What is ab-test-design?

A planning workflow for A/B tests, which compare two versions of a paid advertisement or campaign change. It covers hypothesis writing, sample-size and duration estimates, and setup for Google Ads, Meta, and TikTok.

Use it to plan tests of ad creative, messaging, audiences, bidding, or landing pages in Spain, including success criteria and platform-specific setup.

It helps define a fair comparison and estimate how much traffic and time are needed before judging the result.

How Pauesome/Paid-Media-MCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Pauesome/Paid-Media-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Pauesome/Paid-Media-MCP/main/.claude/skills/ab-test-design/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Pauesome/Paid-Media-MCP

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pauesome/paid-media-mcp/ab-test-design/github.svg)](https://agentmods.dev/skills/pauesome/paid-media-mcp/ab-test-design)

Your own site

<a href="https://agentmods.dev/skills/pauesome/paid-media-mcp/ab-test-design"><img src="https://agentmods.dev/badge/skills/pauesome/paid-media-mcp/ab-test-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pauesome/paid-media-mcp/ab-test-design"><img src="https://agentmods.dev/badge/skills/pauesome/paid-media-mcp/ab-test-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,165 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00081	$0.01165
Opus 5.5	$0.00032	$0.00466
Sonnet 5.5	$0.00016	$0.00233
Haiku 4.5	$0.00008	$0.00117

Measured 2mo ago against content hash ba8eaf6ad238, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ab-test-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/ab-test-design/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A/B Test Design — Spain

Plans rigorous paid-ad experiments. Thresholds and sample-size lookup come from .claude/references/benchmarks-spain.md.

Required Inputs

Up-front (no mid-run prompts):

Platform (google_ads / meta_ads / tiktok_ads)
What is being tested (creative concept, hook, audience, bidding strategy, landing page, etc.)
Baseline CVR (if not known, pull from MCP using client_id + 30-day window)
Minimum Detectable Effect (MDE) — relative %
Daily traffic or click volume per variant (pull from MCP if client_id given)

Hypothesis Framework

Every test starts with a structured hypothesis. Enforce this format:

IF   we [change / action]
THEN [metric] will [increase / decrease] by [estimated %]
BECAUSE [reasoning based on prior data or insight]

Hypothesis quality checklist:

Single variable isolated
Specific metric defined (not "performance")
Effect size stated (required for sample size)
Timeframe defined
Success / failure criteria fixed before launch

Sample Size

n_per_variant = (Z_α + Z_β)² × 2 × p × (1 - p) / MDE²
Z_α = 1.96 (95% confidence)
Z_β = 0.84 (80% power)
p   = baseline conversion rate
MDE = relative detectable effect

For quick estimates, use the lookup table in benchmarks-spain.md (Testing & Statistical Significance section).

Duration

duration_days = n_per_variant / daily_traffic_per_variant

Minimum 7 days (capture weekly patterns)
Maximum 28 days (avoid seasonal drift)
Respect platform learning-phase floors: Google 7–14 d, Meta 3–7 d, TikTok 7–14 d

If the calculated duration < 7 days, still run ≥ 7 days. If > 28 days, either increase MDE, increase traffic, or skip the test.

Platform Setup

Meta Experiments

Ads Manager → Experiments (not manual duplication)
Automatic audience splitting
Budget: ≥ €75/day per variant
Duration 7–14 d; Meta auto-declares winner at 95% confidence

Google Experiments

Campaign experiments or Ad Variations
50/50 traffic split
Primary metric fixed before launch (conversions / CPA / ROAS)
Duration 14–30 d; minimum 2 weeks for bidding tests

Read the full file on GitHub · 163 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 163 lines · 81 tokens per session scan A ba8eaf6ad238

Subscribe to this mod's changes

ab-test-design is a skill published in the GitHub repository Pauesome/Paid-Media-MCP (2 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 1,165 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metrics Marketing and SEO

ab-test-design next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ab-test-designPauesome/Paid-Media-MCP	Skill	2	4mo ago	MIT	A	81	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

Paid-Media-MCP: Skill for Claude Code