Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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
…
The line at the top of this page pins the label git:20260721.efafd9c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_4xd66qao6e2czcvh
GET https://markdownregistry.com/api/v1/resolve?ref=ghosteken/agent-harness/ab-test-setup
GET https://markdownregistry.com/api/v1/blob/2efff4de6ce3fa37bb79f1956b0d6a0e6a7011888279089d7b7ea9cdb5966883
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
ghosteken/agent-harness · archive/skills-community/2slides-ppt-generator/SKILL.md · AI-powered presentation generation via the 2slides API — create slides from text, match a reference image style…
ghosteken/agent-harness · archive/skills-community/acceptance-orchestrator/SKILL.md · Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and…
ghosteken/agent-harness · archive/skills-community/accesslint-audit/SKILL.md · Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written…
ghosteken/agent-harness · archive/skills-community/accesslint-diff/SKILL.md · Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based)…
ghosteken/agent-harness · archive/skills-community/accesslint-scan/SKILL.md · Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix…
ghosteken/agent-harness · archive/skills-community/active-directory-attacks/SKILL.md · Provide comprehensive techniques for attacking Microsoft Active Directory environments. Covers reconnaissance…
ghosteken/agent-harness · archive/skills-community/ad-creative/SKILL.md · Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when…
sickn33/agentic-awesome-skills · plugins/agentic-awesome-skills-claude/skills/ab-test-setup/SKILL.md · Use when designing an A/B or split test: define the hypothesis, control and variants, estimate sample size, verify…
leoyeai/openclaw-marketing-skills · skills/ab-test-setup/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B…
openclaudia/openclaudia-skills · skills/ab-test-setup/SKILL.md · Design, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing…
aitytech/agentkits-marketing · skills/ab-test-setup/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B…
davidpc007/openclaw-marketing-skills · skills/ab-test-setup/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B…
francostino/opencode-skills-collection · bundled-skills/ab-test-setup/SKILL.md · Use when designing an A/B or split test: define the hypothesis, control and variants, estimate sample size, verify…
aicodedecode/awesome-muse-skills · skills-imported/ab-test-setup/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B…