Help us improve
Share bugs, ideas, or general feedback.
From berlin-events
This skill should be used when the user asks about "Berlin event websites", "where to find events in Berlin", "event sources", "Berlin art listings", "Berlin food events", "scrape Berlin events", "extract event data", or when needing to know which websites, APIs, or RSS feeds to use for Berlin event discovery. Provides a curated directory of Berlin event sources organized by extraction method with scraping strategies.
npx claudepluginhub kjgarza/marketplace-claude --plugin berlin-eventsHow this skill is triggered — by the user, by Claude, or both
Slash command
/berlin-events:event-sourcesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A curated directory of websites, APIs, and RSS feeds for discovering art and food events in Berlin. Sources are organized by extraction method reliability.
Searches and inspects public Eventfinda New Zealand event listings by location, category, or keyword from no-login website pages. Returns event URLs, venues, dates, session times, ticket badges, images, and JSON-LD detail.
Scrapes events from Instagram accounts, web aggregators, and Facebook URLs using Python CLI tools. Downloads flyer images and stores raw data in SQLite database.
Extracts structured data (tables, lists, prices) from web pages with multi-strategy fallback, pagination, monitoring, and CSV/JSON export.
Share bugs, ideas, or general feedback.
A curated directory of websites, APIs, and RSS feeds for discovering art and food events in Berlin. Sources are organized by extraction method reliability.
Sources are ranked by data extraction reliability:
Query with location=Berlin and category filters for art/food. Eventbrite and Meetup are strongest for food events. Ticketmaster covers concerts and exhibitions.
Parse XML feeds for latest entries. Berlin Art Link and ART@Berlin are best for art. Mit Vergnuegen covers food events biweekly.
Use the extract-content.js script at ${CLAUDE_PLUGIN_ROOT}/scripts/extract-content.js to extract clean text from event pages. Pass the URL as argument:
bun run ${CLAUDE_PLUGIN_ROOT}/scripts/extract-content.js "https://www.indexberlin.com/events/list/"
The script uses Mozilla's Readability library to strip navigation, ads, and boilerplate, returning only the main content.
references/sources.md - Complete source directory with URLs, RSS endpoints, API docs, language, and scraping notes for each source