world-class-carousel — Claude Code skill
world-class-carousel builds Instagram carousels for any topic with slides, AI visuals, captions, hashtags, and music suggestions. Useful when a post needs a complete publishable package.
MIT ★ 138 updated 2026-09-03
npx skills add happycapy-ai/Happycapy-skills --skill world-class-carousel -a claude-codeWhat world-class-carousel does
The skill produces 7–10 Instagram slides at 1080x1350. It creates AI-generated visuals, applies a typography system, suggests music, and prepares the caption and hashtags. The topic comes from the user; the skill supplies the content structure.
Its process uses an Aristotelian first-principles framework, 7 content archetypes, 6 hook patterns, a design system, and a required Bullshit Test gate. Before any carousel is generated, the skill requires reading KNOWN_ISSUES.md at /home/node/.claude/skills/world-class-carousel/KNOWN_ISSUES.md. That file contains the sizing, data-format, visual-strategy, and quality-control rules used by the workflow.
What it helps with
- create an Instagram carousel for a chosen topic
- produce 7–10 slides at 1080x1350
- generate visuals and set precise typography
- write the caption and hashtags
- select music for an Instagram post
Example prompts for the agent
- Create an Instagram carousel comparing AI tools, including finished slides, visuals, a caption, and hashtags.
- Make a carousel that teaches an AI tool step by step, then choose a suitable slide structure.
- Prepare Instagram slides about a controversial design opinion and run the outline through the Bullshit Test.
How to install world-class-carousel
1Skills CLI (Vercel)
npx skills add happycapy-ai/Happycapy-skills --skill world-class-carousel -a claude-code2Manually: put the files in place
~/.claude/skills/world-class-carousel/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/world-class-carousel/
1Skills CLI (Vercel)
npx skills add happycapy-ai/Happycapy-skills --skill world-class-carousel -a codex2Manually: put the files in place
.agents/skills/world-class-carousel/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add happycapy-ai/Happycapy-skills --skill world-class-carousel -a cursor2Manually: put the files in place
.cursor/skills/world-class-carousel/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install happycapy-ai/Happycapy-skills skills/world-class-carousel2Manually: put the files in place
.github/skills/world-class-carousel/SKILL.md1Skills CLI (Vercel)
npx skills add happycapy-ai/Happycapy-skills --skill world-class-carousel -a gemini-cli2Platform CLI
gemini skills install https://github.com/happycapy-ai/Happycapy-skills --path skills/world-class-carouselManually: put the files in place
.devin/skills/world-class-carousel/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about world-class-carousel
How do I install world-class-carousel in Claude Code?
Run npx skills add happycapy-ai/Happycapy-skills --skill world-class-carousel -a claude-code, then use ~/.claude/skills/world-class-carousel/SKILL.md.
What does world-class-carousel do?
It creates publishable Instagram carousels for any topic, with 7–10 slides, AI visuals, typography, music suggestions, captions, and hashtags.
Why does the skill require KNOWN_ISSUES.md?
The file must be read before generation. It holds the workflow rules for data format, sizing, visual decisions, and quality checks.
Source text
SKILL.md · MIT
---
name: world-class-carousel
description: "Generate world-class Instagram carousel content on any topic. Produces 7-10 publication-ready slides (1080x1350) with AI-generated visuals, precise typography, Instagram music recommendations, optimized captions, and hashtags. Uses Aristotelian first-principles framework with 7 content archetypes, 6 hook patterns, a mandatory Bullshit Test quality gate, and a comprehensive design system. Fully generalized -- works for ANY topic. Triggers: instagram carousel, create carousel, carousel post, make carousel slides, instagram slides, carousel content, slide deck for instagram, swipeable post"
allowed-tools: Bash, Read, Edit, Write, Glob, Grep, WebFetch
---
# World-Class Instagram Carousel Generator
Generate Instagram carousels that are genuinely world-class: content people save, share, and come back to. Not engagement bait. Not AI slop. Actual value, delivered through precise visual design and narrative structure.
This skill is **fully generalized**. It contains FORM (structure, principles, patterns), not MATTER (specific topics). The user provides the matter (topic); the skill provides the form (archetypes, design system, music matrix, quality gates). Together they produce the carousel. Nothing is hardcoded.
