data-analyst
The Data Analyst specialist for Headout's PM OS. Engage this skill whenever a PM needs to understand existing user behavior before (or while) defining a solution. It operates in two modes: Two modes: MODE A — Question Bank: generates the behavioral questions worth answering for a given problem (what to measure, what cuts matter, what would confirm or refute the hypothesis). MODE B — Query Runner: writes and executes BQ queries, interprets results, produces a behavioral insights brief. Trigger for: "what does the data say about X", "pull some numbers on Y", "understand user behavior before writing the spec", "what should I be measuring", "build a data picture of this funnel stage", or any time a PM needs behavioral evidence before committing to a solution.
87
81%
Does it follow best practices?
Impact
98%
1.07xAverage score across 3 eval scenarios
Passed
No known issues
Evaluation results
100%
12%Checkout Funnel Question Bank for Multi-Experience Orders
Mode A question bank generation
Problem Frame used
100%
100%
Clarifying questions documented
100%
100%
Volume & Scale dimension
100%
100%
Funnel Behavior dimension
100%
100%
Segmentation Cuts dimension
100%
100%
Hypothesis Validation dimension
100%
100%
Time & Trend dimension
100%
100%
Behavioral Patterns dimension
100%
100%
Priority vs Secondary split
87%
100%
Why it matters annotations
100%
100%
Queries to write list
0%
100%
Specific not vague questions
70%
100%
Output saved to file
100%
100%
100%
6%BigQuery Analysis: App Search-to-Booking Funnel
Mode B query writing and interpretation
queries.sql file exists
100%
100%
Each query labeled
100%
100%
Clause-level comments
100%
100%
Date range default applied
100%
100%
Rates not raw counts
100%
100%
Segmentation included
100%
100%
interpretation-guide.md exists
100%
100%
Surprising result flagged
100%
100%
Actionable segment identified
100%
100%
Data limitations noted
100%
100%
Correlation caveat
25%
100%
Metric definitions explicit
100%
100%
94%
3%Behavioral Insights Brief: Repeat Booking Rate
Structured critique and insights brief
insights-brief.md format
100%
75%
Implication per finding
100%
100%
Hypothesis assessed
100%
100%
analysis-critique.md exists
100%
100%
Gap/Impact/Recommendation format
62%
100%
Survivorship bias identified
100%
100%
Correlation vs causation flagged
100%
100%
Segment size context
100%
50%
Actionability filter applied
100%
100%
Uncertainty acknowledged
100%
100%
Open Questions section
25%
100%
No smoothed contradiction
100%
100%
- Repository
- headout/pm-os-marketplace
- Commit
d8db811
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.