Photo Composition Critic
Expert photography critic with deep grounding in graduate-level visual aesthetics, computational aesthetics research, and professional image analysis.
When to Use This Skill
Use for:
- Evaluating image composition quality
- Aesthetic scoring with ML models (NIMA, LAION)
- Photo critique with actionable feedback
- Analyzing color harmony and visual balance
- Comparing multiple crop options
- Understanding photography theory
Do NOT use for:
- Generating images → use Stability AI directly
- Photo editing/retouching → use native-app-designer
- Simple image similarity → use clip-aware-embeddings
- Collage creation → use collage-layout-expert
MCP Integrations
| MCP |
Purpose |
| Firecrawl |
Research latest computational aesthetics papers |
| Hugging Face (if configured) |
Access NIMA, LAION aesthetic models |
Quick Reference
Compositional Frameworks
| Framework |
Key Points |
| Visual Weight |
Size, color warmth, isolation, intrinsic interest, position |
| Gestalt |
Proximity, similarity, continuity, closure, figure-ground |
| Dynamic Symmetry |
Root rectangles (√2, √3, φ), baroque/sinister diagonals |
| Arabesque |
S-curve, spiral, diagonal thrust - eye flow through frame |
Color Harmony Types
| Type |
Score |
Notes |
| Complementary |
0.9 |
High visual interest |
| Monochromatic |
0.85 |
Safe, cohesive |
| Triadic |
0.85 |
Balanced, vibrant |
| Analogous |
0.8 |
Natural, harmonious |
| Achromatic |
0.7 |
B&W or desaturated |
| Complex |
0.6 |
May be chaotic or intentional |
ML Model Score Interpretation
| Score Range |
Meaning |
| 7.0+ |
Exceptional (top ~1%) |
| 6.5+ |
Great (top ~5%) |
| 5.0-5.5 |
Mediocre (most images) |
| <5.0 |
Below average |
Analysis Protocol
1. FIRST IMPRESSION (2 seconds)
└── Where does the eye go? Emotional hit? Anything "off"?
2. TECHNICAL SCAN
└── Exposure, focus, noise, color, artifacts
3. COMPOSITIONAL ANALYSIS
└── Subject clarity, structure, balance, flow, depth, edges
4. AESTHETIC EVALUATION
└── Light quality, color harmony, decisive moment, story
5. CONTEXTUAL ASSESSMENT
└── Genre success, photographer intent, audience fit
6. ACTIONABLE RECOMMENDATIONS
└── Specific improvements, post-processing, alt crops
Anti-Patterns
"Just use rule of thirds"
| What it looks like |
Why it's wrong |
| Blindly placing subjects on thirds intersections |
Oversimplification ignores visual weight, gestalt, dynamic symmetry |
| Instead: Analyze visual weight center, consider multiple frameworks |
|
"Higher NIMA score = better photo"
| What it looks like |
Why it's wrong |
| Using ML score as sole quality metric |
Models trained on averages, miss artistic intent, polarizing works |
| Instead: Use ML as one input alongside theoretical analysis |
|
"Color harmony means matching colors"
| What it looks like |
Why it's wrong |
| Recommending monochromatic or matchy palettes |
Ignores Itten's contrasts, Albers' interaction effects |
| Instead: Evaluate harmony type AND contextual appropriateness |
|
Ignoring genre context
| What it looks like |
Why it's wrong |
| Applying portrait criteria to documentary |
Different genres have different quality signals |
| Instead: Assess against genre-appropriate standards |
|
Reference Files
Load these for detailed implementations:
| File |
Contents |
references/composition-theory.md |
Arnheim visual weight, Gestalt, Dynamic Symmetry, Arabesque |
references/color-theory.md |
Albers interaction, Itten's 7 contrasts, harmony detection algo |
references/ml-models.md |
AVA dataset, NIMA, LAION-Aesthetics, VisualQuality-R1 |
references/analysis-scripts.md |
PhotoCritic class, MCP server implementation |
Key Sources
Theory: Arnheim (1974), Hambidge (1926), Itten (1961), Albers (1963), Freeman (2007)
Research: AVA dataset (Murray 2012), NIMA (Talebi 2018), LAION-5B (Schuhmann 2022), Q-Instruct (Wu 2024)
1---2name: photo-composition-critic3description: Expert photography composition critic grounded in graduate-level visual aesthetics education, computational aesthetics research (AVA, NIMA, LAION-Aesthetics, VisualQuality-R1), and professional image analysis with custom tooling. Use for image quality assessment, composition analysis, aesthetic scoring, photo critique. Activate on "photo critique", "composition analysis", "image aesthetics", "NIMA", "AVA dataset", "visual quality". NOT for photo editing/retouching (use native-app-designer), generating images (use Stability AI directly), or basic image processing (use clip-aware-embeddings).4---5
6# Photo Composition Critic
7
8Expert photography critic with deep grounding in graduate-level visual aesthetics, computational aesthetics research, and professional image analysis.
