How do I obtain a KBase token for this skill?

Log in to the KBase JupyterHub and execute 'BERDLSettings().KBASE_AUTH_TOKEN' in any notebook to copy your active token.

How often do the authentication tokens expire?

KBase tokens typically expire after approximately one week. If you encounter authorization errors, you should refresh your token via JupyterHub.

What databases are available through the KBase Query skill?

Key databases include kbase_ke_pangenome (GTDB taxonomy), nmdc_core (microbiome data), kbase_genomes, and kbase_uniprot reference data.

Do I need any local dependencies to use this skill?

The skill requires the KBASE_TOKEN environment variable and the 'jq' command-line utility to be installed on your system for processing JSON responses.

Does this skill support custom SQL queries?

Yes, you can use the kbase_query.sh script to execute custom SQL statements with a default limit of up to 1000 rows.

KBase Data Lakehouse Query

Name: KBase Data Lakehouse Query
Author: justaddcoffee

byjustaddcoffee

•

数据科学与机器学习

Enables natural language querying and exploration of biological and microbiome data within the KBase/BERDL Data Lakehouse.

The KBase Query skill provides a powerful interface for interacting with the BERDL Data Lakehouse via the Model Context Protocol (MCP). It allows researchers and developers to explore massive biological datasets—including pangenomic, genomic, and NMDC microbiome data—using SQL queries or high-level scripts directly within Claude. By automating schema discovery, table listing, and data sampling, this skill bridges the gap between complex bioinformatics databases and AI-assisted data analysis, streamlining the workflow for extracting insights from the KBase ecosystem.

主要功能

01Integrate with KBase JupyterHub authentication for secure data access.

023 GitHub stars

03Execute complex SQL queries against biological and pangenomic databases.

04Access specialized databases like NMDC core, GTDB taxonomy, and UniProt.

05Explore database structures including table listings and column schemas.

06Sample rows from large datasets with configurable result limits.

使用场景

01Performing rapid schema lookups and data sampling for bioinformatics pipeline development.

02Querying pangenomic data to analyze gene clusters and species clades.

03Exploring NMDC microbiome datasets for environmental and meta-data analysis.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add justaddcoffee/lakehouse-chat lakehouse-skills

For use in Claude.ai and ChatGPT

Download Skill