---
## BEFORE YOU START: Read `KNOWN_ISSUES.md`
Before generating ANY carousel, read `/home/node/.claude/skills/world-class-carousel/KNOWN_ISSUES.md`. It contains compressed rules from all previous sessions -- data format gotchas, sizing rules, visual strategy decisions, and quality gates. Ignoring it means repeating solved mistakes.
---
## EXECUTION PIPELINE
When the user requests a carousel, execute these 6 phases in order (Phase 6 runs post-delivery):
### PHASE 1: RESEARCH & STRUCTURING
1. **Analyze the topic** -- What is the core insight? What specific value can this deliver?
2. **Identify the audience** -- What does the target audience NOT already know? What's their current understanding?
3. **Auto-detect content vertical and theme** -- Use the Content Vertical Detection table below
4. **Select the archetype** -- Which of the 7 carousel archetypes (see below) fits best? Use the Archetype Selection Guide below. Auto-select unless the user specifies.
5. **Design the narrative arc** -- Map each archetype role to a renderer slide type using the Role-to-SlideType Mapping below. Ensure each slide creates a curiosity gap that the next slide resolves.
6. **Run the Bullshit Test on the outline** -- Does every slide pass? (See QUALITY GATE below)
#### Content Vertical Detection (Topic -> Theme)
Analyze the topic and auto-select the renderer theme:
| Content Vertical | Keywords/Signals | Renderer Theme | Background Style |
|-----------------|-----------------|----------------|-----------------|
| Tech / AI / Coding | AI, code, developer, API, tools, stack, programming, SaaS, data | `dark` | `gradient` (default) |
| Business / Strategy | growth, revenue, startup, founder, marketing, sales, strategy, scale | `earth` | `gradient` |
| Education / How-To | learn, tutorial, guide, roadmap, beginner, master, course, how to | `clean` | `gradient` |
| Creative / Design | design, UX, brand, visual, aesthetic, portfolio, creative | `dark` | `gradient_mesh` |
| Mindset / Philosophy | mindset, habits, productivity, stoic, growth, mental, philosophy | `warm` | `gradient` |
If the user specifies a brand config with a theme, always use that instead.
#### Content Category Selection (10 Categories, Aristotelian)
Each category has unique visual DNA derived from psychology axioms (Cialdini, cognitive load theory, dual coding, serial position effect). Select based on topic:
| If the topic is about... | Category | Arc Shape | Hook Style | Primary Cialdini |
|--------------------------|----------|-----------|------------|------------------|
| Explaining a research paper | `paper_decoder` | Revelatory | Face + paper panel | Authority |
| Comparing AI tools/models | `tool_showdown` | Divergent | Multi-screenshot face-off | Social Proof |
| Today's AI development | `breaking_news` | Convergent | News-editorial face | Scarcity |
| Step-by-step AI tool how-to | `tool_tutorial` | Linear | Phone-in-hand / device mockup | Reciprocity |
| Controversial opinion | `hot_take` | Confrontational | Bold abstract typography | Authority |
| Copy-paste prompts/templates | `prompt_playbook` | Divergent | Phone screenshot mockup | Reciprocity |
| Complete sector overview | `industry_map` | Divergent | Multi-person face-off | Authority |
| Build [X] with AI project | `build_this` | Linear+Reveal | Multi-device result showcase | Social Proof |
| Funding/business news | `founders_money` | Convergent | Founder portrait + data | Scarcity |
| Future predictions/timeline | `future_scenario` | Revelatory | Abstract cinematic AI imagery | Scarcity |
**Universal Psychology Rules (apply to ALL categories):**
- Max 4 information chunks per slide (Cognitive Load Theory, Sweller)
- Pattern interrupt every 2-3 slides (diagram, comparison, color shift, or layout change)
- Density wave: H-M-H-M-H-H-M (never 3 high-density slides consecutively)
- Synthesis slide = THE save trigger (Serial Position Effect: last items remembered best)
- Dual-code the hardest concept (Paivio: visual + text = 6.5x retention)
- CTA matches save trigger: utility categories → "Save this", social categories → "Share/Comment"
**Category-to-Slide-Sequence Quick Reference:**
- `paper_decoder` (9 slides): hook → body → **diagram** → body → body → **diagram** → body → synthesis → cta
- `tool_showdown` (8 slides): hook → body → **comparison** → body → body → **comparison** → synthesis → cta
- `breaking_news` (8 slides): hook → body → body → body → **diagram** → body → synthesis → cta
- `tool_tutorial` (8 slides): hook → body → **tool** → **tool** → **tool** → body → synthesis → cta
