Art Skill

Customization

• PREFERENCES.md - Aesthetic preferences, default model, output location
• CharacterSpecs.md - Character design specifications
• SceneConstruction.md - Scene composition guidelines

🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)

1. Send voice notification:
   bashCopy

   curl -s -X POST http://localhost:31337/notify \
     -H "Content-Type: application/json" \
     -d '{"message": "Running the WORKFLOWNAME workflow in the Art skill to ACTION"}' \
     > /dev/null 2>&1 &

2. Output text notification:
   Running the **WorkflowName** workflow in the **Art** skill to ACTION...

What It Does

The Problem

How It Works

🛑 STRUCTURAL ENFORCEMENT — --workflow=<name> IS REQUIRED

1. Generate.ts itself refuses to run unless you pass --workflow=<name> (or the explicit --freeform-confirmed opt-out). It exits non-zero with the workflow lookup table.
2. ArtWorkflowGuard.hook.ts (PreToolUse Bash) blocks any Bash command containing Art/Tools/Generate.ts without --workflow= or --freeform-confirmed, with exit code 2 and the same lookup table.

Most Common Failure Mode (don't repeat it)

Workflow → command (copy-paste)

bun ~/.claude/skills/Art/Tools/Generate.ts \
  --workflow=<WorkflowName> \
  --model nano-banana-pro \
  --prompt "..." \
  --size 2K \
  --aspect-ratio 16:9 \
  --output ~/Downloads/<filename>.png

🚨🚨🚨 MANDATORY: Output to Downloads First 🚨🚨🚨

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
⚠️  ALL GENERATED IMAGES GO TO ~/Downloads/ FIRST                   ⚠️
⚠️  NEVER output directly to project directories                    ⚠️
⚠️  User MUST preview in Finder/Preview before use                  ⚠️
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🚨🚨🚨 MANDATORY: Transparency Rules for Blog Headers 🚨🚨🚨

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
⚠️  INLINE (body) image → TRANSPARENT (PNG with alpha)           ⚠️
⚠️  SOCIAL THUMBNAIL (frontmatter) → SEPIA #EAE9DF (opaque)       ⚠️
⚠️  EVERY blog header MUST use --thumbnail (produces both)        ⚠️
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

• --thumbnail is the ONLY correct flag for blog headers — it implicitly enables --remove-bg and produces BOTH output.png (transparent) AND output-thumb.png (#EAE9DF background).
• Background removal runs locally via rembg (no external API). If the model returns JPEG (Nano Banana Pro often does), Generate.ts automatically renames the output from .jpg → .png after rembg processing so the final transparent file is a real PNG with a real alpha channel. If you ever see a .jpg labeled "transparent", that is NOT transparent.
• If rembg isn't installed at ~/.local/bin/rembg, the tool fails loudly with install instructions rather than silently producing an opaque image. Install: pipx install rembg (or set REMBG_BIN env var to override the path).

1. file ~/Downloads/[name].png → must report PNG image data, ... RGBA (8-bit/color RGBA). If it says JPEG or 8-bit colormap without alpha, transparency failed.
2. file ~/Downloads/[name]-thumb.png → must report PNG image data. The thumb is intentionally opaque with sepia background.
3. Only after both pass: copy to the project directory and wire into the post.

• Body inline: [![Alt](/images/blog/[slug]/header.webp)](/images/blog/[slug]/header.webp) — use the transparent WebP converted from the .png.
• Frontmatter: thumbnail: https://example.com/images/blog/[slug]/header-thumb.png — always the -thumb.png (opaque sepia).

Workflow Routing

Core Aesthetic

• Visual style and influences
• Line treatment and rendering approach
• Color palette and wash technique
• Character design specifications
• Scene composition rules

Reference Images

• Reference image locations
• Style examples by use case
• Character and scene reference guidance

Image Generation

Model-Specific Size Requirements

Model Selection — when to pick which

🚨 CRITICAL: Always Output to Downloads First

1. Generate to ~/Downloads/[descriptive-name].png
2. User reviews in Preview
3. If approved, THEN copy to final destination (e.g., cms/public/images/)
4. Create WebP and thumbnail versions at final destination

# CORRECT - Output to Downloads for preview
bun run ${LIFEOS_SKILL_DIR}/Tools/Generate.ts \
  --model nano-banana-pro \
  --prompt "[PROMPT]" \
  --size 2K \
  --aspect-ratio 1:1 \
  --thumbnail \
  --output ~/Downloads/blog-header-concept.png

# After approval, copy to final location (substitute your blog/site path)
cp ~/Downloads/blog-header-concept.png ~/your-site/public/images/
cp ~/Downloads/blog-header-concept-thumb.png ~/your-site/public/images/

Multiple Reference Images (Character/Style Consistency)