9
10## When to Use This Skill
11
12**Use for:**
13- Evaluating image composition quality
14- Aesthetic scoring with ML models (NIMA, LAION)
15- Photo critique with actionable feedback
16- Analyzing color harmony and visual balance
17- Comparing multiple crop options
18- Understanding photography theory
19
20**Do NOT use for:**
21- Generating images → use **Stability AI** directly
22- Photo editing/retouching → use **native-app-designer**
23- Simple image similarity → use **clip-aware-embeddings**
24- Collage creation → use **collage-layout-expert**
25
26## MCP Integrations
27
28| MCP | Purpose |
29|-----|---------|
30| **Firecrawl** | Research latest computational aesthetics papers |
31| **Hugging Face** (if configured) | Access NIMA, LAION aesthetic models |
32
33## Quick Reference
34
35### Compositional Frameworks
36
37| Framework | Key Points |
38|-----------|------------|
39| **Visual Weight** | Size, color warmth, isolation, intrinsic interest, position |
40| **Gestalt** | Proximity, similarity, continuity, closure, figure-ground |
41| **Dynamic Symmetry** | Root rectangles (√2, √3, φ), baroque/sinister diagonals |
42| **Arabesque** | S-curve, spiral, diagonal thrust - eye flow through frame |
43
44### Color Harmony Types
45
46| Type | Score | Notes |
47|------|-------|-------|
48| Complementary | 0.9 | High visual interest |
49| Monochromatic | 0.85 | Safe, cohesive |
50| Triadic | 0.85 | Balanced, vibrant |
51| Analogous | 0.8 | Natural, harmonious |
52| Achromatic | 0.7 | B&W or desaturated |
53| Complex | 0.6 | May be chaotic or intentional |
54
55### ML Model Score Interpretation
56
57| Score Range | Meaning |
58|-------------|---------|
59| 7.0+ | Exceptional (top ~1%) |
60| 6.5+ | Great (top ~5%) |
61| 5.0-5.5 | Mediocre (most images) |
62| <5.0 | Below average |
63
64## Analysis Protocol
65
66```
671. FIRST IMPRESSION (2 seconds)
68 └── Where does the eye go? Emotional hit? Anything "off"?
69
702. TECHNICAL SCAN
71 └── Exposure, focus, noise, color, artifacts
72
733. COMPOSITIONAL ANALYSIS
74 └── Subject clarity, structure, balance, flow, depth, edges
75
764. AESTHETIC EVALUATION
77 └── Light quality, color harmony, decisive moment, story
78
795. CONTEXTUAL ASSESSMENT
80 └── Genre success, photographer intent, audience fit
81
826. ACTIONABLE RECOMMENDATIONS
83 └── Specific improvements, post-processing, alt crops
84```
85
86## Anti-Patterns
87
88### "Just use rule of thirds"
89
90| What it looks like | Why it's wrong |
91|--------------------|----------------|
92| Blindly placing subjects on thirds intersections | Oversimplification ignores visual weight, gestalt, dynamic symmetry |
93| **Instead**: Analyze visual weight center, consider multiple frameworks |
94
95### "Higher NIMA score = better photo"
96
97| What it looks like | Why it's wrong |
98|--------------------|----------------|
99| Using ML score as sole quality metric | Models trained on averages, miss artistic intent, polarizing works |
100| **Instead**: Use ML as one input alongside theoretical analysis |
101
102### "Color harmony means matching colors"
103
104| What it looks like | Why it's wrong |
105|--------------------|----------------|
106| Recommending monochromatic or matchy palettes | Ignores Itten's contrasts, Albers' interaction effects |
107| **Instead**: Evaluate harmony type AND contextual appropriateness |
108
109### Ignoring genre context
110
111| What it looks like | Why it's wrong |
112|--------------------|----------------|
113| Applying portrait criteria to documentary | Different genres have different quality signals |
114| **Instead**: Assess against genre-appropriate standards |
115
116## Reference Files
117
118Load these for detailed implementations:
119
120| File | Contents |
121|------|----------|
122| `references/composition-theory.md` | Arnheim visual weight, Gestalt, Dynamic Symmetry, Arabesque |
123| `references/color-theory.md` | Albers interaction, Itten's 7 contrasts, harmony detection algo |
124| `references/ml-models.md` | AVA dataset, NIMA, LAION-Aesthetics, VisualQuality-R1 |
125| `references/analysis-scripts.md` | PhotoCritic class, MCP server implementation |
126
127## Key Sources
128
129**Theory**: Arnheim (1974), Hambidge (1926), Itten (1961), Albers (1963), Freeman (2007)
130
131**Research**: AVA dataset (Murray 2012), NIMA (Talebi 2018), LAION-5B (Schuhmann 2022), Q-Instruct (Wu 2024)
majiayu000