skills/web-design/carousel-brand-system/SKILL.md
Build a complete brand design system tuned for social media carousel production. Interactive workflow: propose color palettes with reasoning, explore font pairings, generate an HTML picker for the user to click what resonates, analyze picks, lock the system in Figma, and produce carousel-format combo cards. Triggers: "build a carousel design system", "create brand colors for carousels", "design system for social media", "carousel brand system", "explore colors for our brand", "pick fonts for carousels", "lock our design system", "brand system for content production", "social media design system", or any request to build a visual identity system specifically for carousel / social media content production. Does NOT trigger for: building individual carousels (use carousel-designer), general brand guidelines docs (use brand-guidelines-builder), or website design systems (use laniameda-brand-design).
npx skillsauth add michailbul/laniameda-skills carousel-brand-systemInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Build a locked, production-ready brand design system for social media carousels. The output is a color + typography + gradient + combo system that feeds directly into carousel production (Canva, Figma, or HTML).
This skill runs as an interactive conversation, not a one-shot generation. The user explores, picks, and you lock.
| Skill | Use when | |-------|----------| | carousel-brand-system (this) | Building the visual system that powers all carousels | | carousel-designer | Producing an individual carousel using an existing system | | brand-guidelines-builder | Creating a general brand identity doc from scratch | | laniameda-brand-design | Building website/landing page designs in Pencil | | typography-master | Deep-diving into font exploration independently |
Before proposing anything, understand what exists.
Read first:
studio/brand-guidelines.md)use_figma to inspect)brand/Extract:
Output: Brief internal summary. Don't dump this on the user — just confirm: "I see your base palette is X, fonts are Y, and the mood is Z. Ready to explore accent directions?"
Generate 3-4 distinct accent palette directions. Each direction should:
Format as an HTML page (not just text). The page should:
Key principles for color proposals:
Write the HTML to brand/color-exploration.html and open it in the browser.
Wait for user reaction before proceeding.
If fonts aren't already locked, explore pairings. Two approaches:
A) Figma specimens — Create font pairing cards in Figma showing headline + body samples at carousel scale (1080x1350). Each card uses a different pairing with the same sample text.
B) HTML specimens — Generate an HTML page with all candidate pairings rendered at real sizes, using Google Fonts imports.
Pairing rules:
Wait for user feedback. Some pairings will get cut.
Generate an HTML picker page that lets the user click to select what they like. This is the core of the workflow.
The picker must include:
Picker UX requirements:
=== BRAND PICKS ===
## Base (locked)
[list locked colors]
## Accent Colors I Like
- [Name] [Hex]
## Font Pairings I Like
- [Headline font] + [Body font]
## Combo Cards I Like
- [Description of combo]
## Gradients I Like
- [Color A] → [Color B]
Write the picker to brand/color-picker.html and open it.
Tell the user: "Click everything you like, hit Export Picks, paste the summary back to me."
When the user pastes their picks:
Present the analysis as a clear summary table:
Ask two questions max before locking:
Build the design system page in Figma using use_figma MCP tool.
Page structure (vertical auto-layout, no background fill):
Header — Brand name + "Design System v[X].0"
01 COLOR SYSTEM
Primary Palette — base color swatches (locked)
Primary Accents — tier 1 accent swatches
Supporting Accents — tier 2 swatches
Situational Accents — tier 3 swatches
Color Usage Rules — panel with pairing rules
02 TYPOGRAPHY
Font Showcase — carousel-format cards (1080x1350) using locked pairings
Layout: top group (label + accent bar + headline) → flex spacer → bottom group (body + meta)
Each card: different color combo + font pairing
Organized in rows of 3
Type Scale — if needed
02B THEMES
Dark/Light side-by-side preview cards
01B COLOR PAIRINGS
Primary Reading Pairs
Accent on Dark Surfaces
Statement Backgrounds
03 GRADIENTS
Rows of gradient strips with labels
04 USAGE GUIDELINES
DO / DON'T columns
Carousel Pairing Cheatsheet — specific recipes (bg + headline font + headline color + body font)
Footer
Carousel combo card template (for Figma):
Frame: 1080x1350, cornerRadius 16, vertical auto-layout
paddingTop: 64, paddingBottom: 56, paddingLeft: 64, paddingRight: 64
Top group (auto, vertical, gap 16):
Label — 13px Inter Regular, uppercase, letter-spacing 10%, opacity 0.4
Accent bar — 48x4, cornerRadius 2
Headline — [headline font], [headline size], letterSpacing -2%
Flex spacer — layoutSizingVertical: FILL
Bottom group (auto, vertical, gap 16):
Body text — [body font], 24px, lineHeight 38px, opacity 0.75
Meta label — 11px Inter Regular, uppercase, letter-spacing 8%, opacity 0.25
After building: Take screenshots to verify. Fix any layout issues (collapsed auto-layout, wrong fills, missing text).
Start from the brand's emotional core, not from color theory abstractions.
