ab-test-setup
Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.
66
47%
Does it follow best practices?
Impact
100%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/ab-test-setup/SKILL.mdEvaluation results
100%
Onboarding Completion Test Plan
Full A/B test design document
Hypothesis: observation
100%
100%
Hypothesis: single change
100%
100%
Hypothesis: directional expectation
100%
100%
Hypothesis: defined audience
100%
100%
Hypothesis: MDE specified
100%
100%
Test type A/B
100%
100%
Single primary metric
100%
100%
Guardrail metrics defined
100%
100%
Significance level 95%
100%
100%
Statistical power 80%
100%
100%
Sample size per variant
100%
100%
Assumptions listed
100%
100%
Execution readiness checklist
100%
100%
No implementation steps
100%
100%
100%
2%Checkout Flow Test — Results Review
Test results analysis and record
No-ship recommendation
100%
100%
Guardrail failure cited
100%
100%
Record: hypothesis
100%
100%
Record: variants
100%
100%
Record: metrics
100%
100%
Record: sample size vs achieved
100%
100%
Record: results
100%
100%
Record: decision
100%
100%
Record: learnings
66%
100%
Record: follow-up ideas
100%
100%
No over-generalization
100%
100%
Stat vs business separated
100%
100%
External factors documented
100%
100%
100%
1%Growth Team Test Proposal Assessment
Refusal conditions and design flaw identification
Refuses to proceed
100%
100%
Multiple variables flagged
100%
100%
Unknown baseline flagged
100%
100%
Traffic insufficiency flagged
100%
100%
Undefined primary metric flagged
100%
100%
Peeking risk flagged
100%
100%
Hypothesis quality issues
87%
100%
Next steps recommended
100%
100%
Single test recommendation
100%
100%
No false approval
100%
100%
- Repository
- duclm1x1/Dive-Ai
- Commit
20ba150
- 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.