Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Wireframe-first pass — outputs an ASCII layout + state list + content inventory + question list before any code. Use when starting a new screen from scratch or when the user's brief is still ambiguous. Invoke when the user asks for shape on their UI, or mentions 'shape' alongside design / UI / frontend work.
.claude/skills/educlopez-shape/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -15% | 0% |
<!-- HARNESS MIRROR — do not edit here. Canonical source: skills/ or commands/. After editing source, copy into cli/assets/<harness>/ and repo-root harness mirrors. -->
Context: this sub-skill is one lens of the broader ui-craft skill. If the ui-craft skill is also installed, read its SKILL.md first for Discovery + Anti-Slop + Craft Test, then apply the specific lens below.
Shape the UI for $ARGUMENTS before writing code. Load the ui-craft skill.
This command produces a shape artifact, not JSX. The point is to force low-fi thinking — content inventory, layout regions, state coverage, open questions — before any component is written. Skipping this step is how generic AI UIs get built: straight to hi-fi, no discovery, every screen looks the same.
Step 1 — Clarify (3-5 questions). Ask the user before shaping. Don't guess. Minimum questions:
Step 2 — Content inventory. Bullet list of every piece of content that will appear. Annotate each by priority:
Example:
- P0 Headline (one line, the value prop)
- P0 Primary CTA
- P0 Hero chart / metric
- P1 Secondary nav tabs
- P1 Recent activity list
- P2 Export / integrations menuStep 3 — ASCII layout. Low-fi sketch showing regions. No specific copy, no colors, no font sizes. One desktop variant + one mobile variant. Use box characters:
Desktop
┌──────────────────────────────────────────────┐
│ [logo] [nav] [user] │
├──────────────────────────────────────────────┤
│ ┌────────────────┐ ┌───────────────────┐ │
│ │ Headline + sub │ │ │ │
│ │ │ │ Hero visual │ │
│ │ [Primary CTA] │ │ │ │
│ └────────────────┘ └───────────────────┘ │
│ │
│ ── Social proof row ── │
│ │
│ ┌─── Feature 1 ───┐ ┌─── Feature 2 ───┐ │
│ └─────────────────┘ └─────────────────┘ │
└──────────────────────────────────────────────┘
Mobile
┌──────────────────┐
│ [logo] [☰] │
├──────────────────┤
│ Headline + sub │
│ │
│ [Primary CTA] │
│ │
│ ┌── Hero ──┐ │
│ └──────────┘ │
│ │
│ Social proof │
│ │
│ Feature 1 │
│ Feature 2 │
└──────────────────┘Asymmetry is fine and often better — don't force center-everything.
Step 4 — State list. Enumerate the states this screen must handle. Point at references/state-design.md for the contracts.
Mark each as required / optional (why) / N/A.
Step 5 — Open questions. Do NOT start coding until these are answered. Default set:
SKILL.md.)typography.md.)stack.md if the user opts in.)accessibility.md?Knob awareness.
CRAFT_LEVEL ≥ 7, add two more sections:references/motion.md.CRAFT_LEVEL ≤ 4, strip Step 4 to idle / loading / error only. Skip the motion shape.Step 6 — Offer to persist to .ui-craft/spec.md (opt-in).
After printing all five steps, offer to write the output as a spec section:
> "Write this shape to .ui-craft/spec.md as ## Surface: <name>? (Persists the composition choice, layout, and acceptance bar for the build phase.)"
## Surface: <name> section following the template in ../skills/ui-craft/references/spec.md, then write or append to .ui-craft/spec.md. Confirm in one line: "Written to .ui-craft/spec.md → ## Surface: <name>."Print-only is the default when /shape is run standalone. Step 6 is the offer; it does not execute unless the user explicitly confirms.
Output contract.
/ui-craft:audit (or use Build mode) once the code exists."_Next step: /craft — build the surface you just wireframed (rung 1).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 23,411 | 20,872 | -11% | 1 | 1 | 0% | 3,601 | 5,504 | +53% | 0 | 0 | — |
case-02 | fail→pass | 24,655 | 17,999 | -27% | 1 | 1 | 0% | 4,635 | 4,756 | +3% | 0 | 0 | — |
case-03 | fail→pass | 42,635 | 20,668 | -52% | 1 | 1 | 0% | 5,716 | 4,931 | -14% | 0 | 0 | — |
case-04 | fail→pass | 35,716 | 22,283 | -38% | 1 | 1 | 0% | 6,193 | 5,299 | -14% | 0 | 0 | — |
case-05 | fail→pass | 26,807 | 13,069 | -51% | 1 | 1 | 0% | 4,732 | 4,043 | -15% | 0 | 0 | — |
case-06 | fail→pass | 18,963 | 17,369 | -8% | 1 | 1 | 0% | 3,333 | 4,575 | +37% | 0 | 0 | — |
case-07 | fail→pass | 29,221 | 12,996 | -56% | 1 | 1 | 0% | 4,954 | 3,755 | -24% | 0 | 0 | — |
case-08 | fail→pass | 34,159 | 20,738 | -39% | 1 | 1 | 0% | 6,178 | 5,059 | -18% | 0 | 0 | — |
case-09 | pass→pass | 21,055 | 17,040 | -19% | 1 | 1 | 0% | 3,650 | 4,711 | +29% | 0 | 0 | — |
case-10 | fail→pass | 19,512 | 12,153 | -38% | 1 | 1 | 0% | 3,345 | 3,748 | +12% | 0 | 0 | — |
case-11 | fail→fail | 24,365 | 17,338 | -29% | 1 | 1 | 0% | 4,436 | 4,649 | +5% | 0 | 0 | — |
case-12 | pass→pass | 21,058 | 15,752 | -25% | 1 | 1 | 0% | 3,715 | 4,295 | +16% | 0 | 0 | — |
case-13 | pass→pass | 31,436 | 23,478 | -25% | 1 | 1 | 0% | 5,395 | 5,933 | +10% | 0 | 0 | — |
case-14 | fail→pass | 25,875 | 19,829 | -23% | 1 | 1 | 0% | 4,195 | 4,942 | +18% | 0 | 0 | — |
case-15 | pass→pass | 31,191 | 19,141 | -39% | 1 | 1 | 0% | 5,060 | 4,839 | -4% | 0 | 0 | — |
case-16 | pass→pass | 28,109 | 19,580 | -30% | 1 | 1 | 0% | 4,459 | 4,625 | +4% | 0 | 0 | — |
case-17 | fail→pass | 39,779 | 27,507 | -31% | 1 | 1 | 0% | 6,179 | 6,584 | +7% | 0 | 0 | — |
case-18 | fail→pass | 28,981 | 20,756 | -28% | 1 | 1 | 0% | 4,644 | 4,973 | +7% | 0 | 0 | — |
case-19 | pass→fail | 21,737 | 19,187 | -12% | 1 | 1 | 0% | 4,624 | 4,708 | +2% | 0 | 0 | — |
case-20 | pass→fail | 5,044 | 21,814 | +332% | 1 | 1 | 0% | 892 | 5,552 | +522% | 0 | 0 | — |
case-21 | pass→fail | 13,401 | 16,907 | +26% | 1 | 1 | 0% | 2,725 | 4,369 | +60% | 0 | 0 | — |
case-22 | pass→fail | 19,040 | 20,926 | +10% | 1 | 1 | 0% | 4,619 | 5,491 | +19% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +36 percentage points is the difference between those two pass rates over the 22 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.