Translate a fuzzy analytical question into a rigorous investigation plan. Interrogates the ask, grounds the plan in the available data dictionary, applies analytical best practices, and produces a structured brief of query specifications for a downstream query-writing skill. Plans, does not write SQL.
| Argument | Required / Default | Description |
|---|---|---|
--dataset <id> | Optional | Pre-bind one or more datasets (comma-separated). Skips dataset discovery. |
--no-schema | Optional | Work from a user-pasted schema only. Skip every narrative-mcp call. |
--brief-only | Optional | Skip interrogation prompts when the user has already framed the question precisely. Use sparingly. |
<free-text tail> | Optional | The user's analytical question. With no arguments, the skill walks the user through interrogation interactively. |
| Prompt | When to use it |
|---|---|
Why did matched-email coverage drop last month? | Turn a vague 'the numbers are down' question into a testable investigation plan. |
Is there a relationship between household_id size and match rate? | Scope a correlation analysis grounded in the available data dictionary. |
Design an analysis for our highest-value segments | Produce a structured brief of query specs before any SQL is written. |
/design-analysis --dataset 123 --brief-only why did match rate drop in March? | Skip interrogation for an already-framed question and bind dataset 123 directly. |
This skill builds on the skills listed below — each runs as a step in its workflow.
This skill calls tools from the MCP servers listed below — connect them so your agent has the tools the skill needs.