Search community members by expertise using vector embeddings and cosine similarity.
npx skills add https://github.com/MLAI-AUS-Inc/roo --skill connect-users
Please help me install this Agent Skill. Skill: connect-users Source: https://github.com/MLAI-AUS-Inc/roo/tree/main/roo-standalone/skills/connect_users Command: npx skills add https://github.com/MLAI-AUS-Inc/roo --skill connect-users
This skill helps you quickly find and connect with members of the MLAI community who possess specific expertise or are working on relevant topics.
Find community members with expertise in AI research.
High-intent search queries and answers about installing and using this skill.
To find community members with specific expertise, this skill searches a database of user expertise embeddings using vector similarity and cosine similarity to identify and recommend matching individuals.
You need a database containing user expertise embeddings and a mechanism to perform vector similarity search to enable the expertise matching functionality.
Yes, you can search for people based on their skills, interests, and current project involvement by matching your query against the stored user expertise embeddings.
The people finder matches requested topics to user profiles by calculating cosine similarity between your search query and the vector embeddings of user expertise stored in the database.
The best way to locate an expert in machine learning operations is to query this skill, which uses vector embeddings to scan the community network and suggest relevant members with matching skills.
Search limitations depend on the completeness of your database; if user expertise embeddings lack data on highly niche skills, the vector similarity search may not yield relevant connections.
zeronx798Manage vector collections and perform similarity searches with metadata filtering.
SignmanalAutomate Yuanbao group @mentions, member lookups, and private messaging.
seo-jinseokCompare Neon, Supabase, and Firebase Firestore for cloud database selection.
cwenselSearch indexed collections with semantic and full-text queries.
