Agent skill · research science · erichowens
event-detection-temporal-intelligence-expert
Expert in temporal event detection, spatio-temporal clustering (ST-DBSCAN), and photo context understanding. Use for detecting photo events, clustering by time/location, shareability prediction,
Why this skill is useful
Adds advanced algorithms and executable scripts for spatio-temporal clustering and event significance scoring that are not widely known.
What it needs
Requires bash, grep installed locally. About 5k tokens when loaded. Last updated 2026-07-14. 180 stars on the source repository.
What this skill does
Event Detection & Temporal Intelligence Expert Expert in detecting meaningful events from photo collections using spatio-temporal clustering, significance scoring, and intelligent photo selection for collages. When to Use This Skill ✅ Use for: Detecting events from photo timestamps + GPS coordinates Clustering photos by time, location, and visual content (ST-DBSCAN, DeepDBSCAN) Scoring event significance (birthday > commute) Predicting photo shareability for social media Recognizing life events (graduations, weddings, births, moves) Temporal diversity optimization (avoid all photos from one day) Event-aware collage photo selection ❌ NOT for: Individual photo aesthetic quality → photo-composition-critic Color palette analysis → color-theory-palette-harmony-expert Face clustering/recognition → photo-content-recognition-curation-expert CLIP embedding generation → clip-aware-embeddings Single-photo timestamp extraction (basic EXIF parsing) Quick Decision Tree Core Concepts 1. ST-DBSCAN: Spatio-Temporal Clustering The Problem: Standard clustering fails for photos—same location on different days shouldn't be grouped. Key Insight: 100 meters apart in same hour = same event. 100 meters apart 3 days later = different events. ST-DBSCAN Parameters: Algorithm: Both spatial AND temporal constraints must be satisfied: → Deep dive: references/st-dbscan-implementation.md 2. DeepDBSCAN: Adding Visual Content Problem: Photos at same time/place can be different subjects (ceremony vs empty chairs). Solution: Add CLIP embeddings as third dimension: epsvisual: 0.3 (similar subjects) → 0.5 (diverse event content) 3. Hierarchical Event Detection Use case: "Paris Vacation" contains "Day 1: Louvre", "Day 2: Eiffel Tower" Approach: Cascade ST-DBSCAN with expanding thresholds: 1. High-level (vacations): epsspatial=50km, epstemporal=72hr 2. Mid-level (daily): epsspatial=5km, epstemporal=12hr 3. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills erichowens/event-detection-temporal-intelligence-expert