- `hot_take` (7 slides): hook → body → body → body → body → synthesis → cta (text-driven, no diagrams)
- `prompt_playbook` (9 slides): hook → body → body → body → **comparison** → body → body → synthesis → cta
- `industry_map` (9 slides): hook → **diagram** → body → body → body → **comparison** → **diagram** → synthesis → cta
- `build_this` (8 slides): hook → body → **tool** → **tool** → **tool** → body → synthesis → cta
- `founders_money` (7 slides): hook → body → body → body → **diagram** → synthesis → cta
- `future_scenario` (8 slides): hook → body → body → **diagram** → body → body → synthesis → cta
#### Role-to-SlideType Mapping
Map each archetype role to a renderer slide type when building the carousel spec:
| Archetype Role | Renderer Slide Type | Notes |
|---------------|-------------------|-------|
| `hook` | `hook` | Use `title` + `title_highlight` for split title effect |
| `intro`, `context`, `reveal`, `before` | `body` | Use `title_highlight` for the key phrase |
| `step`, `component`, `layer`, `shift`, `evidence`, `action` | `body` | Use `bullets` for key points |
| `item` | `body` | Use `title_highlight` for the item name, `bullets` for details |
| `diagram`, `connection` | `diagram` | Use `diagram_nodes` with `vertical` or `horizontal` layout |
| `contrast`, `reframe` | `comparison` | Use `columns` with opposing views |
| `result`, `after`, `lesson`, `implication` | `body` | Use title highlight to emphasize the key outcome |
| `synthesis` | `synthesis` | Use `points[]` for numbered key takeaways |
| `cta` | `cta` | Use `handle`, `cta_text`, optional `stats[]` |
| `bonus`, `pitfalls`, `prediction` | `body` | Use bullets for listed points |
### PHASE 1.5: VISUAL STRATEGY DECISION (Before Writing Content)
Before writing any content, decide the **visual strategy** for this carousel. You have access to multiple tools -- choose the right ones for the topic.
#### Available Visual Tools Inventory
| Tool | What It Does | When to Use | How to Invoke |
|------|-------------|-------------|---------------|
| **AI Cinematic Images** | HD photorealistic/artistic images (Gemini 3 Pro) | Hook/CTA backgrounds, emotional priming, conceptual anchoring | `generate-image` skill with hyper-detailed prompt (50+ words) |
| **AI Flowcharts/Diagrams** | Production-quality flowcharts with text labels, arrows, boxes | Process flows, pipelines, decision trees -- REPLACES TikZ for better visuals | `generate-image` skill with structural prompt describing boxes + connections |
| **AI Architecture Diagrams** | Blueprint-style system diagrams with components and connections | Microservices, tech stacks, system design | `generate-image` skill with component/connection prompt |
| **AI Infographics/Charts** | Bar charts, data visualizations with accurate labels and proportions | Market data, statistics, comparisons | `generate-image` skill with data + style description |
| **AI Abstract Backgrounds** | Neural networks, geometric patterns, cosmic visuals | Slide backgrounds via `ai_bg` | `generate-image` skill with atmosphere/material prompt |
| **TikZ Diagrams** | Vector flowcharts in LaTeX (basic but reliable) | Simple 3-5 node flows where AI image gen is overkill | Use `diagram` slide type with `diagram_nodes` |
| **Gradient Backgrounds** | TikZ-rendered gradient fills with geometric accents | Default for all text-only slides | Set `bg_style: "gradient"` in slide data |
#### CRITICAL: Slide-Type Visual Rule (Experimentally Verified)
This rule was established through controlled A/B experiments (7 strategies, same content, scored 1-10). It overrides gut instinct:
| Slide Type | Visual Strategy | WHY (Experimental Evidence) |
|-----------|----------------|---------------------------|
| **Hook** | `ai_bg` full-bleed + 0.60-0.68 overlay | Scroll-stopping power. First slide = 80% of engagement. Score: 8.0/10 |
| **Body** | **TEXT-ONLY. No images.** | Images on body slides destroy 40% of content space. Text-only scored 8.3/10 vs 5.7/10 with images |
| **Diagram** | **AI-generated diagram as `ai_bg`** (preferred) OR TikZ fallback | Gemini 3 Pro generates production-quality flowcharts with readable labels, arrows, and boxes. Far more visually striking than basic TikZ. Use `ai_bg` + 0.55-0.65 overlay so text remains readable over the diagram. |
| **Synthesis** | Text-only | Save-worthy reference material. Images would reduce information density. |
| **CTA** | `ai_bg` full-bleed + 0.65-0.70 overlay | Emotional close with visual punch. |
