Meta Ads A/B Test

/loop 1d Start the "Meta Ads A/B Test" loop.

Goal: underperforming variants are paused and winning creatives scale within budget
Max iterations: 20
Between iterations run: Review CTR, CPA, and spend by variant for Facebook and Instagram
Exit when: launch meets target CPA or max test cycles complete with a documented winner

Step 1: Pull performance, pause losers, draft new variants for approval, and report winners.

## Before you start

Connect plugins:
- Meta Ads (required) — Read Facebook/Instagram campaign, spend, variant, and creative performance.
- Google Analytics (required) — Read traffic, conversion, product, or campaign performance signals.
- Slack (required) — Post summaries, approvals, blockers, and handoff updates.
- Figma (required) — Inspect designs, dimensions, assets, and handoff notes.
- Browser / Web access (required) — Open pages, inspect live state, collect evidence, and verify changes.

Attach skills:
- Loop runner (required) — Self-pace iterations, run the check between passes, and stop only on the exit condition.
- Approval workflows (optional) — Keep outbound actions in draft or approval states when risk is non-trivial.
- Growth operations (optional) — Evaluate campaign performance, creative tests, CPA, and launch readiness.
- Visual design QA (optional) — Compare implementation against visual expectations and capture regressions.
- Browser QA (optional) — Exercise product flows, capture visual evidence, and verify fixes in-browser.

Self-pace this loop. After each iteration, run the check command, read the output, and only continue if the exit condition is not met. Stop when the exit condition passes or max iterations is reached. Give a short status update each pass.