A/B Test Setup
Gated checklist that blocks invalid A/B tests before any code is written
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 18, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 30, 2026 · a5f0881
⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 18, 2026; it's queued for a re-test.
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 18, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Asked both to set up a signup-button color test: the baseline gave loose 'pick a metric and check significance' advice, while the skill forced an MDE and sample-size estimate (exposing that a tiny color effect needs large traffic) and ran a five-step tracking-verification checklist plus explicit refusal conditions the baseline skipped. It is a single self-contained SKILL.md with no bundled scripts; the trailing generic 'When to Use / Limitations' boilerplate adds nothing.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 4/5
What A/B Test Setup does
Walks an A/B test through hard gates for hypothesis, metrics, sample size, and execution readiness, refusing to proceed when a design is underpowered or a metric is undefined. Includes a concrete tracking-verification checklist (event firing, variant attribution, de-duplication, randomization audit) and no-peeking discipline. Triggers when you want to set up, design, or validate an experiment.
How to install A/B Test Setup
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger A/B Test Setup
-
/ab-test-setupGated checklist that blocks invalid A/B tests before any code is written
It also activates on plain-language prompts like these:
-
Help me set up an A/B test changing my signup button from blue to green. -
I want to test two versions of my landing page, walk me through it. -
Run an experiment on my checkout flow, make sure it's statistically valid.
Frequently asked questions
- Is the A/B Test Setup skill free?
- Yes. The skill itself is free from sickn33/agentic-awesome-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does A/B Test Setup work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 18, 2026. Verdict: Tested · Works. Asked both to set up a signup-button color test: the baseline gave loose 'pick a metric and check significance' advice, while the skill forced an MDE and sample-size estimate (exposing that a tiny color effect needs large traffic) and ran a five-step tracking-verification checklist plus explicit refusal conditions the baseline skipped. It is a single self-contained SKILL.md with no bundled scripts; the trailing generic 'When to Use / Limitations' boilerplate adds nothing.
- What is the A/B Test Setup SkillProof Score?
- 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
- How do I install A/B Test Setup?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use A/B Test Setup with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.