Collage & Layout Composition Expert
Expert in ALL forms of computational collage composition - from Instagram grids to Hockney joiners, from magazine layouts to generative art.
When to Use This Skill
✅ Use for:
- Grid Collages: Instagram profiles, regular layouts, tiled compositions
- Photo Mosaics: Small images forming larger pictures
- Hockney-Style Joiners: Multi-perspective photographic assemblies
- Scrapbook/Journal: Mixed media with text, frames, embellishments
- Magazine/Editorial: Professional layouts with text integration
- Vision/Mood Boards: Inspiration collections, design references
- Memory Walls: Scattered Polaroid-style arrangements
- Social Media: Stories, carousel previews, profile grids
- Abstract/Generative: Algorithmic and procedural arrangements
- Art-Historical: Dadaist, Surrealist, Pop Art styles
❌ Do NOT use for:
- Simple image editing → native-app-designer
- Generating new images → Stability AI
- Single photo quality → photo-composition-critic
- Image similarity search → clip-aware-embeddings
- Color palette extraction → color-theory-palette-harmony-expert
Expert vs Novice Shibboleths
| Topic |
Novice |
Expert |
| Layout |
"Just arrange randomly" |
Visual weight, balance, golden ratio |
| Blending |
Hard edges or simple feather |
Poisson blending preserves gradients |
| Color |
"Match colors manually" |
Optimal transport; LAB space advantages |
| Composition |
Fills all space |
Negative space as design element |
| Scale |
Same size for everything |
Varies scale for hierarchy |
| Mosaic |
"More tiles = better" |
Tile size vs. recognition tradeoff |
| Hockney |
"Stitch seamlessly" |
Imperfection IS the technique |
Decision Tree: Choosing a Style
What's the purpose?
- Systematic display → Grid Collage
- Artistic portrait from photos → Photo Mosaic
- Personal memories → Scrapbook or Memory Wall
- Design inspiration → Mood Board
- Professional/publication → Magazine Layout
- Social media → Social Templates
- Art project → Hockney/Dadaist/Surrealist
What's the vibe?
- Clean, modern → Grid with tight gutters
- Nostalgic, warm → Polaroid scatter, vintage frames
- Edgy, disruptive → Dadaist sharp cuts
- Dreamy, surreal → Seamless Poisson blending
- Cubist, intellectual → Hockney joiners
Core Algorithms (Summary)
| Algorithm |
Use Case |
Performance |
| Edge-Based Assembly |
Hockney joiners |
0.5s for 10 photos |
| Poisson Blending |
Seamless transitions |
20ms (512×512) |
| Optimal Transport |
Color harmonization |
Real-time w/ affine approx |
| Force-Directed |
Organic scatter |
200ms (50 images) |
| K-d Tree Matching |
Photo mosaic tiles |
2s for 10k tiles |
→ See references/algorithms.md for full implementations.
Anti-Patterns to Avoid
1. Ignoring Visual Weight
What it looks like: All images same size, random placement
Why it's wrong: No focal point, viewer's eye wanders aimlessly
Fix: Establish 60/30/10 hierarchy with one hero image
2. Over-Saturating the Canvas
What it looks like: Every pixel filled with image content
Why it's wrong: Visual claustrophobia, no breathing room
Fix: Use negative space intentionally (20-30% white space minimum)
3. Linear FFT for Color Matching
What it looks like: Poor perceptual color matches
Why it's wrong: RGB is not perceptually uniform
Fix: Use LAB color space for matching
4. Seamless Hockney Joiners
What it looks like: Perfectly stitched panorama
Why it's wrong: Misses the entire point - multiple perspectives
Fix: Embrace ±2° rotation variance, 5-15% overlap, intentional gaps
5. Global Poisson Blending
What it looks like: Entire image becomes washed out
Why it's wrong: Destroys local contrast, looks fake
Fix: Apply locally at seams only, preserve source gradients
6. Reusing Mosaic Tiles
What it looks like: Obvious repetition patterns in mosaic
Why it's wrong: Human eye detects patterns immediately
Fix: Track tile usage, penalize reuse, use larger tile library
MCP Integrations
| MCP |
Purpose |
| Stability AI |
Generate backgrounds, textures, missing elements |
| Firecrawl |
Research techniques, algorithm papers, art history |
| WebFetch |
Fetch documentation, tutorials, design references |
Performance Targets
| Operation |
Mac M2 |
iPhone 15 Pro |
| Grid layout (20 photos) |
<50ms |
<100ms |
| Photo mosaic (10k tiles) |
2s |
5s |
| Force-directed (50 images) |
200ms |
500ms |
| Poisson blending (512×512) |
20ms |
50ms |
| Hockney assembly (10 photos) |
0.5s |
2s |
References
→ references/collage-types.md - Grid, mosaic, scrapbook, magazine, social templates
→ references/art-historical-styles.md - Hockney, Dadaist, Surrealist, Rauschenberg
→ references/algorithms.md - Edge assembly, Poisson, optimal transport, force-directed
→ references/advanced-techniques.md - Cross-photo interactions, narrative sequences
→ references/implementation-guide.md - Metal shaders, Core ML, performance
Integrates With
- photo-composition-critic - Assess individual photos before collaging
- color-theory-palette-harmony-expert - Extract/match color palettes
- clip-aware-embeddings - Semantic grouping of images
- native-app-designer - Build collage creation UI
- metal-shader-expert - GPU-accelerated blending/effects
Remember: Great collages tell stories through arrangement. Whether grid-precise or Hockney-chaotic, the layout serves the narrative. Master both the math and the art.
