Evaluate A/B tests for inclusive product impact across user groups, accessibility needs, device constraints, privacy behavior, bandwidth, geography, and underrepresented segments.
SkillScore86Maintained
Automatic
◆Data Analyst pack
Last verified 8/16/2026
What it changes
Passed 19 of 22 test cases with the skill, and 15 of 22 without it.
Without skill68%
With skill86%
Checks it passed that the model alone missed
The response uses the section header '## Change Under Review'.
The response includes the section header '## User Dimensions'.
The response includes the exact section header '## Balance And Impact'.
and 6 more in the full report
5 fixed14 passed either way2 still failing1 broke
Pass-rate lift
+18 pp
Tokens
+3%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 8/16/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
Our growth experiment shows potential inclusion risks caused by unequal variant exposure across low-bandwidth mobile networks in rural regions. Which related skill is best suited to set up post-assignment verification and exposure monitoring across device geographies?
What was checked, without and with the skill
Checked
Without skill
With skill
The response directs the user to reference the experiment-verification-monitoring skill.
Missed
Passed
case-07 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md75 linessingle file
Inclusive Experiment Analysis
Use this skill to make sure experiment design and readouts consider the range
of users affected by a product change. It focuses on subgroup impact,
accessibility, representation, data dimensions, and unintended harm.
Source Traceability
Primary source: Practical A/B Testing by Leemay Nassery. Guidance is
transformed and paraphrased from chapter 1 lines 719-912 and related subgroup
analysis context from lines 639-718. Metric and eligibility context comes from
chapter 2 lines 1564-1735.
Related Advanced Skills
trustworthy-experiment-insights: use when subgroup findings may be
underpowered, false positives, or false negatives.
experiment-verification-monitoring: use when inclusion risks depend on
assignment, exposure, device, geography, accessibility, or segment monitoring.
adaptive-experimentation-strategy: use cautiously when contextual bandits or
personalization could create uneven user impact across groups.
Reference Routing
Need
Read
Inclusive experiment concepts
references/core/knowledge.md
Design and analysis rules
references/core/rules.md
Segment examples
references/core/examples.md
Review workflow
workflows/review-inclusive-impact.md
Workflow
Identify which user groups could experience the change differently.
Choose dimensions that are relevant, ethical, and available.
Check test/control balance for important dimensions when possible.
Include accessibility, bandwidth, device, privacy, geography, and usage-level
concerns where relevant.
Analyze subgroup outcomes without cherry-picking.
Recommend launch, mitigation, follow-up testing, or deeper research.