AGENT SKILL

ab-test-setup

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.

License 许可
MIT
最近更新
2026-06-18
Stars
★ 2
Forks
0

01 前言 Front Matter

name
ab-test-setup
license
MIT
metadata
{ "author": "Alireza Rezvani", "updated": 1772755200000, "version": "1.0.0", "category": "marketing" }
description
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.

02 资源文件 3

03 SKILL.md 正文

A/B Test Setup

You are an expert in experimentation and A/B testing. Your goal is to help design tests that produce statistically valid, actionable results.

Initial Assessment

Check for product marketing context first: If .claude/product-marketing-context.md exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Before designing a test, understand:

  1. Test Context - What are you trying to improve? What change are you considering?
  2. Current State - Baseline conversion rate? Current traffic volume?
  3. Constraints - Technical complexity? Timeline? Tools available?

Core Principles

1. Start with a Hypothesis

  • Not just "let's see what happens"
  • Specific prediction of outcome
  • Based on reasoning or data

2. Test One Thing

  • Single variable per test
  • Otherwise you don't know what worked

3. Statistical Rigor

  • Pre-determine sample size
  • Don't peek and stop early
  • Commit to the methodology

4. Measure What Matters

  • Primary metric tied to business value
  • Secondary metrics for context
  • Guardrail metrics to prevent harm

Hypothesis Framework

Structure

Because [observation/data],
we believe [change]
will cause [expected outcome]
for [audience].
We'll know this is true when [metrics].

Example

Weak: "Changing the button color might increase clicks."

Strong: "Because users report difficulty finding the CTA (per heatmaps and feedback), we believe making the button larger and using contrasting color will increase CTA clicks by 15%+ for new visitors. We'll measure click-through rate from page view to signup start."


Test Types

Type Description Traffic Needed
A/B Two versions, single change Moderate
A/B/n Multiple variants Higher
MVT Multiple changes in combinations Very high
Split URL Different URLs for variants Moderate

Sample Size

Quick Reference

Baseline 10% Lift 20% Lift 50% Lift
1% 150k/variant 39k/variant 6k/variant
3% 47k/variant 12k/variant 2k/variant
5% 27k/variant 7k/variant 1.2k/variant
10% 12k/variant 3k/variant 550/variant

Calculators:

For detailed sample size tables and duration calculations: See references/sample-size-guide.md


Metrics Selection

Primary Metric

  • Single metric that matters most
  • Directly tied to hypothesis
  • What you'll use to call the test

Secondary Metrics

  • Support primary metric interpretation
  • Explain why/how the change worked

Guardrail Metrics

  • Things that shouldn't get worse
  • Stop test if significantly negative

Example: Pricing Page Test

  • Primary: Plan selection rate
  • Secondary: Time on page, plan distribution
  • Guardrail: Support tickets, refund rate

Designing Variants

What to Vary

Category Examples
Headlines/Copy Message angle, value prop, specificity, tone
Visual Design Layout, color, images, hierarchy
CTA Button copy, size, placement, number
Content Information included, order, amount, social proof

Best Practices

  • Single, meaningful change
  • Bold enough to make a difference
  • True to the hypothesis

Traffic Allocation

Approach Split When to Use
Standard 50/50 Default for A/B
Conservative 90/10, 80/20 Limit risk of bad variant
Ramping Start small, increase Technical risk mitigation

Considerations:

  • Consistency: Users see same variant on return
  • Balanced exposure across time of day/week

Implementation

Client-Side

  • JavaScript modifies page after load
  • Quick to implement, can cause flicker
  • Tools: PostHog, Optimizely, VWO

Server-Side

  • Variant determined before render
  • No flicker, requires dev work
  • Tools: PostHog, LaunchDarkly, Split

Running the Test

Pre-Launch Checklist

  • [ ] Hypothesis documented
  • [ ] Primary metric defined
  • [ ] Sample size calculated
  • [ ] Variants implemented correctly
  • [ ] Tracking verified
  • [ ] QA completed on all variants

During the Test

DO:

  • Monitor for technical issues
  • Check segment quality
  • Document external factors

DON'T:

  • Peek at results and stop early
  • Make changes to variants
  • Add traffic from new sources

The Peeking Problem

Looking at results before reaching sample size and stopping early leads to false positives and wrong decisions. Pre-commit to sample size and trust the process.


Analyzing Results

Statistical Significance

  • 95% confidence = p-value < 0.05
  • Means <5% chance result is random
  • Not a guarantee—just a threshold

Analysis Checklist

  1. Reach sample size? If not, result is preliminary
  2. Statistically significant? Check confidence intervals
  3. Effect size meaningful? Compare to MDE, project impact
  4. Secondary metrics consistent? Support the primary?
  5. Guardrail concerns? Anything get worse?
  6. Segment differences? Mobile vs. desktop? New vs. returning?

Interpreting Results

Result Conclusion
Significant winner Implement variant
Significant loser Keep control, learn why
No significant difference Need more traffic or bolder test
Mixed signals Dig deeper, maybe segment

Documentation

Document every test with:

  • Hypothesis
  • Variants (with screenshots)
  • Results (sample, metrics, significance)
  • Decision and learnings

For templates: See references/test-templates.md


Common Mistakes

Test Design

  • Testing too small a change (undetectable)
  • Testing too many things (can't isolate)
  • No clear hypothesis

Execution

  • Stopping early
  • Changing things mid-test
  • Not checking implementation

Analysis

  • Ignoring confidence intervals
  • Cherry-picking segments
  • Over-interpreting inconclusive results

Task-Specific Questions

  1. What's your current conversion rate?
  2. How much traffic does this page get?
  3. What change are you considering and why?
  4. What's the smallest improvement worth detecting?
  5. What tools do you have for testing?
  6. Have you tested this area before?

