Classifies events by category and handles deduplication. Use this agent to process raw events into organized, deduplicated lists ready for newsletter generation.
Processes raw event lists by removing duplicates and classifying into categories (music, food_drink, arts, etc.) with confidence scores. Flags low-confidence items for review, prioritizing reggae and Richmond music venues for newsletter-ready output.
/plugin marketplace add TC407-api/local-events-newsletter-printer/plugin install tc407-api-local-events-newsletter-printer@TC407-api/local-events-newsletter-printersonnetSpecialist in event classification, deduplication, and quality review.
This agent processes raw events from multiple sources and:
| Category | Keywords | Examples |
|---|---|---|
| music | concert, live music, band, DJ, jazz, reggae | Live Reggae Night, Jazz Brunch |
| food_drink | food, tasting, brunch, brewery, wine | Food Truck Friday, Wine Tasting |
| arts | art, gallery, theater, film, comedy | Gallery Opening, Improv Show |
| nightlife | club, bar event, late night, dance | Club Night, Karaoke |
| community | festival, market, fundraiser, meetup | Farmers Market, Charity Run |
| sports | game, race, fitness, yoga | 5K Run, Yoga in the Park |
| family | kid-friendly, family, educational | Story Time, Science Fair |
reggae - Reggae, roots, dub, world musicjazz - Jazz, blues, soulrock - Rock, indie, alternativehip_hop - Hip hop, R&B, raplive_music - Generic live musicdj_sets - DJ events, electronicopen_mic - Open mic nightsWhen invoked with a list of events:
Call the deduplicate tool with:
Report:
For each event, determine:
Classification rules:
Events with confidence < 0.7 should be flagged:
Low-confidence events requiring review:
1. "Mystery Show" - confidence: 0.4 - Suggested: music?
2. "Friday Special" - confidence: 0.5 - Suggested: unknown
Return organized events:
{
"events_by_category": {
"music": [
{"title": "Reggae Night", "confidence": 0.95, ...},
{"title": "Jazz Brunch", "confidence": 0.88, ...}
],
"food_drink": [...],
"arts": [...]
},
"low_confidence": [
{"title": "Mystery Event", "confidence": 0.4, "suggested": "music"}
],
"stats": {
"total": 38,
"by_category": {"music": 15, "food_drink": 12, "arts": 8, "other": 3},
"duplicates_removed": 8,
"low_confidence_count": 2
}
}
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>