guided-investigation

Decompose open-ended questions into targeted sub-questions for data-driven investigations.

3|1|Updated Dec 12, 2025

Search Tags:#templates #SQL #synthesis #investigate #open-ended #data-discovery

Ready to run

npx skills add https://github.com/tilmon-engineering/claude-skills --skill guided-investigation

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: guided-investigation
Source: https://github.com/tilmon-engineering/claude-skills/tree/main/plugins/datapeeker/skills/guided-investigation
Command: npx skills add https://github.com/tilmon-engineering/claude-skills --skill guided-investigation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a repeatable framework to tackle open-ended questions by decomposing them into specific, answerable sub-questions and guiding progress through a formal five-phase workflow.

Core Features & Use Cases

Structured question decomposition: Break vague questions into 3-5 concrete sub-questions with explicit success criteria.
Data mapping and discovery guidance: Align sub-questions with available data, and document gaps and quality checks.
Systematic investigation: Execute each sub-question in sequence, recording rationale, methods, results, and observations.
Synthesis and actionable conclusions: Integrate findings into a coherent narrative and craft recommendations.

Quick Start

Begin a guided investigation by creating a dedicated analysis workspace and following the five-phase workflow to explore a broad question such as "Why is user engagement dropping in Q3?".

Frequently Asked Questions about guided-investigation

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

FAQPage Schema

How do I structure an open-ended data investigation into answerable sub-questions?▼

To structure an open-ended data investigation, decompose vague questions into 3-5 specific sub-questions with explicit success criteria, then map them to available data before executing targeted SQL queries.

What is the best way to track progress during an open-ended data discovery process?▼

The best way to track data discovery progress is using a formal five-phase workflow that records rationale, methods, and results for each sub-question, ensuring systematic investigation and preventing lost insights.

How do I synthesize SQL query results into actionable recommendations?▼

To synthesize SQL query results into actionable recommendations, integrate findings from individual sub-questions into a coherent narrative, capturing observations and data quality checks to support final conclusions.

Can I document data gaps and quality checks while investigating vague analytical questions?▼

Yes, you can document data gaps and quality checks during the data mapping phase by aligning your decomposed sub-questions with available data sources and explicitly recording missing information.

Does this guided investigation framework support custom scripts and external references?▼

Yes, the framework supports optional scripts, references, and assets for extensibility, allowing you to enforce YAML frontmatter while customizing the investigation workflow to fit specific data analysis needs.

When should I use a structured question decomposition approach for data analysis?▼

Use structured question decomposition when tackling broad, open-ended analytical problems like identifying why user engagement is dropping, ensuring your data discovery process remains trackable and produces actionable conclusions.