Temperature mapping:
Tier architecture:
Common accent roles: | Role | Example | Usage | |------|---------|-------| | Warm signal | Amber, Gold | Headlines on dark, highlight moments | | Emotional dark | Plum, Deep Indigo | Background for moody slides | | Cool ground | Slate Blue, Steel | Professional/editorial frames | | Hot signal | Vermillion, Hot Pink | CTAs, stop-and-look moments | | Neutral depth | Graphite, Charcoal | Layering, subtle backgrounds | | Quiet organic | Muted Teal, Sage | Dividers, secondary accents | | Glow text | Electric Cream, Warm White | Text on dark moody backgrounds |
Always give colors evocative names, not technical descriptions:
Names should feel like they belong in the brand's world.
All generated HTML pages should:
#0e0c0a or similar)Always await figma.loadFontAsync({ family, style }) before creating text nodes. Common gotchas:
figma.setCurrentPageAsync(page) not figma.currentPage = pagelayoutSizingHorizontal = 'FILL' AFTER parent.appendChild(child)primaryAxisSizingMode = 'FIXED' for cards with fixed heightlayoutSizingVertical = 'FILL' for flex spacerscounterAxisSizingMode only accepts 'FIXED' or 'AUTO' (not 'FILL')fills = [{
type: 'GRADIENT_LINEAR',
gradientTransform: [[1, 0, 0], [0, 1, 0]], // left to right
// or [[0, 1, 0], [-1, 0, 1]] for top to bottom
gradientStops: [
{ position: 0, color: { r, g, b, a: 1 } },
{ position: 1, color: { r, g, b, a: 1 } }
]
}]
Figma uses 0-1 range, not 0-255. Convert: r/255, g/255, b/255.
At the end of this workflow, the user should have:
brand/color-exploration.html — Color direction proposalsbrand/color-picker.html — Interactive picker with all optionsbrand-guidelines.md or CLAUDE.md — Reflecting the locked systemUser: "Let's build a design system for our social media carousels"
→ Phase 1: Read existing brand docs, Figma, CLAUDE.md
→ "I see your base is Coral + Carbon + Teal + Linen with 7 font pairings.
The screaming accents feel off-brand. Ready to explore new directions?"
User: "Yes, let's explore"
→ Phase 2: Generate color-exploration.html with 3-4 directions
→ Open in browser
→ "What direction pulls you?"
User: "I like B and C"
→ Phase 3: Generate more B+C hybrids with font pairings in combo cards
→ "Want to try the picker?"
User: "Yes"
→ Phase 4: Generate color-picker.html
→ "Click everything you like, export, paste back"
User: [pastes picks]
→ Phase 5: Analyze picks, identify tiers, propose final system
→ "Here's what emerged. Ready to lock?"
User: "Lock it"
→ Phase 6: Build in Figma, verify with screenshots
→ "Done. Design System v2.0 is locked."
development
Seedance 2.0 video prompt director. Converts plain-text scene descriptions into production-ready bilingual EN+ZH video prompts optimized for the Seedance 2.0 video generator. Handles all Seedance work — action (combat, pursuit, stunts), general (landscapes, journeys, atmosphere), dialogue (confrontations, negotiations, interrogations), and non-narrative commercial work (ad spots, music videos, fashion films, automotive inserts, product shots, pet/character demos, cutaway montages, social reels for TikTok / Reels / YouTube Shorts). Use whenever the user wants to create a Seedance video prompt, mentions Seedance, or describes a cinematic scene for video generation. For NARRATIVE screenplay-integrated work, use seedance-screenwriter instead.
development
Write Seedance 2.0 prompts in screenplay format for narrative storytelling — when the prompts will be cut into a film, short, or scene. Use whenever you're generating shots that will be edited into a continuous story with dialogue, character beats, scene continuity, or coverage. Pairs with the screenwriter skill — read the scene's screenplay first (or the project's `scene.md` if it exists), then translate each shot into a Seedance prompt that reads as a screenplay page, not as an engineering spec.
documentation
Скилл-инструмент для сценариста полнометражного фильма или сериала. Используй всегда, когда пользователь хочет писать сценарий, поэпизодник, разрабатывать сцены, бит-шит, диалоги, делать ревизии, считать экранное время, резать длину, работать с персонажами или мифологией истории. Скилл работает на основе методологий Макки, Кэмпбелла и Аристотеля, выдаёт Hollywood-формат .docx, поддерживает билингвальные сценарии (диалог на одном языке + перевод в скобках под ним), и помогает аудитировать структуру по причинности и движению ценности. Скилл не привязан к конкретной истории — пользователь приносит свою.
development
Extract shot composition DNA from any car photograph into structured JSON — camera angle, lens, framing, lighting — stripped of car-specific details. Then reuse extracted angles with any car identity to generate new images at scale. Use when: extracting angles from reference photos, building a shot library, batch-analyzing car photography, replicating a great angle with a different car, running extraction pipelines in Freepik or Flora. Triggers: "extract this angle", "steal this composition", "shot DNA", "analyze this car photo", "replicate this shot with my car", "batch extract angles", "car photography analysis", "angle extraction", "build a shot library".