JasonColapietro/suede-creator-skills / skills/suede-design
suede-design
VerifiedUse when asked "review this UI diff" or "audit this flow"; to design interface hierarchy, tokens, color, type, accessibility or a design system; run a whole-flow review; restyle a dashboard; or verify a visual build. NOT FOR: component state workbenches or live variants (use suede-component-lab), source-backed effect explanations (use suede-interface-explain), sales copy (use suede-copy), funnel architecture (use suede-site-alchemy), or general code/security review (use suede-code).
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 5.3 KB |
| LICENSE.jakubkrehel-skills-MIT.txt | markdown | 1.0 KB |
| SKILL.md | skill md | 20.8 KB |
| agents/openai.yaml | config | 580 B |
| references/build-delivery.md | markdown | 4.1 KB |
| references/design-laws.md | markdown | 3.8 KB |
| references/interface-accessibility.md | markdown | 3.4 KB |
| references/interface-behavior.md | markdown | 3.4 KB |
| references/interface-color.md | markdown | 2.8 KB |
| references/interface-layout.md | markdown | 3.3 KB |
| references/interface-review.md | markdown | 8.4 KB |
| references/interface-typography.md | markdown | 3.1 KB |
| references/interface-writing.md | markdown | 3.4 KB |
| references/restyle-playbook.md | markdown | 6.0 KB |
| references/scoped-bans.md | markdown | 5.7 KB |
| references/surface-lenses.md | markdown | 3.0 KB |
| references/ui-component-sources.md | markdown | 5.1 KB |
| references/usage-contract.md | markdown | 2.6 KB |
references/surface-lenses.md
View on GitHub# Surface Lenses
Named lenses for shaping or critiquing a surface in suede-design. These are lenses (notes, not shell commands) to name and apply while shaping a surface. Use them where useful; do not run all of them by default.
During review, these produce observations and proposals only. Implement changes
only within the named authorized scope. Preserve approved sales copy, factual
claims, assets and brand conventions; a lens is not a conversion case or consent
to rewrite them. Record task evidence before suggesting aesthetic changes.
Lenses about analytics, follow-up or publication do not authorize external
actions, tracking or new network dependencies.
- `/vibe-scan`: name the current feeling, desired feeling, and the mismatch that blocks trust, desire, clarity, or action.
- `/first-frame`: judge only the first viewport for brand, offer, proof, and primary action.
- `/desire-line`: trace the path from first glance to click and remove sections that do not increase want, trust, urgency, or clarity.
- `/hero-voltage`: sharpen the hero around a concrete noun, buyer-visible outcome, proof hint, and one primary CTA.
- `/offer-spine`: reduce the page to one buyer, one pain, one transformation, one proof stack, and one action.
- `/cta-magnet`: turn vague buttons into specific actions with clear next-step value.
- `/objection-burn`: answer the smart buyer's hesitation with proof, scope, terms, and risk reversal.
- `/palette-pressure`: improve contrast, hierarchy, semantic roles, and palette richness without one-hue design.
- `/type-chemistry`: tune display, body, mono, button, and caption type so the page feels deliberate and readable.
- `/section-rhythm`: balance density and breathing room so proof, product, story, and action do not collapse into a wall of cards.
- `/trust-lacquer`: turn trust marks, stats, logos, testimonials, security, and proof claims into a real argument without fake proof.
- `/proof-stack`: build a layered proof argument from artifacts, links, screenshots, commands, examples, quotes, docs, and visible product evidence.
- `/console-moment`: add one inspectable product-style moment (status rail, audit result, campaign ledger, asset passport, workflow card).
- `/aeo-shine`: tune titles, metadata, schema, headings, answer blocks, FAQ, plain-language summaries, and crawler-readable structure.
- `/visitor-intent`: surface what the visitor is trying to do and route them to the right proof, action, docs, demo, or contact path.
- `/proof-to-pipeline`: connect proof, content, landing pages, visitor signals, follow-up, and next actions.
- `/mobile-seduction`: make mobile feel intentionally composed instead of merely stacked.
- `/motion-restraint`: use motion only when it clarifies state, sequence, or premium feel, and respect reduced motion.
- `/link-sweep`: click or inspect every CTA and navigation path, then remove or replace dead or misleading routes.
- `/ship-polish`: run formatting, checks, browser QA, screenshots or render notes, link checks, and live verification before handoff.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |