data-analyst

Clarify ambiguous business questions and execute bounded SQL queries on ClickHouse.

19|3|Updated May 17, 2026
One-click install
npx skills add https://github.com/cline/skills --skill data-analyst-cline
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analyst
Source: https://github.com/cline/skills/tree/main/skills/data-analyst
Command: npx skills add https://github.com/cline/skills --skill data-analyst-cline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of ad-hoc ClickHouse data analysis, eliminating the need for users to manually write complex SQL, resolve ambiguous metric definitions, or interpret raw query results for business questions about metrics, funnels, trends, user behavior, and revenue.

Core Features & Use Cases

  • Elicitation-first workflow: Automatically clarifies underspecified data requests to pin down exact metric definitions, populations, time windows, and filters before querying, avoiding misleading results from ambiguous assumptions.
  • Safe ClickHouse integration: Executes bounded, optimized SQL via the official clickhousectl CLI for local or ClickHouse Cloud instances, with built-in schema discovery, query safety guardrails, and secure credential handling.
  • End-to-end analysis delivery: Turns raw query results into report-ready findings, visualizations, and exportable artifacts (CSVs, charts) with full context on definitions, caveats, and reproduction steps. Use case example: A product manager asking for last month's feature adoption rates can get a clarified request, correctly calculated metric, bar chart visualization, and CSV export without writing any SQL.

Quick Start

Use the data-analyst skill to show me the 7-day retention rate for users who signed up in the last 14 days, broken down by signup platform, and export the results as a CSV.

Frequently Asked Questions about data-analyst

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run ad-hoc data analysis on ClickHouse without writing SQL?

Ad-hoc ClickHouse data analysis is automated by clarifying ambiguous metric requests and executing safe, bounded SQL queries. The tool resolves metric definitions and time windows before querying, returning report-ready findings and visualizations without manual SQL.

Can I export ClickHouse query results to CSV for dashboard reporting?

Yes, ClickHouse query results can be exported as CSV files and charts. The analysis produces exportable artifacts alongside documented metric definitions, caveats, and full query reproduction context for report delivery.

Does the data analyst tool work with both local and ClickHouse Cloud deployments?

The analyst integrates safely with both local ClickHouse and ClickHouse Cloud instances. It executes optimized SQL via the official clickhousectl CLI, featuring built-in schema discovery, query safety guardrails, and secure credential handling.

What is an elicitation-first workflow for metrics analysis?

An elicitation-first workflow automatically clarifies underspecified data requests to pin down exact metric definitions, populations, time windows, and filters before querying. This prevents misleading results from ambiguous assumptions during ad-hoc analysis.

How do I visualize user retention and feature adoption trends from ClickHouse telemetry?

User retention and feature adoption trends are visualized by querying ClickHouse telemetry data and generating report-ready charts. The analysis clarifies the exact metric definitions first, then produces bar charts and exportable artifacts.

What are the limitations of using bounded SQL for ad-hoc ClickHouse metrics?

Bounded SQL queries are constrained by built-in safety guardrails to prevent unsafe operations during ad-hoc analysis. This ensures optimized, secure execution via clickhousectl but limits unbounded or unrestricted database modifications.