**DO NOT** put AI images on body slides. This was the single biggest quality mistake found in testing.
**DO NOT** use browser screenshots on any slides. They always look terrible embedded in carousel slides.
#### Visual Strategy Decision Matrix (Topic-Level)
For each topic, determine the primary visual mode, background style, and which slide-level visuals to use:
| Topic Type | Background Style | Hook Visual | Body Visuals | Diagram Strategy | Example |
|-----------|-----------------|-------------|-------------|-----------------|---------|
| **Philosophy / Mindset** | `gradient` | AI image: symbolic figure | None (text carries weight) | AI-generated concept map | Stoic principles: marble bust + storm |
| **Tool Review / SaaS** | `gradient` or `gradient_mesh` | AI image: abstract tech glow | None (text-only bullets describe tools) | AI-generated comparison chart | "6 AI Tools": text descriptions + AI chart |
| **News / Current Events** | `gradient` | AI image: dramatic scene | None (text with citations) | AI-generated timeline or power map | "AI War 2025": cinematic + AI power map |
| **Technical Tutorial** | `gradient` (clean) | AI image: conceptual diagram | None (step-by-step text) | AI-generated architecture/flowchart | "Deploy with Docker": AI architecture diagram |
| **Business / Strategy** | `gradient` | AI image: bold abstract | None (text with real data citations) | AI-generated bar chart or funnel | "Growth Hacking": AI infographic |
| **Comparison / Versus** | `gradient_mesh` | AI image: abstract contrast | `comparison` slide type columns | AI-generated side-by-side chart | "React vs Vue": comparison columns + AI chart |
| **Creative / Design** | `gradient_mesh` (dark) | AI image: artistic/gallery quality | None (text-only) | AI-generated process flow | "UX Trends 2025": artistic + AI flow |
| **Framework / Mental Model** | `gradient` | AI image: system metaphor | None (text explains components) | AI-generated flowchart (preferred over TikZ) | "OODA Loop": AI flowchart as `ai_bg` |
| **Data / Research** | `gradient` | AI image: data visualization concept | None (text with specific numbers) | AI-generated bar chart / infographic | "AI Market 2025": AI bar chart |
#### AI Image Generation Best Practices
**Model & Routing**:
- Use `generate-image` skill (uses `AI_GATEWAY_API_KEY`). Nano-banana-pro requires `GEMINI_API_KEY` (often unset) but uses the same underlying model.
- Model: `google/gemini-3-pro-image-preview` (primary). Fallback: `google/gemini-3.1-flash-image-preview`.
- Output: ~1408x768 landscape. Overlay compensates for portrait stretch on slides.
**Gemini 3 Pro Proven Capabilities** (Experimentally Verified):
| Capability | Quality | Best Use in Carousels | Prompt Strategy |
|-----------|---------|----------------------|-----------------|
| **Cinematic portraits** | Excellent | Hook/CTA backgrounds | 50+ words: materials, lighting, composition, colors, atmosphere |
| **Multi-image composition** | Excellent (avg 9.6/10) | Hook slides with real faces + screenshots | Aristotelian axioms below. Send base64 to `/api/v1/images/generations` |
| **Screenshot → device mockup** | Excellent | Tool showcase, product launch slides | "floating laptop/phone mockup, dark studio, reflective surface" |
| **Person + screenshot editorial** | Excellent | News hooks with evidence | "person as SUBJECT, screenshot as floating holographic EVIDENCE panel" |
| **Multi-screenshot dashboard** | Excellent | Comparison/versus slides | "floating panels at varied depths, color-coded edge glows, grid floor" |
| **Flowcharts** | Excellent | Diagram slides as `ai_bg` | Describe boxes, arrows, labels, and connections structurally |
| **Abstract backgrounds** | Excellent | Any slide background | Materials, colors, atmosphere, "no text no words" |
#### The 7 Aristotelian Axioms for Multi-Image Composition (Experimentally Proven)
These irreducible premises govern ALL multi-image prompts. Every prompt must satisfy all 7:
**A1: VISUAL HIERARCHY** -- Eye processes: faces > contrast edges > text > color fields. Composition must respect this order.
