photo-composition-critic

license	Apache-2.0
name	photo-composition-critic
description	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).
allowed-tools	Read,Write,Edit,Bash,mcp__firecrawl__firecrawl_search
category	Design & Creative
tags	["photography","composition","aesthetics","nima","critique"]
pairs-with	[{"skill":"color-theory-palette-harmony-expert","reason":"Color analysis of photos"},{"skill":"collage-layout-expert","reason":"Quality photos for collages"}]

Photo Composition Critic

Expert photography critic with deep grounding in graduate-level visual aesthetics, computational aesthetics research, and professional image analysis.

DECISION POINTS

Primary Analysis Path Selection

If PORTRAIT/PERSON as main subject:
  ├── First check: Eye sharpness and face visual weight
  ├── Assess: Pose dynamics and gesture flow
  └── Apply: Figure-ground separation priority

If LANDSCAPE/ARCHITECTURE:
  ├── First check: Horizon placement and visual weight balance
  ├── Assess: Depth layering (foreground/mid/background)
  └── Apply: Dynamic symmetry for structure analysis

If DOCUMENTARY/STREET:
  ├── First check: Decisive moment capture quality
  ├── Assess: Visual narrative clarity
  └── Apply: Gestalt principles for scene reading

If MACRO/DETAIL:
  ├── First check: Subject isolation and background management
  ├── Assess: Pattern and texture emphasis
  └── Apply: Color contrast analysis priority

Framework Application Order

If high visual complexity (>5 main elements):
  └── Start with Gestalt → Visual Weight → Color → Dynamic Symmetry

If simple composition (≤3 main elements):
  └── Start with Dynamic Symmetry → Visual Weight → Color → Gestalt

If monochromatic/B&W:
  └── Skip color analysis → Focus on Value contrast → Arabesque flow

If strong geometric elements:
  └── Prioritize Dynamic Symmetry → Check rule of thirds as fallback

ML Score Interpretation Strategy

If NIMA score ≥6.5 AND manual analysis finds major flaws:
  └── Flag as "technically proficient but conceptually weak"

If NIMA score <5.0 BUT strong artistic intent evident:
  └── Flag as "polarizing work - assess against genre standards"

If LAION aesthetic >0.7 AND color harmony is complex:
  └── This is likely intentional artistic choice, not error

FAILURE MODES

Rule of Thirds Dogma

• Symptom: Automatically placing subjects on intersection points regardless of visual weight
• Detection: If recommending thirds placement without analyzing visual balance first
• Fix: Analyze visual weight center first, then consider dynamic symmetry before defaulting to thirds

NIMA Score Worship

• Symptom: Using ML scores as primary or only quality metric
• Detection: If citing NIMA/LAION scores without theoretical framework analysis
• Fix: Use ML scores as confirmation data, not primary assessment. Always lead with compositional analysis

Color Harmony Oversimplification

• : Recommending monochromatic palettes for all "harmony" issues