1---2name: collage-layout-expert3description: Expert in ALL computational collage composition: photo mosaics, grid layouts, scrapbook/journal styles, magazine editorial, vision boards, mood boards, social media collages, memory walls, abstract/generative arrangements, and art-historical techniques (Hockney joiners, Dadaist photomontage, Surrealist assemblage, Rauschenberg combines). Masters edge-based assembly, Poisson blending, optimal transport color harmonization, and aesthetic optimization. Activate on 'collage', 'photo mosaic', 'grid layout', 'scrapbook', 'vision board', 'mood board', 'photo wall', 'magazine layout', 'Hockney', 'joiner', 'photomontage'. NOT for simple image editing (use native-app-designer), generating new images (use Stability AI), single photo enhancement (use photo-composition-critic), or basic image similarity search (use clip-aware-embeddings).4---5
6# Collage & Layout Composition Expert
7
8Expert in **ALL forms of computational collage composition** - from Instagram grids to Hockney joiners, from magazine layouts to generative art.
9
10## When to Use This Skill
11
12✅ **Use for:**
13- **Grid Collages**: Instagram profiles, regular layouts, tiled compositions
14- **Photo Mosaics**: Small images forming larger pictures
15- **Hockney-Style Joiners**: Multi-perspective photographic assemblies
16- **Scrapbook/Journal**: Mixed media with text, frames, embellishments
17- **Magazine/Editorial**: Professional layouts with text integration
18- **Vision/Mood Boards**: Inspiration collections, design references
19- **Memory Walls**: Scattered Polaroid-style arrangements
20- **Social Media**: Stories, carousel previews, profile grids
21- **Abstract/Generative**: Algorithmic and procedural arrangements
22- **Art-Historical**: Dadaist, Surrealist, Pop Art styles
23
24❌ **Do NOT use for:**
25- Simple image editing → **native-app-designer**
26- Generating new images → **Stability AI**
27- Single photo quality → **photo-composition-critic**
28- Image similarity search → **clip-aware-embeddings**
29- Color palette extraction → **color-theory-palette-harmony-expert**
30
31## Expert vs Novice Shibboleths
32
33| Topic | Novice | Expert |
34|-------|--------|--------|
35| **Layout** | "Just arrange randomly" | Visual weight, balance, golden ratio |
36| **Blending** | Hard edges or simple feather | Poisson blending preserves gradients |
37| **Color** | "Match colors manually" | Optimal transport; LAB space advantages |
38| **Composition** | Fills all space | Negative space as design element |
39| **Scale** | Same size for everything | Varies scale for hierarchy |
40| **Mosaic** | "More tiles = better" | Tile size vs. recognition tradeoff |
41| **Hockney** | "Stitch seamlessly" | Imperfection IS the technique |
42
43## Decision Tree: Choosing a Style
44
45**What's the purpose?**
46- Systematic display → **Grid Collage**
47- Artistic portrait from photos → **Photo Mosaic**
48- Personal memories → **Scrapbook** or **Memory Wall**
49- Design inspiration → **Mood Board**
50- Professional/publication → **Magazine Layout**
51- Social media → **Social Templates**
52- Art project → **Hockney/Dadaist/Surrealist**
53
54**What's the vibe?**
55- Clean, modern → Grid with tight gutters
56- Nostalgic, warm → Polaroid scatter, vintage frames
57- Edgy, disruptive → Dadaist sharp cuts
58- Dreamy, surreal → Seamless Poisson blending
59- Cubist, intellectual → Hockney joiners
60
61## Core Algorithms (Summary)
62
63| Algorithm | Use Case | Performance |
64|-----------|----------|-------------|
65| **Edge-Based Assembly** | Hockney joiners | 0.5s for 10 photos |
66| **Poisson Blending** | Seamless transitions | 20ms (512×512) |
67| **Optimal Transport** | Color harmonization | Real-time w/ affine approx |
68| **Force-Directed** | Organic scatter | 200ms (50 images) |
69| **K-d Tree Matching** | Photo mosaic tiles | 2s for 10k tiles |
70
71→ See `references/algorithms.md` for full implementations.
