UI Skill: Visualizing, Ranking, Filtering, and Annotating Vector Databases

This skill provides guidelines and templates for building a lightweight web UI to visualize, rank, filter, and annotate vector databases. The databases contain vector embeddings computed from raw inputs (e.g., audio segments, camera trap images, or text segments), where each row corresponds to one embedding.

[!CAUTION] DATABASE SAFETY AND INTEGRITY: Do NOT write, modify, or insert test annotations directly into the user's production databases. If you need to test database operations (such as saving annotations or training models), you MUST copy the database to a temporary location (e.g., inside the conversation scratch directory) and test against the copy. Never leave testing data in production databases.

The skill's output is generic, implementing common features and leaving specific implementation details (like media rendering or custom inference models) to downstream skills (e.g., bioacoustics, camera traps).

UI Architecture