malloy-analyze

Analysis with Malloy

This skill covers two workflows:

• EDA exploration (Steps 1-6): iteratively query data, build hypotheses, validate findings
• View/dashboard building: create views, dashboards, notebooks from an existing model

Tool names are written bare here - get_context, execute_query, search_malloy_docs. The exact prefixed name depends on the host surface; match each against the tools you actually have.

To formalize analysis into a polished semantic model, hand off to the modeling skill's "Starting from Analysis" workflow (skill:malloy-model).

Prerequisites

• The Malloy MCP tools must be configured (get_context, execute_query, search_malloy_docs). If they are not available, STOP and ensure your host's MCP server is connected.
• Call search_malloy_docs liberally: it has powerful analysis patterns (window functions, cohorts, percent-of-total, nested drill-downs).

EDA WORKFLOW

ORIENT → PROFILE → HYPOTHESIZE → INVESTIGATE → VALIDATE → SYNTHESIZE
                     (user)                      (user)     (user)

Adaptive Checkpoints

The 6-step structure is a framework, not a rigid script.

Situation	Adaptation
User has a clear hypothesis ("what's driving churn?")	Skip HYPOTHESIZE, jump to INVESTIGATE on their question
Open-ended ("what's interesting?")	Follow all steps. PROFILE and HYPOTHESIZE are essential
User wants you to just go ("explore and show me")	Compress checkpoints, present findings at SYNTHESIZE

Step 1: ORIENT: Understand the Data

1. Ground yourself with get_context. It returns the package's sources, views, and fields (with their docs), so this is where you learn what data exists.
2. Note the source names, the connection they sit on, and the key tables/fields they expose.
3. Inspect the existing dimensions, measures, and views the model already defines, then query the data to confirm shape and values.
4. Create a working analysis file (this grows throughout the session):

   source: main_table is conn.table('schema.table') extend { primary_key: pk }