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).4license: Apache-2.05---6
7# Collage & Layout Composition Expert
8
9Expert in **ALL forms of computational collage composition** - from Instagram grids to Hockney joiners, from magazine layouts to generative art.
10
11## When to Use This Skill
12
13✅ **Use for:**
14- **Grid Collages**: Instagram profiles, regular layouts, tiled compositions
15- **Photo Mosaics**: Small images forming larger pictures
16- **Hockney-Style Joiners**: Multi-perspective photographic assemblies
17- **Scrapbook/Journal**: Mixed media with text, frames, embellishments
18- **Magazine/Editorial**: Professional layouts with text integration
19- **Vision/Mood Boards**: Inspiration collections, design references
20- **Memory Walls**: Scattered Polaroid-style arrangements
21- **Social Media**: Stories, carousel previews, profile grids
22- **Abstract/Generative**: Algorithmic and procedural arrangements
23- **Art-Historical**: Dadaist, Surrealist, Pop Art styles
24
25❌ **Do NOT use for:**
26- Simple image editing → **native-app-designer**
27- Generating new images → **Stability AI**
28- Single photo quality → **photo-composition-critic**
29- Image similarity search → **clip-aware-embeddings**
30- Color palette extraction → **color-theory-palette-harmony-expert**
31
32## Expert vs Novice Shibboleths
33
34| Topic | Novice | Expert |
35|-------|--------|--------|
36| **Layout** | "Just arrange randomly" | Visual weight, balance, golden ratio |
37| **Blending** | Hard edges or simple feather | Poisson blending preserves gradients |
38| **Color** | "Match colors manually" | Optimal transport; LAB space advantages |
39| **Composition** | Fills all space | Negative space as design element |
40| **Scale** | Same size for everything | Varies scale for hierarchy |
41| **Mosaic** | "More tiles = better" | Tile size vs. recognition tradeoff |
42| **Hockney** | "Stitch seamlessly" | Imperfection IS the technique |
43
44## Decision Tree: Choosing a Style
45
46**What's the purpose?**
47- Systematic display → **Grid Collage**
48- Artistic portrait from photos → **Photo Mosaic**
49- Personal memories → **Scrapbook** or **Memory Wall**
50- Design inspiration → **Mood Board**
51- Professional/publication → **Magazine Layout**
52- Social media → **Social Templates**
53- Art project → **Hockney/Dadaist/Surrealist**
54
55**What's the vibe?**
56- Clean, modern → Grid with tight gutters
57- Nostalgic, warm → Polaroid scatter, vintage frames
58- Edgy, disruptive → Dadaist sharp cuts
59- Dreamy, surreal → Seamless Poisson blending
60- Cubist, intellectual → Hockney joiners
61
62## Core Algorithms (Summary)
63
64| Algorithm | Use Case | Performance |
65|-----------|----------|-------------|
66| **Edge-Based Assembly** | Hockney joiners | 0.5s for 10 photos |
67| **Poisson Blending** | Seamless transitions | 20ms (512×512) |
68| **Optimal Transport** | Color harmonization | Real-time w/ affine approx |
69| **Force-Directed** | Organic scatter | 200ms (50 images) |
70| **K-d Tree Matching** | Photo mosaic tiles | 2s for 10k tiles |
71
72→ See `references/algorithms.md` for full implementations.
73
74## Anti-Patterns to Avoid
75
76### 1. Ignoring Visual Weight
77**What it looks like**: All images same size, random placement
78**Why it's wrong**: No focal point, viewer's eye wanders aimlessly
79**Fix**: Establish 60/30/10 hierarchy with one hero image
80
81### 2. Over-Saturating the Canvas
82**What it looks like**: Every pixel filled with image content
83**Why it's wrong**: Visual claustrophobia, no breathing room
84**Fix**: Use negative space intentionally (20-30% white space minimum)
85
86### 3. Linear FFT for Color Matching
87**What it looks like**: Poor perceptual color matches
88**Why it's wrong**: RGB is not perceptually uniform
89**Fix**: Use LAB color space for matching
90
91### 4. Seamless Hockney Joiners
92**What it looks like**: Perfectly stitched panorama
93**Why it's wrong**: Misses the entire point - multiple perspectives
94**Fix**: Embrace ±2° rotation variance, 5-15% overlap, intentional gaps
95
96### 5. Global Poisson Blending
97**What it looks like**: Entire image becomes washed out
98**Why it's wrong**: Destroys local contrast, looks fake
99**Fix**: Apply locally at seams only, preserve source gradients
100
101### 6. Reusing Mosaic Tiles
102**What it looks like**: Obvious repetition patterns in mosaic
103**Why it's wrong**: Human eye detects patterns immediately
104**Fix**: Track tile usage, penalize reuse, use larger tile library
105
106## MCP Integrations
107
108| MCP | Purpose |
109|-----|---------|
110| **Stability AI** | Generate backgrounds, textures, missing elements |
111| **Firecrawl** | Research techniques, algorithm papers, art history |
112| **WebFetch** | Fetch documentation, tutorials, design references |
113
114## Performance Targets
115
116| Operation | Mac M2 | iPhone 15 Pro |
117|-----------|--------|---------------|
118| Grid layout (20 photos) | <50ms | <100ms |
119| Photo mosaic (10k tiles) | 2s | 5s |
120| Force-directed (50 images) | 200ms | 500ms |
121| Poisson blending (512×512) | 20ms | 50ms |
122| Hockney assembly (10 photos) | 0.5s | 2s |
123
124## References
125
126→ `references/collage-types.md` - Grid, mosaic, scrapbook, magazine, social templates
127→ `references/art-historical-styles.md` - Hockney, Dadaist, Surrealist, Rauschenberg
128→ `references/algorithms.md` - Edge assembly, Poisson, optimal transport, force-directed
129→ `references/advanced-techniques.md` - Cross-photo interactions, narrative sequences
130→ `references/implementation-guide.md` - Metal shaders, Core ML, performance
131
132## Integrates With
133
134- **photo-composition-critic** - Assess individual photos before collaging
135- **color-theory-palette-harmony-expert** - Extract/match color palettes
136- **clip-aware-embeddings** - Semantic grouping of images
137- **native-app-designer** - Build collage creation UI
138- **metal-shader-expert** - GPU-accelerated blending/effects
139
140---
141
142**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.
curiositech