72
73## Anti-Patterns to Avoid
74
75### 1. Ignoring Visual Weight
76**What it looks like**: All images same size, random placement
77**Why it's wrong**: No focal point, viewer's eye wanders aimlessly
78**Fix**: Establish 60/30/10 hierarchy with one hero image
79
80### 2. Over-Saturating the Canvas
81**What it looks like**: Every pixel filled with image content
82**Why it's wrong**: Visual claustrophobia, no breathing room
83**Fix**: Use negative space intentionally (20-30% white space minimum)
84
85### 3. Linear FFT for Color Matching
86**What it looks like**: Poor perceptual color matches
87**Why it's wrong**: RGB is not perceptually uniform
88**Fix**: Use LAB color space for matching
89
90### 4. Seamless Hockney Joiners
91**What it looks like**: Perfectly stitched panorama
92**Why it's wrong**: Misses the entire point - multiple perspectives
93**Fix**: Embrace ±2° rotation variance, 5-15% overlap, intentional gaps
94
95### 5. Global Poisson Blending
96**What it looks like**: Entire image becomes washed out
97**Why it's wrong**: Destroys local contrast, looks fake
98**Fix**: Apply locally at seams only, preserve source gradients
99
100### 6. Reusing Mosaic Tiles
101**What it looks like**: Obvious repetition patterns in mosaic
102**Why it's wrong**: Human eye detects patterns immediately
103**Fix**: Track tile usage, penalize reuse, use larger tile library
104
105## MCP Integrations
106
107| MCP | Purpose |
108|-----|---------|
109| **Stability AI** | Generate backgrounds, textures, missing elements |
110| **Firecrawl** | Research techniques, algorithm papers, art history |
111| **WebFetch** | Fetch documentation, tutorials, design references |
112
113## Performance Targets
114
115| Operation | Mac M2 | iPhone 15 Pro |
116|-----------|--------|---------------|
117| Grid layout (20 photos) | <50ms | <100ms |
118| Photo mosaic (10k tiles) | 2s | 5s |
119| Force-directed (50 images) | 200ms | 500ms |
120| Poisson blending (512×512) | 20ms | 50ms |
121| Hockney assembly (10 photos) | 0.5s | 2s |
122
123## References
124
125→ `references/collage-types.md` - Grid, mosaic, scrapbook, magazine, social templates
126→ `references/art-historical-styles.md` - Hockney, Dadaist, Surrealist, Rauschenberg
127→ `references/algorithms.md` - Edge assembly, Poisson, optimal transport, force-directed
128→ `references/advanced-techniques.md` - Cross-photo interactions, narrative sequences
129→ `references/implementation-guide.md` - Metal shaders, Core ML, performance
130
131## Integrates With
132
133- **photo-composition-critic** - Assess individual photos before collaging
134- **color-theory-palette-harmony-expert** - Extract/match color palettes
135- **clip-aware-embeddings** - Semantic grouping of images
136- **native-app-designer** - Build collage creation UI
137- **metal-shader-expert** - GPU-accelerated blending/effects
138
139---
140
141**Remember**: Great collages tell stories through arrangement. Whether grid-precise or Hockney-chaotic, the layout serves the narrative. Master both the math and the art.
majiayu000