Ab Testing Design
A/B test design, experiment setup, variant design, and statistical analysis for designers.
Install
$ agentstack add skill-dragoon0x-everything-design-taste-ab-testing-design ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-dragoon0x-everything-design-taste-ab-testing-design) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Ab Testing Design
Experiment Design
What to Test
- High impact, easy to change: Copy, color, layout, CTA.
- Clear hypothesis: "Changing the CTA from 'Sign Up' to 'Start Free Trial' will increase conversions because it communicates zero commitment."
What Not to Test
- Preferences ("Do users prefer blue or green?").
- Everything at once (test one variable).
- Insignificant elements (button border-radius doesn't matter).
Variant Design
- Control (A) = current experience.
- Variant (B) = one change with a hypothesis.
- Don't create wildly different variants (you won't know what caused the difference).
Statistical Rigor
- Sample size calculator before starting.
- Run for full weeks (not 2 days — behavior varies by day).
- 95% confidence minimum before declaring a winner.
- Watch for novelty effects (new things get more clicks initially).
Reporting
- State the hypothesis.
- Show the numbers (conversion rate, confidence interval).
- State the winner with context.
- Document learnings for future tests.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Dragoon0x
- Source: Dragoon0x/everything-design-taste
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.