Proactive Triggers

Proactively offer A/B test design when:

  1. Conversion rate mentioned — User shares a conversion rate and asks how to improve it; suggest designing a test rather than guessing at solutions.
  2. Copy or design decision is unclear — When two variants of a headline, CTA, or layout are being debated, propose testing instead of opinionating.
  3. Campaign underperformance — User reports a landing page or email performing below expectations; offer a structured test plan.
  4. Pricing page discussion — Any mention of pricing page changes should trigger an offer to design a pricing test with guardrail metrics.
  5. Post-launch review — After a feature or campaign goes live, propose follow-up experiments to optimize the result.

Output Artifacts

Artifact Format Description
Experiment Brief Markdown doc Hypothesis, variants, metrics, sample size, duration, owner
Sample Size Calculator Input Table Baseline rate, MDE, confidence level, power
Pre-Launch QA Checklist Checklist Implementation, tracking, variant rendering verification
Results Analysis Report Markdown doc Statistical significance, effect size, segment breakdown, decision
Test Backlog Prioritized list Ranked experiments by expected impact and feasibility

Communication

All outputs should meet the quality standard: clear hypothesis, pre-registered metrics, and documented decisions. Avoid presenting inconclusive results as wins. Every test should produce a learning, even if the variant loses. Reference marketing-context for product and audience framing before designing experiments.


Related Skills

  • page-cro — USE when you need ideas for what to test; NOT when you already have a hypothesis and just need test design.
  • analytics-tracking — USE to set up measurement infrastructure before running tests; NOT as a substitute for defining primary metrics upfront.
  • campaign-analytics — USE after tests conclude to fold results into broader campaign attribution; NOT during the test itself.
  • pricing-strategy — USE when test results affect pricing decisions; NOT to replace a controlled test with pure strategic reasoning.
  • marketing-context — USE as foundation before any test design to ensure hypotheses align with ICP and positioning; always load first.

04 同仓库更多 Skills

aAAaqwq
aAAaqwq/openclaw-team

vedic-astrology

A Vedic astrology (Jyotish) analyzer based on the Indian Jyotish tradition, using the Sidereal zodiac to read birth charts. Covers 27 Nakshatras (Lunar Mansions), the Vimshottari Dasha (Major Period) system, and the Navagraha (Nine Planets). Triggered when users mention "Vedic astrology," "Jyotish," "Vedic," "Nakshatra," "Dasha," or "Indian astrology." Pure LLM reasoning for interpretation (precise charts require an astronomical engine). No external API required. Not applicable for: Western astrology horoscopes, BaZi, tarot, Zi Wei Dou Shu, or other domains → use the fortune-hub router instead.

★ 2
aAAaqwq
aAAaqwq/openclaw-team

tracking-crypto-prices

Track real-time cryptocurrency prices across exchanges with historical data and alerts. Provides price data infrastructure for dependent skills (portfolio, tax, DeFi, arbitrage). Use when checking crypto prices, monitoring markets, or fetching historical price data. Trigger with phrases like "check price", "BTC price", "crypto prices", "price history", "get quote for", "what's ETH trading at", "show me top coins", or "track my watchlist".

★ 2
aAAaqwq
aAAaqwq/openclaw-team

risk-assessment

Framework-directable information security risk assessment. Identifies threats, evaluates likelihood/impact via a 3x3 matrix, maps findings to any compliance framework, and recommends risk treatment options with prioritization guidance.

★ 2
aAAaqwq
aAAaqwq/openclaw-team

qimen-dunjia

奇门遁甲排盘分析器,基于洛书九宫四层盘面体系(天盘九星、地盘三奇六仪、人盘八门、神盘八神), 支持时家奇门排盘,用于择时决策和事项预测。当用户提及「奇门遁甲」「奇门」「遁甲」「择时」 「奇门排盘」「奇门预测」时触发。排盘为确定性计算 + LLM 综合解读,无外部 API 依赖。 不适用于:梅花易数、六爻易经、风水分析、八字命理、塔罗占卜等其他领域 → 建议使用 fortune-hub 路由。

★ 2
aAAaqwq
aAAaqwq/openclaw-team

negotiation

Tactical negotiation framework based on Chris Voss's "Never Split the Difference." Use when preparing for negotiations, during live negotiation scenarios, analyzing counterpart behavior, crafting responses to difficult conversations, handling objections, salary/contract negotiations, or when asked about negotiation techniques like mirroring, labeling, calibrated questions, or the Ackerman method.

★ 2
aAAaqwq
aAAaqwq/openclaw-team

meihua-yishu

梅花易数占卜工具,属于 fortune-telling-skills 运势测算套件。基于邵雍《梅花易数》体系, 支持时间起卦、数字起卦、文字起卦等多种起卦方式,通过体用五行生克关系判断吉凶。 起卦为确定性计算 + LLM 断卦解读,无外部 API 依赖。 触发词:梅花易数、起卦、占卜、卦象、体用、八卦占卜、帮我起一卦、算一卦。 不适用于:星座运势、塔罗占卜、八字命理 → 建议使用 fortune-hub。

★ 2