openscientist-io/openscientist/jgi-lakehouse

Claude Code and agent skill by openscientist-io/openscientist

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Skills for querying the JGI Dremio Lakehouse containing GOLD and IMG genomics databases. Use this when users want to explore JGI databases, query GOLD (Genomes OnLine Database), IMG (Integrated Microbial Genomes), or run SQL queries against JGI genomics data. Triggers on mentions of JGI, GOLD database, IMG database, genome metadata, or JGI lakehouse queries.

Install

npx vskill@latest install openscientist-io/openscientist/jgi-lakehouse

SKILL.md

JGI Lakehouse Query

Query the JGI Dremio Lakehouse via CLI.

Setup

bash
pip install linkml-store[dremio]
export DREMIO_USER="your_username"
export DREMIO_PASSWORD="your_password"

Connection

bash
# Base connection (no schema filter)
DB="dremio-rest://lakehouse.jgi.lbl.gov"
 
# GOLD database
GOLD="dremio-rest://lakehouse.jgi.lbl.gov?schema=gold-db-2 postgresql.gold"
 
# IMG Core database
IMG="dremio-rest://lakehouse.jgi.lbl.gov?schema=img-db-2 postgresql.img_core_v400"

SQL Queries

Direct SQL via --sql flag:

bash
# Query GOLD studies
linkml-store -d "$DB" query --sql 'SELECT * FROM "gold-db-2 postgresql".gold.study LIMIT 10'
 
# Count by ecosystem
linkml-store -d "$DB" query --sql 'SELECT ecosystem, COUNT(*) as cnt FROM "gold-db-2 postgresql".gold.study GROUP BY ecosystem ORDER BY cnt DESC'
 
# Join tables
linkml-store -d "$DB" query --sql 'SELECT s.study_name, p.project_name FROM "gold-db-2 postgresql".gold.study s JOIN "gold-db-2 postgresql".gold.project p ON s.study_id = p.study_id LIMIT 10'
 
# Output formats
linkml-store -d "$DB" query --sql '...' -O json
linkml-store -d "$DB" query --sql '...' -O csv
linkml-store -d "$DB" query --sql '...' -O yaml

Collection Queries

When schema is set, use collection-based queries:

bash
# List tables
linkml-store -d "$GOLD" list-collections
 
# Query collection
linkml-store -d "$GOLD" -c study query --limit 10
 
# With filter
linkml-store -d "$GOLD" -c study query -w "ecosystem=Host-associated" --limit 20
 
# Describe table
linkml-store -d "$GOLD" -c study describe

Schema Export

bash
# Export LinkML schema with FK relationships
linkml-store -d "$GOLD" schema -O yaml -o gold.linkml.yaml

Key Databases

Schema PathTablesDescription
"gold-db-2 postgresql".gold42GOLD - genome project metadata
"img-db-2 postgresql".img_core_v400244IMG Core - genes, taxa, annotations
"img-db-2 postgresql".img_ext84IMG Extended data
"img-db-2 postgresql".img_sat_v450141IMG Satellite/experimental

See references/databases.md for complete listing.

Common SQL Patterns

bash
# List schemas
linkml-store -d "$DB" query --sql 'SELECT TABLE_SCHEMA, COUNT(*) as tables FROM INFORMATION_SCHEMA."TABLES" GROUP BY TABLE_SCHEMA ORDER BY TABLE_SCHEMA'
 
# List tables in schema
linkml-store -d "$DB" query --sql 'SELECT TABLE_NAME FROM INFORMATION_SCHEMA."TABLES" WHERE TABLE_SCHEMA = '\''gold-db-2 postgresql.gold'\'' ORDER BY TABLE_NAME'
 
# Table columns
linkml-store -d "$DB" query --sql 'SELECT COLUMN_NAME, DATA_TYPE FROM INFORMATION_SCHEMA."COLUMNS" WHERE TABLE_SCHEMA = '\''gold-db-2 postgresql.gold'\'' AND TABLE_NAME = '\''study'\'' ORDER BY ORDINAL_POSITION'
 
# Row count
linkml-store -d "$DB" query --sql 'SELECT COUNT(*) FROM "gold-db-2 postgresql".gold.study'

Pre-generated Schemas

LinkML schemas with FK relationships: /Users/cjm/repos/linkml-store/jgi-lakehouse-analysis/

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
63
Repository forks
16
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/openscientist-io/openscientist/jgi-lakehouse/badge)](https://verified-skill.com/skills/openscientist-io/openscientist/jgi-lakehouse)

Something wrong with this skill or its page? Tell us.