| Density   | Low            | High              | Medium        |
| Primary action visibility | Low | High | Medium |
| Scan-ability | High | Medium | Low |
| Feel | Calm, trusted | Sharp, tool-like | Inviting, energetic |

**My take:** Utilitarian dense for power users, calm editorial for content-forward audiences. Playful split is weakest — tries to do both and commits to neither.

Let the user pick a winner, or combine two into a hybrid, or ask for another round.

Theming (when the project has a visual identity)

If the user has an existing theme (colors, fonts, tokens), put shared tokens in prototype/themes/tokens.css and @import them in each variant. Keep tokens minimal:

/* prototype/themes/tokens.css */
:root {
  --color-bg: #fafafa;
  --color-fg: #1a1a1a;
  --color-accent: #0066ff;
  --color-muted: #666;
  --radius: 8px;
  --font-display: "Inter", sans-serif;
  --font-body: -apple-system, BlinkMacSystemFont, sans-serif;
}

Don't over-tokenize a throwaway sketch — three colors and one font is usually enough.

Interactivity bar

A sketch is interactive enough when the user can:

1. Click a primary action and something visible happens (state change, modal, toast, navigation feint)
2. See one meaningful state transition (filter a list, toggle a mode, open/close a panel)
3. Hover recognizable affordances (buttons, rows, tabs)

More than that is over-engineering a throwaway. Less than that is a screenshot.

Frontier mode (picking what to sketch next)

If sketches already exist and the user says "what should I sketch next?":

• Consistency gaps — two winning variants from different sketches made independent choices that haven't been composed together yet
• Unsketched screens — referenced but never explored
• State coverage — happy path sketched, but not empty / loading / error / 1000-items
• Responsive gaps — validated at one viewport; does it hold at mobile / ultrawide?
• Interaction patterns — static layouts exist; transitions, drag, scroll behavior don't

Propose 2-4 named candidates. Let the user pick.

Output

• In the tGD lifecycle: variants under $TGD_DIR/<feature-name>/prototype/ (see "Where variants live" above). Ad-hoc: the location the user chose — never the code repo root.
• One subdir per variant: <stance>/index.html + README.md
• Tell the user how to open them: open .../prototype/conservative/index.html on macOS, xdg-open on Linux, start on Windows
• Keep variants disposable — a sketch that you felt the need to preserve should be promoted into real project code, not curated as an asset

Typical sequence for one variant: create the variant directory, write index.html and README.md, open the file in a browser via the tgd-agent-browser skill, screenshot, fix anything visibly broken. Repeat for each variant, then present the comparison table.

Attribution

Adapted from the GSD (Get Shit Done) project's /gsd-sketch workflow — MIT © 2025 Lex Christopherson (gsd-build/get-shit-done). The full GSD system ships persistent sketch state, theme/variant pattern references, and consistency-audit workflows; install with npx get-shit-done-cc --hermes --global.