**A2: INPUT TYPE DETERMINES ROLE** -- Each input has exactly one role:
- Photo of person → SUBJECT (preserve face, never modify)
- Screenshot/UI → EVIDENCE (float as holographic panel, stylize frame, preserve content)
- Logo/brand → ANCHOR (small, consistent corner placement)
- Abstract/texture → ATMOSPHERE (background only)
**A3: UNIFIED LIGHT SOURCE** -- All elements share one dominant light direction. Mixed lighting = instant "fake" detection.
**A4: DEPTH CREATES DRAMA** -- Foreground sharp (subject), midground recessed (screenshots), background soft (atmosphere). 3 layers minimum.
**A5: NEGATIVE SPACE IS FUNCTIONAL** -- Bottom 30-35% dark for text overlay. Not waste -- it's where the headline goes.
**A6: COLOR TEMPERATURE = STORY** -- Cool blue/teal = innovation. Warm red = urgency. Split red/blue = competition. Mono + accent = editorial.
**A7: NO-TEXT SEAL** -- Always end with "absolutely no text, no words, no letters, no watermarks" (outside screenshots).
#### Proven Scenario Prompt Templates (avg 9.6/10 across 10 tests)
**Person + News Screenshot** (9.5/10): "Image 1 is [person] -- preserve face, place in left 60%, dramatic side lighting. Image 2 is screenshot -- float as glowing translucent panel, tilted 8 degrees, recessed behind subject, cyan edge glow. Dark moody background, cinematic depth of field. Bottom 30% dark. No text outside screenshot."
**Tool Screenshot Showcase** (9/10): "Place screenshot on sleek floating laptop mockup angled 15 degrees. Dark gradient background, ambient teal glow from screen. Glossy reflective surface below. Premium Apple product launch aesthetic. No text outside screenshot."
**Multi-Screenshot Dashboard** (9.5/10): "Arrange as glowing panels floating in dark space, varied depths and angles (5-15 degrees). Largest centered. Color-coded edge glows. Grid floor, particle effects. Digital command center aesthetic. No text outside screenshots."
**Person + Screenshots + Logo** (10/10): "Person as dominant subject center-left, face preserved. Screenshots as holographic panels around them. Logo small in upper corner with glow. Volumetric light rays, 3-layer depth. No text outside screenshots/logo."
**Face-Off + Data** (10/10): "Person A on LEFT in profile facing right, red lighting. Person B on RIGHT facing left, blue lighting. Dashboard between them as floating holographic display. Smoke and sparks in the gap. Competitive energy. No text outside screenshot."
**Phone in Hand** (10/10): "Screenshot on smartphone held in hand from lower-right. Dark background, soft bokeh lights. Screen bright and crisp. Lifestyle photography style. No text outside screenshot."
**5-Image Mega** (10/10): "2 people (main foreground, secondary recessed) + 2 screenshots (holographic panels, color-coded glows) + logo (corner). Volumetric light, split lighting, multiple depth layers. No text outside screenshots/logo."
**Prompt Rules**:
- **HYPER-DETAILED** (50+ words): materials, lighting, composition, colors, atmosphere. Generic = bad.
- **Always end with "absolutely no text, no words, no letters, no watermarks"** -- AI models add unwanted text otherwise.
- **Declare each input's role explicitly** (per A2): "Image 1 is a portrait... Image 2 is a screenshot..."
- **Specify depth map** (per A4): "subject sharp foreground, screenshots floating midground, atmospheric background"
- **Lock light direction** (per A3): "single dominant light from upper-left, rim light on subject"
- For editorial portraits: add "ABSOLUTELY NO TEXT NO LOGOS NO MAGAZINE ELEMENTS" or Gemini creates TIME covers.
