Skip to content
LiveNew tools this week
Submit
AIMarketly
ab-test-setup logo

ab-test-setup

Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.

techwavedev/agi-agent-kit0installs4stars

SKILL.md

Full skill instructions

A/​B Test Setup

1️⃣ Purpose & Scope

Ensure every A/​B test is valid, rigorous, and safe before a single line of code is written.

  • Prevents "peeking"
  • Enforces statistical power
  • Blocks invalid hypotheses

2️⃣ Pre-Requisites

You must have:

  • A clear user problem
  • Access to an analytics source
  • Roughly estimated traffic volume

Hypothesis Quality Checklist

A valid hypothesis includes:

  • Observation or evidence
  • Single, specific change
  • Directional expectation
  • Defined audience
  • Measurable success criteria

3️⃣ Hypothesis Lock (Hard Gate)

Before designing variants or metrics, you MUST:

  • Present the final hypothesis
  • Specify:
    • Target audience
    • Primary metric
    • Expected direction of effect
    • Minimum Detectable Effect (MDE)

Ask explicitly:

“Is this the final hypothesis we are committing to for this test?”

Do NOT proceed until confirmed.

4️⃣ Assumptions & Validity Check (Mandatory)

Explicitly list assumptions about:

  • Traffic stability
  • User independence
  • Metric reliability
  • Randomization quality
  • External factors (seasonality, campaigns, releases)

If assumptions are weak or violated:

  • Warn the user
  • Recommend delaying or redesigning the test

5️⃣ Test Type Selection

Choose the simplest valid test:

  • A/​B Test – single change, two variants
  • A/​B/​n Test – multiple variants, higher traffic required
  • Multivariate Test (MVT) – interaction effects, very high traffic
  • Split URL Test – major structural changes

Default to A/​B unless there is a clear reason otherwise.

6️⃣ Metrics Definition

Primary Metric (Mandatory)
  • Single metric used to evaluate success
  • Directly tied to the hypothesis
  • Pre-defined and frozen before launch
Secondary Metrics
  • Provide context
  • Explain why results occurred
  • Must not override the primary metric
Guardrail Metrics
  • Metrics that must not degrade
  • Used to prevent harmful wins
  • Trigger test stop if significantly negative

7️⃣ Sample Size & Duration

Define upfront:

  • Baseline rate
  • MDE
  • Significance level (typically 95%)
  • Statistical power (typically 80%)

Estimate:

  • Required sample size per variant
  • Expected test duration

Do NOT proceed without a realistic sample size estimate.

8️⃣ Execution Readiness Gate (Hard Stop)

You may proceed to implementation only if all are true:

  • Hypothesis is locked
  • Primary metric is frozen
  • Sample size is calculated
  • Test duration is defined
  • Guardrails are set
  • Tracking is verified

If any item is missing, stop and resolve it.

Running the Test

During the Test

DO:

  • Monitor technical health
  • Document external factors

DO NOT:

  • Stop early due to “good-looking” results
  • Change variants mid-test
  • Add new traffic sources
  • Redefine success criteria

Analyzing Results

Analysis Discipline

When interpreting results:

  • Do NOT generalize beyond the tested population
  • Do NOT claim causality beyond the tested change
  • Do NOT override guardrail failures
  • Separate statistical significance from business judgment

Interpretation Outcomes

ResultAction
Significant positiveConsider rollout
Significant negativeReject variant, document learning
InconclusiveConsider more traffic or bolder change
Guardrail failureDo not ship, even if primary wins

Documentation & Learning

Test Record (Mandatory)

Document:

  • Hypothesis
  • Variants
  • Metrics
  • Sample size vs achieved
  • Results
  • Decision
  • Learnings
  • Follow-up ideas

Store records in a shared, searchable location to avoid repeated failures.

Refusal Conditions (Safety)

Refuse to proceed if:

  • Baseline rate is unknown and cannot be estimated
  • Traffic is insufficient to detect the MDE
  • Primary metric is undefined
  • Multiple variables are changed without proper design
  • Hypothesis cannot be clearly stated

Explain why and recommend next steps.

Key Principles (Non-Negotiable)

  • One hypothesis per test
  • One primary metric
  • Commit before launch
  • No peeking
  • Learning over winning
  • Statistical rigor first

Final Reminder

A/​B testing is not about proving ideas right. It is about learning the truth with confidence.

If you feel tempted to rush, simplify, or “just try it” — that is the signal to slow down and re-check the design.

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

<!-- AGI-INTEGRATION-START -->

AGI Framework Integration

Adapted for @techwavedev/​agi-agent-kit Original source: antigravity-awesome-skills

Memory-First Protocol

Retrieve prior test strategies, known flaky tests, and coverage gaps. Cache test infrastructure setup to avoid re-configuring test environments.

# Check for prior testing/​QA context before starting
python3 execution/​memory_manager.py auto --query "test patterns and coverage strategies for Ab Test Setup"

Storing Results

After completing work, store testing/​QA decisions for future sessions:

python3 execution/​memory_manager.py store \
  --content "Testing strategy: integration tests hit real DB (no mocks), 85% line coverage, mutation testing on critical paths" \
  --type technical --project <project> \
  --tags ab-test-setup testing

Multi-Agent Collaboration

Share test results and coverage reports with code review agents so they can verify adequate coverage on changed code.

python3 execution/​cross_agent_context.py store \
  --agent "<your-agent>" \
  --action "QA complete — test suite expanded with 12 new integration tests, all passing" \
  --project <project>

TDD Enforcement

This skill integrates with the framework's iron-law RED-GREEN-REFACTOR cycle. No production code without a failing test first.

Agent Team: QA

Dispatch qa_team to generate tests and verify they pass before marking implementation complete.

<!-- AGI-INTEGRATION-END -->