# Multiple reference images for better likeness
bun run ${LIFEOS_SKILL_DIR}/Tools/Generate.ts \
  --model nano-banana-pro \
  --prompt "Person from references at a party..." \
  --reference-image face1.jpg \
  --reference-image face2.jpg \
  --reference-image face3.jpg \
  --size 2K \
  --aspect-ratio 16:9 \
  --output ~/Downloads/character-scene.png

• Up to 5 human reference images
• Up to 6 object reference images
• Maximum 14 total reference images per request

Examples

User: "create a header for my AI agents post"
→ Invokes ESSAY workflow
→ Generates charcoal sketch prompt
→ Creates image with architectural aesthetic
→ Saves to ~/Downloads/ for preview
→ After approval, copies to public/images/

User: "make a diagram showing the SPQA pattern"
→ Invokes TECHNICALDIAGRAMS workflow
→ Creates structured architecture visual
→ Outputs PNG with consistent styling

User: "visualize humans vs AI decision-making"
→ Invokes COMPARISONS workflow
→ Creates side-by-side visual
→ Charcoal sketch with labeled elements

User: "create icon for the skill system pack"
→ Invokes CREATEPAIPACKICON workflow
→ Reads workflow from Workflows/CreateLifeosPackIcon.md
→ Generates 1K image with --remove-bg for transparency
→ Resizes to 256x256 RGBA PNG
→ Outputs to ~/Downloads/ for preview
→ After approval, copies to ${PROJECTS_DIR}/LIFEOS/Packs/icons/

Gotchas

• Always output to ~/Downloads/ first — NEVER directly to project directories. User must preview before use. Multiple past failures from pushing wrong images directly to repos.
• Verify image dimensions match target use case before claiming done. Social media previews, blog headers, and thumbnails have different size requirements. A header that works on the blog may break OG/social previews.
• nano-banana-pro uses --size for resolution (1K/2K/4K) and SEPARATE --aspect-ratio flag. Don't pass aspect ratio values to --size.
• Reference images: max 5 human, 6 object, 14 total per request (Gemini API limit).
• After generating, use Read tool to visually confirm the image before reporting success. "Generated successfully" means nothing if you haven't looked at it.
• When asked to use a specific image URL or file, use EXACTLY that asset. Don't substitute similar images. Past rating-1 failures from using wrong image assets.
• --remove-bg may produce black backgrounds instead of transparency. Always verify transparent PNG output visually before deploying.
• --remove-bg is unsafe for thin-linework technical diagrams. rembg classifies thin black ink on a light field as "background" and strips it, leaving a near-empty ghost. Documented 2026-05-11 on the free-will flowchart. Mitigations: (a) prompt for thick saturated linework first so rembg has a strong signal, or (b) skip --remove-bg entirely when the destination background matches the image's background (blog page is sepia #EAE9DF — opaque sepia diagram on sepia page composites with zero visible seam, no alpha needed).
• Logo fidelity breaks in 3D/perspective scenes even with a reference image. Documented 2026-06-11 on the UL wallpaper set: straight-on and macro scenes held the glyph topology in 7/7 rolls, but the isometric 3D scene closed the open mark into a loop and dropped its isolated dot. For any perspective/3D composition with a logo, add topology-locked negative language to the prompt ("do not close the shape into a loop", "do not omit the isolated dot", name every stroke and terminal) on top of --reference-image, and vision-verify the topology specifically.
• nano-banana-pro "4K 16:9" is actually 5504×3072 (43:24, ~0.8% wider than 16:9), saved as .jpg even when --output says .png. Disclose the native ratio when the spec says 16:9, and probe the real filename before Read/delivery.
• White-box-on-cream bug (2026-06-20): flattening an OPAQUE jpeg on #EAE9DF is a no-op. nano-banana-pro returns an opaque JPEG; magick -background "#EAE9DF" -flatten only fills alpha, so the model's baked near-white ground survives and paints a white rectangle on the cream blog page ("it has a fucking white background"). For inline blog headers, cut true alpha FIRST (bun ~/.claude/LIFEOS/TOOLS/RemoveBg.ts), then derive the WebP, and verify identify -format "%[channels]" inline.webp == srgba. Opaque-sepia inline is valid ONLY on an image that already has alpha. See Essay.md Step 7.0.5.
• Essay/blog headers MUST be signed "{{DA_NAME}}" (2026-06-20 principal directive) — human handwriting, never calligraphy. Programmatic stamp in Essay.md Step 7.1 (Bradley-Hand-Bold, semi-transparent charcoal, bottom-right); never prompt the signature into the model (it garbles). Snell-Roundhand / Apple-Chancery / Savoye script faces were explicitly rejected — real-hand look, not calligraphy.

Execution Log

echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","skill":"Art","workflow":"WORKFLOW_USED","input":"8_WORD_SUMMARY","status":"ok|error","duration_s":SECONDS}' >> ~/.claude/LIFEOS/MEMORY/SKILLS/execution.jsonl