- Overlay opacity sweet spot: 0.60-0.68 for hooks, 0.55-0.65 for diagrams, 0.65-0.70 for CTA.
#### Background Style Selection
Set `bg_style` in the carousel spec or per-slide `data` to control the look:
| `bg_style` Value | Visual Result | Best For |
|-----------------|--------------|----------|
| `"gradient"` (default) | Top-to-bottom gradient with subtle accent glow | All themes. Clean, modern, professional |
| `"texture"` | AI-generated paper/fabric texture | AVOID -- produces grey rock look |
| `"gradient_mesh"` | Multi-stop gradient with geometric accent shapes | Creative, premium, high-contrast |
| `"solid"` | Flat theme background color | Clean/education themes, data-heavy content |
| (AI background) | Full-bleed AI image with overlay | Dramatic hooks, artistic carousels |
Set it at the spec level for all slides: `"bg_style": "gradient"` in the spec JSON.
Or per-slide for variation: `"data": {"bg_style": "gradient_mesh", ...}` on specific slides.
#### Screenshot Capture Protocol -- DEPRECATED
**DO NOT use browser screenshots on carousel slides.** They consistently look terrible -- low resolution, poorly framed, and badly integrated with the slide design. This was tested extensively and abandoned.
**Instead**: Use AI-generated images via Gemini 3 Pro for any visual needs:
- Tool/product visuals: Generate an AI illustration or abstract representation
- Data/charts: Generate AI bar charts or infographics (Gemini 3 Pro handles these well)
- Architecture/flows: Generate AI flowcharts or architecture diagrams
- People: Use text descriptions instead of photos
### PHASE 2: CONTENT CREATION
1. **Write the hook** (Slide 1) -- Apply the Hook Taxonomy. This slide determines everything.
2. **Write each slide** -- One idea per slide. No exceptions. Apply the Bullshit Test to each.
3. **Map to renderer data format** -- For each slide, create the JSON data object matching the slide type's required fields (see Data fields by slide type in RENDERING SCRIPTS).
4. **Execute the visual strategy** decided in Phase 1.5:
- Generate AI images per the 2-3 Rule (hook + 1-2 emotional peaks). State each image's telos.
- Capture browser screenshots for any real tools/products/news referenced.
- Set `bg_style` per the Background Style Selection table.
- Use `diagram` slide type for any process/flow that benefits from a visual.
5. **Select Instagram music** -- Apply the Music Decision Matrix (see MUSIC SELECTION).
6. **Write the caption** -- Front-load value in first 2 lines. Include CTA and hashtags.
7. **Build the carousel spec JSON** -- Assemble all slides into a single spec file for the orchestrator.
### PHASE 3: VISUAL PRODUCTION (LaTeX Pipeline)
Use the **LaTeX-based rendering pipeline** for publication-grade output. This produces slides that match or exceed the quality of accounts with 1M+ followers (Chase AI, Analytics Vidhya, etc.).
The pipeline: **LaTeX (TikZ) -> PDF (pdflatex) -> PNG (pdftoppm at 300 DPI) -> resize to 1080x1350**
#### Why LaTeX (not Pillow/HTML)
- **Knuth-Plass optimal line breaking** -- no ugly word wraps
- **Professional font kerning and ligatures** -- Palatino with microtype
- **Native vector diagrams** -- TikZ flow charts (fallback for simple diagrams)
- **AI image integration** -- full-bleed Gemini 3 Pro images for hook/CTA/diagram backgrounds
- **Gradient backgrounds** -- clean TikZ-rendered gradients for text-only slides
- **Publication-grade output** -- the same engine that typesets academic papers and books
#### Step 3a: Generate AI Images (Hook, CTA, Diagrams)
Generate AI images for hook background, CTA background, and optionally diagram backgrounds:
```bash
# Hook background (cinematic, hyper-detailed 50+ word prompt)
python3 ~/.claude/skills/generate-image/scripts/generate_image.py \
"Dramatic cinematic split-screen composition: left side dark blue crystalline monolith with electric energy, right side warm golden organic neural network, clash of opposing forces, volumetric lighting, no text no words no letters" \
