Event Detection Temporal Intelligence Expert

What it does

When your agent uses it

• Detecting photo events
• Clustering by time/location
• Shareability prediction
• Place recognition

Example prompts

• “event detection”
• “temporal clustering”
• “ST-DBSCAN”
• “/event-detection-temporal-intelligence-expert”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob, mcp__firecrawl__firecrawl_search, WebFetch

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1ST-DBSCAN: Spatio-Temporal Clustering
2. 2DeepDBSCAN: Adding Visual Content
3. 3Hierarchical Event Detection

What it can do on your machine

Read from SKILL.md and the folder at commit 6713fc7. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash
  • Grep
  • Glob
  • mcp__firecrawl__firecrawl_search
  • WebFetch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Event Detection Temporal Intelligence Expert loads about 2.6k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 189 tokens; SKILL.md has 814 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~189

When it runs · the whole SKILL.md, loaded when a task matches

~2.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Bash, Grep, Glob, mcp__firecrawl__firecrawl_search, WebFetch

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from curiositech/some_claude_skills at commit 6713fc7, republished under its MIT licence (© curiositech). 814 words, ~2,634 tokens.

name

event-detection-temporal-intelligence-expert

description

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, place recognition, event significance scoring, and life event detection. Activate on 'event detection', 'temporal clustering', 'ST-DBSCAN', 'spatio-temporal', 'shareability prediction', 'place recognition', 'life events', 'photo events', 'temporal diversity'. NOT for individual photo aesthetic quality (use photo-composition-critic), color palette analysis (use color-theory-palette-harmony-expert), face recognition implementation (use photo-content-recognition-curation-expert), or basic EXIF timestamp extraction.

allowed-tools

Read, Write, Edit, Bash, Grep, Glob, mcp__firecrawl__firecrawl_search, WebFetch

metadata.category

AI & Machine Learning

metadata.tags

temporal, clustering, events, spatio-temporal, photo-context

Need to group photos into meaningful events?
├─ Have GPS + timestamps? ──────────────────── ST-DBSCAN
│   ├─ Also need visual similarity? ────────── DeepDBSCAN (add CLIP)
│   └─ Need hierarchical events? ───────────── Multi-level cascading
│
├─ No GPS, only timestamps? ────────────────── Temporal binning
│   └─ With visual content? ─────────────────── CLIP + temporal
│
└─ Photos have faces + want groups? ─────────── Face clustering first
    └─ Then event detection per person

ε_spatial:   50m (indoor) → 500m (outdoor festival) → 5km (city tour)
ε_temporal:  1hr (short event) → 8hr (day trip) → 24hr (multi-day)
min_pts:     3 (small gathering) → 10 (large event)

Neighbor(p) = {q | distance(p,q) ≤ ε_spatial AND |time(p)-time(q)| ≤ ε_temporal}

Neighbor(p) = {q | spatial_ok AND temporal_ok AND cosine_sim(clip_p, clip_q) > threshold}

MMR(photo) = λ × quality + (1-λ) × min_temporal_distance_to_selected

clusters = KMeans(n_clusters=10).fit(timestamps)  # WRONG

distance = sqrt((lat2-lat1)**2 + (lon2-lon1)**2)  # WRONG

from geopy.distance import geodesic
distance_meters = geodesic((lat1, lon1), (lat2, lon2)).meters

features['event_significance'] = photo.event.significance_score

from event_detection import EventDetectionPipeline

pipeline = EventDetectionPipeline()

# Process photo corpus
results = pipeline.process_photo_corpus(photos)

# Access events
for event in results['events']:
    print(f"{event.label}: {len(event.photos)} photos, significance={event.significance_score:.2f}")

# Access life events
for life_event in results['life_events']:
    print(f"{life_event.type} detected on {life_event.timestamp}")

# Select for collage with diversity
collage_photos = pipeline.select_for_collage(results, target_count=100)

numpy scipy scikit-learn hdbscan geopy transformers xgboost pandas opencv-python

© curiositech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in .claude/skills/event-detection-temporal-intelligence-expert of curiositech/some_claude_skills.

• SKILL.md
• .claude-plugin/plugin.json
• CHANGELOG.md
• references/event-scoring-shareability.md
• references/place-recognition-life-events.md
• references/st-dbscan-implementation.md
• references/temporal-diversity-pipeline.md

Open the folder on GitHubat commit 6713fc7