CtrlK
BlogDocsLog inGet started
Tessl Logo

ab-test-setup

Plan, design, or implement an A/B test or experiment. Includes methodology, statistical significance, and metric selection.

72

1.27x
Quality

70%

Does it follow best practices?

Impact

97%

1.27x

Average score across 2 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/ab-test-setup/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

24%

Homepage Headline Test Feasibility Assessment

Low-traffic A/B test feasibility assessment with alternatives

Criteria
Without this skill
With this skill

Duration calculation

100%

100%

Four sample-size inputs acknowledged

100%

100%

60-day threshold applied

40%

100%

4-8 week maximum flag

100%

100%

Increase MDE alternative

100%

100%

Combine or redirect traffic alternative

100%

100%

Qualitative / no-test alternative

100%

100%

Lower confidence alternative

0%

100%

Sequential testing tools named

0%

100%

Underpowered test mistake identified

100%

100%

Clear recommendation

100%

100%

95%

18%

Onboarding Email Experiment Plan

A/B test plan with duration calculation and structured documentation

Criteria
Without this skill
With this skill

Hypothesis structure

41%

100%

Primary metric defined

100%

100%

Secondary metrics present

100%

100%

Guardrail metrics present

100%

100%

Duration formula applied

80%

100%

B2B minimum duration rule

62%

100%

Maximum duration guideline

100%

100%

Quick decision framework applied

87%

100%

Pre-launch checklist present

100%

100%

Template section structure

100%

100%

Product-marketing context check

0%

50%

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.