--model "google/gemini-3-pro-image-preview" --output tmp/carousel/hook_bg.png
# CTA background (emotional close)
python3 ~/.claude/skills/generate-image/scripts/generate_image.py \
"Mesmerizing cosmic portal with swirling deep indigo and purple energy, golden light rays, ethereal atmosphere, no text no words" \
--model "google/gemini-3-pro-image-preview" --output tmp/carousel/cta_bg.png
# Diagram as AI image (optional -- replaces TikZ for better visuals)
python3 ~/.claude/skills/generate-image/scripts/generate_image.py \
"Professional flowchart: Data Collection box connects to Processing box connects to Output box, clean white background, blue and grey, sharp vector style, readable labels" \
--model "google/gemini-3-pro-image-preview" --output tmp/carousel/diagram_bg.png
```
#### Step 3b: Render Slides with 7 Slide Types
The LaTeX renderer (`render_latex_slide.py`) supports 7 slide types:
| Type | Description | Best For |
|------|-------------|----------|
| `hook` | Large title + highlighted phrase + subtitle | Cover / first slide |
| `body` | Title + highlighted text + body + bullets | Content-heavy slides, curated list items |
| `comparison` | Multi-column comparison table | Side-by-side analysis |
| `diagram` | Title + TikZ flow diagram (vertical/horizontal) | Architecture, workflows |
| `synthesis` | Styled numbered points with badges | Save-worthy summary |
| `cta` | Centered title + text + handle button | Call to action |
**4 Color Themes**: `warm` (parchment/terracotta), `clean` (white/blue), `dark` (indigo/purple), `earth` (sage/gold)
**Slide 1 (Hook)** -- Title with AI background:
```bash
python3 ~/.claude/skills/world-class-carousel/scripts/render_latex_slide.py \
--type hook \
--data tmp/carousel/hook_data.json \
--output tmp/carousel/slide_01.png \
--theme dark --brand tmp/carousel/brand.json
```
Where `hook_data.json` contains: `{"title": "6 AI Tools That Will", "title_highlight": "Replace Your Stack", "subtitle": "The tools 10x engineers are switching to.", "callout": "Save this!", "slide_num": 1, "total_slides": 8, "ai_bg": "tmp/carousel/hook_bg.png", "overlay_opacity": 0.63}`
**Body slides** -- Content-heavy with bullets (gradient bg, NO texture):
```bash
python3 ~/.claude/skills/world-class-carousel/scripts/render_latex_slide.py \
--type body \
--data tmp/carousel/body_data.json \
--output tmp/carousel/slide_02.png \
--theme dark --brand tmp/carousel/brand.json
```
Where `body_data.json` contains: `{"title": "Why Most Developers", "title_highlight": "Get This Wrong", "body": "The biggest mistake is...", "bullets": ["Point 1", "Point 2"], "slide_num": 2, "total_slides": 8, "bg_style": "gradient"}`
**NOTE**: Always pass data as a JSON file path, never inline JSON. Always include `"bg_style": "gradient"` for text-only slides. Always pass `--brand`.
**Comparison slide** -- Multi-column:
```bash
python3 ~/.claude/skills/world-class-carousel/scripts/render_latex_slide.py \
--type comparison \
--data tmp/carousel/comparison_data.json \
--output tmp/carousel/slide_04.png \
--theme warm --brand tmp/carousel/brand.json
```
Where `comparison_data.json` contains: `{"title": "Claude vs GPT", "subtitle": "How they compare", "columns": [{"name": "Claude", "items": [{"label": "Best for", "value": "Complex refactors"}]}, {"name": "GPT-4", "items": [{"label": "Best for", "value": "Quick prototyping"}]}], "slide_num": 4, "total_slides": 9, "bg_style": "gradient"}`
**Diagram slide** -- AI-generated diagram background (preferred) or TikZ fallback:
```bash
python3 ~/.claude/skills/world-class-carousel/scripts/render_latex_slide.py \
--type diagram \
--data tmp/carousel/diagram_data.json \
--output tmp/carousel/slide_07.png \
--theme dark --brand tmp/carousel/brand.json
```
