lamindb

What it does

This skill enables AI agents to interact with LaminDB, a Python-based data management system designed for organizing and querying biological datasets. It allows agents to create tables, manage metadata, and execute queries directly within the LaminDB environment to streamline data analysis workflows.

When to use it

• Organizing experimental data: Structure complex biological datasets by creating new tables with specific columns for samples, conditions, and measurements.
• Retrieving specific records: Query existing databases to filter and extract subsets of data based on defined criteria without writing manual scripts.
• Automating data validation: Use the database interface to check for missing metadata or inconsistencies before proceeding with downstream analysis.
• Integrating with LaminDB workflows: Connect AI agents to existing LaminDB instances to ensure consistent access to curated research data.

Key capabilities

• Create and manage tables within a LaminDB instance
• Define schema structures including columns and data types
• Execute SQL-like queries to retrieve filtered datasets
• Handle metadata associated with biological samples and experiments

Example prompts

• "Create a new table in my LaminDB instance to store RNA-seq sample metadata with columns for sample_id, condition, and batch."
• "Query the 'samples' table to find all entries where the condition is 'treated' and the batch size exceeds 100."
• "Update the metadata for specific samples in the database to reflect a new sequencing run date."

Tips & gotchas

Ensure you have an active LaminDB instance running locally or on a server before attempting to connect. The skill relies on the underlying Python library, so compatibility with your environment's Python version and dependencies is critical for successful operation.