Analyzing Data

This is a data warehouse query assistant that caches what it learns. Instead of rediscovering table schemas and query patterns every time, it maintains concept mappings (like "customer" maps to CUSTOMERS table, key column user_id) and pattern libraries for common question types. The workflow is pattern lookup first, then concept lookup, then table discovery if needed, always followed by caching learnings before presenting results. It runs queries through a persistent kernel with Polars and Pandas support, which is nice for iterative analysis without re-authenticating. The caching layer makes the most sense if you're asking similar questions repeatedly or have a team that hits the same data from different angles. Works best when you actually feed it learnings rather than treating it as a one-shot query tool.

skills.sh installs: 1.4K
GitHub stars: 459
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add astronomer/agents --skill analyzing-data --agent claude-code

Installs into .claude/skills of the current project.

Files

Data Analysis

Answer business questions by querying the data warehouse. The kernel auto-starts on first exec call.

All CLI commands below are relative to this skill's directory. Before running any scripts/cli.py command, cd to the directory containing this file.

Workflow

Pattern lookup — Check for a cached query strategy:

uv run scripts/cli.py pattern lookup "<user's question>"

If a pattern exists, follow its strategy. Record the outcome after executing:

uv run scripts/cli.py pattern record <name> --success  # or --failure

Concept lookup — Find known table mappings:

uv run scripts/cli.py concept lookup <concept>

Table discovery — If cache misses, search the codebase (Grep pattern="<concept>" glob="**/*.sql") or query INFORMATION_SCHEMA. See reference/discovery-warehouse.md.

Execute query:

uv run scripts/cli.py exec "df = run_sql('SELECT ...')"
uv run scripts/cli.py exec "print(df)"

SKILL.md on GitHub

Details

Repository: github.com/astronomer/agents
Category: Databases
First seen: Apr 16, 2026