Where `diagram_data.json` contains: `{"title": "The Architecture", "description": "How the tools connect.", "diagram_nodes": [{"label": "Code", "desc": "Write"}, {"label": "Deploy", "desc": "Ship"}, {"label": "Monitor", "desc": "Track"}], "diagram_type": "vertical", "slide_num": 7, "total_slides": 9, "ai_bg": "tmp/carousel/diagram_bg.png", "overlay_opacity": 0.60, "bg_style": "gradient"}`
**Synthesis slide** -- Save-worthy numbered summary:
```bash
python3 ~/.claude/skills/world-class-carousel/scripts/render_latex_slide.py \
--type synthesis \
--data tmp/carousel/synthesis_data.json \
--output tmp/carousel/slide_08.png \
--theme dark --brand tmp/carousel/brand.json
```
Where `synthesis_data.json` contains: `{"title": "Your Stack", "points": ["Tool 1 for X", "Tool 2 for Y", "Tool 3 for Z"], "slide_num": 8, "total_slides": 9, "bg_style": "gradient"}`
**CTA slide** -- with AI background for emotional close:
```bash
python3 ~/.claude/skills/world-class-carousel/scripts/render_latex_slide.py \
--type cta \
--data tmp/carousel/cta_data.json \
--output tmp/carousel/slide_09.png \
--theme dark --brand tmp/carousel/brand.json
```
Where `cta_data.json` contains: `{"title": "Want the full breakdown?", "cta_text": "Follow for daily tips.", "handle": "@yourbrand", "slide_num": 9, "total_slides": 9, "show_nav": false, "ai_bg": "tmp/carousel/cta_bg.png", "overlay_opacity": 0.67}`
#### Step 3d: Full Carousel Generation (Orchestrator)
Generate a complete carousel from a single JSON spec:
```bash
python3 ~/.claude/skills/world-class-carousel/scripts/generate_carousel.py \
--spec carousel_spec.json \
--output-dir outputs/carousel/ \
--brand tmp/carousel/brand.json
```
The spec JSON format:
```json
{
"topic": "6 AI Tools That Will Replace Your Stack",
"brand": "AI Builder",
"theme": "dark",
"bg_style": "gradient",
"slides": [
{"type": "hook", "data": {"title": "...", "title_highlight": "...", "ai_bg": "tmp/hook_bg.png", "overlay_opacity": 0.63}},
{"type": "body", "data": {"title": "...", "bullets": ["..."], "bg_style": "gradient"}},
{"type": "diagram", "data": {"title": "...", "diagram_nodes": [{"label": "...", "desc": "..."}], "diagram_type": "vertical", "ai_bg": "tmp/diagram_bg.png", "overlay_opacity": 0.60}},
{"type": "synthesis", "data": {"title": "...", "points": ["..."], "bg_style": "gradient"}},
{"type": "cta", "data": {"title": "...", "handle": "@brand", "ai_bg": "tmp/cta_bg.png", "overlay_opacity": 0.67}}
]
}
```
**Spec-level `bg_style`** applies to all slides. Per-slide `data.bg_style` overrides it. Options: `"gradient"`, `"gradient_mesh"`, `"solid"`. If omitted, defaults to `"gradient"`. **Never** use `"texture"`.
The orchestrator auto-injects brand name, slide numbering, renders all slides, and creates a preview grid.
#### Brand Configuration System
The design system is fully generalized through brand configs -- JSON files that define visual identity per channel or brand. Pass `--brand brand.json` to any render command.
**Brand config JSON format**:
```json
{
"name": "TechStack AI", // Brand name shown in header
"logo": "path/to/logo.png", // Optional: logo image replaces text in header
"theme": "dark", // Base theme: warm, clean, dark, earth
"accent_override": "6366F1", // Optional: override accent hex (no #)
"font_serif": "newpxtext", // LaTeX serif font package (default: Palatino)
"header_style": "bold", // Header text: italic, bold, or plain
"nav_style": "circle", // Navigation arrow: circle, arrow, none
"divider_style": "line", // Dividers: line, ornament (diamond), dots, none
"corner_radius": "6pt" // Rounded corner radius for labels/badges
}
```
**3 sample brand configs** (in `tmp/brands/`):
| Brand | Theme | Accent | Header | Divider | Character |
|-------|-------|--------|--------|---------|-----------|
| TechStack AI | dark | Indigo `6366F1` | Bold | Line | Modern dev/AI content |
| Growth Academy | earth | Amber `B45309` | Italic | Ornament | Business coaching |
| Code Academy | clean | Blue (default) | Bold | Dots | Educational tut...
© happycapy-ai · MIT · happycapy-ai/Happycapy-skills