social-media-content-aggregation

Automated link harvesting extracts URLs from Discord, Telegram, and Slack using regex, classifies topics with an LLM, and saves the deduplicated articles directly to your Obsidian vault. You can run it as a scheduled daemon to persistently aggregate social media content into your knowledge base.

Yes, you need Python 3 and curl installed to execute the polling scripts and perform the social media content aggregation. You must also configure environment variables for API access and credentials before the classification and link harvesting process can run.

LLM classification identifies topics from extracted URLs, while SHA256 hashing handles deduplication to prevent duplicate links in your vault. Keyword matching serves as a fallback mechanism if LLM classification fails, ensuring consistent content categorization.

Yes, this Skill is ideal for building a persistent, scheduled daemon that polls multiple social media platforms for content. It automates credential setup, URL extraction, topic classification, and saves the aggregated links directly to an Obsidian vault.

The best way is to use a script that polls social media platforms, extracts URLs via regex, and utilizes LLM classification for topic identification before saving. It ensures articles are deduplicated using SHA256 and formatted correctly for your Obsidian vault.