/infographic-v2

name: infographic-v2
description: Generate professional infographics using Nano Banana MCP (Gemini AI image generation). Follows a guided flow - analyze content, suggest visualizable concepts, propose visualization approaches, then generate on-brand images. USE THIS SKILL WHEN user says "create infographic v2", "make a visual v2", "infographic-v2". Modular architecture with lazy-loaded reference files for each phase.
disable-model-invocation: true

Infographic Generator

Create professional infographics in the BenAI brand style for LinkedIn and newsletters. Uses Gemini AI via the Nano Banana MCP server for image generation.

**Connectors:** Nano Banana MCP (Gemini AI image generation)

**Core philosophy:** The quality of the output is determined by the quality of the thinking BEFORE any prompt is written. Spend 70% of the effort understanding what to visualize and 30% on how to visualize it.

**UX philosophy:** Every user interaction must be a genuine taste decision. If the AI can make a good default, it should make it silently and let the user override. Never ask for confirmation of something the AI decided.

---

When This Skill Loads

**DO NOT load any reference files yet.** Files load lazily, one phase at a time.

1. Execute Phase 0 (silent config check) 2. If API key is NOT configured: skip to Phase 5 (API Key Setup). Do NOT ask about content. 3. If API key IS configured: begin Phase 1.

---

UNDERSTAND

Phase 0: Silent Config Check

Run silently. Do NOT ask questions yet.

0.1: Ensure Directory Structure

mkdir -p .infographic/images
mkdir -p .infographic/prompts

0.2: Check for API Key

if [ -n "$GEMINI_API_KEY" ]; then
  echo "API key found in environment"
elif [ -f .env ] && grep -q "^GEMINI_API_KEY=.\+" .env; then
  echo "API key found in .env file"
else
  echo "API key not configured"
fi

**Decision:**

• Found (env var OR .env): proceed silently to Phase 1
• NOT found: jump IMMEDIATELY to Phase 5 (API Key Setup)

0.3: Check for Brand Config

Check these locations in order (first found wins):

if [ -f ./branding.md ]; then
  cat ./branding.md
elif [ -f .infographic/brand.md ]; then
  cat .infographic/brand.md
fi

If brand config exists, acknowledge briefly: "I found your brand context. Ready to create your infographic!"

**How branding.md gets created:** The `/ads-creative` skill collects brand info (colors, fonts, voice, audience) and writes `./branding.md` in the project root. If the user has run an ads creative audit, this file will already exist. The infographic skill uses it for on-brand color palettes, typography, and style anchors.

---

Phase 1: Content Intake

**No reference files loaded.** Just collect the raw material.

**No AskUserQuestion.** Just say naturally:

> "What content should I turn into an infographic? Paste text, share a URL, or point me to a file."

Wait for content. Acknowledge receipt briefly ("Got it, analyzing now..."). Proceed immediately to Phase 2.

---

Phase 2: Analysis + First Choices

>>> READ references/content-analysis.md NOW

2.1: Four-Layer Analysis (silent)

Apply the framework from `content-analysis.md`. Extract meaning at all 4 layers:

• Layer 1 (Narrative): What happened?
• Layer 2 (Themes): What is it about?
• Layer 3 (Claims): What does it SAY is true about the world?
• Layer 4 (Information): What concrete data, comparisons, or frameworks exist?

Present the analysis explicitly labeled by layer with honest strength ratings (Weak / Moderate / Strong).

2.2: Auto-Decide Intent + Output Mode

Based on the layer analysis, AUTO-DECIDE the output mode. Do NOT ask the user.

| Layer Strengths | Auto-Decision | |---|---| | Layer 3 Strong, Layer 4 Weak | Editorial Illustration | | Layer 4 Strong, Layer 3 Weak | Information Graphic | | Both Layer 3 and Layer 4 Strong | Hybrid (see sub-mode rules below) | | Both Weak | Ask the user for guidance (this is the only case where you ask) |

Hybrid Sub-Modes

When both Layer 3 and Layer 4 are strong, pick the sub-mode based on which layer is STRONGER:

| Relative Strength | Hybrid Sub-Mode | What It Produces | |---|---|---| | Layer 4 >= Layer 3 | **Data-led hybrid** | An Information Graphic (BenAI brand system, cards, data structures) with an emotionally resonant headline or framing from Layer 3. The infographic IS the output. The claim provides the hook. | | Layer 3 > Layer 4 | **Editorial-led hybrid** | An Editorial Illustration (cinematic scene, artistic style) with a small data overlay anchoring the emotion. The scene IS the output. The data provides credibility. |

**Default when equal:** Data-led hybrid. Most LinkedIn content benefits more from a clear infographic with a strong headline than from an artistic scene with a data footnote.

State the decision inline with the analysis, including the sub-mode:

> "Your content is strong at both Layer 3 and Layer 4, but the concrete framework is the real asset. I'll create a **data-led hybrid** -- a clean infographic with your philosophical claim as the headline."

If the user disagrees at any point, they can override by saying so in free text.

2.3: Batch Platform + Type + Style

Use ONE `AskUserQuestion` with TWO questions (batched). Always ask BOTH questions regardless of the auto-detected output mode. The user should always have the choice between infographic and editorial styles.

questions:
  - question: "Where will this be posted?"
    header: "Platform"
    options:
      - label: "LinkedIn (Recommended)"
        description: "4:5 portrait, optimized for feed engagement"
      - label: "Instagram"
        description: "1:1 square or 4:5 portrait"
      - label: "Twitter/X"
        description: "16:9 landscape for timeline"
      - label: "Presentation"
        description: "16:9 landscape for slides"

  - question: "What type of visual should this be?"
    header: "Type"
    options:
      - label: "Infographic (Recommended)"
        descripti