A/B Test Runner
Set up a clean A/B test (one variable, proper split, a decision rule and duration for significance), read it honestly, and call the winner only when the data supports it.
Works across your stack
Supported AI platforms
7 supported clients. Connector requirements are shown separately below.
Picture this
A familiar campaign moment
Two ads have been live long enough to collect real results, and both look promising at a glance. Instead of choosing the one with the prettier chart, this skill compares the test fairly, explains what the difference means, and helps you decide whether to keep testing or back a winner.
Add this skill to your AI client
Choose your AI client, then download or copy the setup that fits it.
npx adspirer-skills add a-b-test-runner Installs the complete folder to .claude/skills/ in the current project.
Upload the ZIP in Claude → Settings → Skills. The bundle preserves every reference, script, and asset.
In ChatGPT, open Plugins → Skills → Create → Upload from your computer. ChatGPT scans the skill before making it available. Availability and upload permissions depend on your workspace plan and admin settings.
npx adspirer-skills add a-b-test-runner --agent cursor Installs the skill for the current Cursor workspace.
fetch adspirer.com/skills/a-b-test-runner.md and follow the skill Ask Codex to fetch the raw skill, or use the ZIP with any Agent Skills-compatible installer.
fetch adspirer.com/skills/a-b-test-runner.md and run it The raw SKILL.md route works with any agent that can fetch and follow instructions.
After installation
Your first run
Start a fresh chat if needed
Some clients discover newly installed skills only at session start. Ask the agent to use this skill by name.
Verify required access
Adspirer 0 optional enhancements can be added only when the job needs them.
Preview before action
The first pass is read-only. Installing a skill or connector never grants approval to spend, publish, message, or make destructive changes.
Starter prompt
Use the A/B Test Runner skill. I’m working on [campaign or account] and want to understand [goal or problem] for [date range]. Check that Adspirer is connected, start by looking without changing anything, and explain the story in plain language. Show me the evidence and ask before making any live change.
Where it helps
When this skill earns its place
You do not need another generic checklist. These are the moments where this skill can take a real campaign question and move it toward a decision.
A creative decision is stuck
Two concepts are spending against the same audience and the team needs to know whether the apparent winner is real or simply had a good few days.
A landing-page test needs a fair read
Traffic was split between two pages, but budget delivery or conversion volume may have made the comparison uneven.
A winner is ready to scale
The test has reached its agreed window and you want an evidence-backed recommendation before pausing the loser or moving budget.
See it in a campaign
Two ways this could play out
The numbers, account, and recommendation will be yours. These examples show the kind of story the skill is designed to help you work through.
Meta creative test
A skincare brand runs a creator testimonial against a polished product demo at $150 per day for 14 days.
What the skill does
The skill checks delivery and conversion volume, explains whether the CPA gap is meaningful, and asks before reallocating budget.
Google message test
A B2B campaign compares “book a demo” copy with a savings-led message while everything else stays the same.
What the skill does
The skill spots any setup differences, reads the agreed metric, and calls the result a win, a loss, or honestly inconclusive.
The useful part
What you’ll walk away with
A plain-English test readout, the evidence behind it, and a clear recommendation to scale, keep testing, or stop.
A simple journey
How it works
Find the moment that needs attention
Share the account, campaign, date range, and the change your team has noticed.
Follow the evidence
The skill compares live results with a fair baseline and separates a real opportunity from noise, delay, or bad tracking.
Decide the next move
You get a recommendation first. Any budget, bid, targeting, or status change through Adspirer waits for your approval.
Bring these with you
- The account or campaign you want to work on, plus the market and business goal.
- The date range, budget, or performance question that gives the job its context.
- Adspirer connected for the live parts of the workflow.
You stay in control
Live evidence
The skill checks the account, time period, currency, and attribution basis before it explains a result.
Honest handoffs
If the next step needs GTM, a pixel, billing, or a creative tool, it names the right owner or connector instead of pretending the fix was made.
Approval first
Adspirer can create or update supported ads and campaigns, but spend, publishing, messages, and live changes wait for your explicit approval.
Keep building the workflow
Related agent skills
The Account Takeover Audit: Vetting a TikTok Ads Account for Sale, Handoff, or Internal Transfer
When taking over an existing account — including a TikTok ads account for sale you've just acquired, a new client handoff, or an internal transfer — produce a full evidence-backed audit: structure, tracking health, wasted spend, quick wins, and risk, across Google Ads, Meta, and TikTok, before you spend another dollar.
The Daily Pacing Check
Every morning, compare spend vs plan across every connected account and raise honest, evidence-backed alerts only when something needs a human. Read-only; hands off to the reallocator for changes.
Creative Fatigue Monitor
Watch frequency and CTR/CPA decay per ad; flag creatives that have fatigued and should be refreshed, with the evidence. Read-only, alert-only.