Skip to main content
Advertising

Daily Account Health Check

mx-daily-health-check

Comprehensive exception-based daily review across campaign types, objectives, and item groups, using percentile-based confidence intervals.

Run it in chat
/mixshift-ai:mx-daily-health-check <brand>

or just say run the daily health check for <brand>

Comes with the plugin, one install activates every skill. See the install flow. Needs brand setup first.

Why it exists

Every morning someone has to log in and eyeball spend and ACoS across every campaign type, objective, and item group to catch the one thing that broke overnight. It is slow, easy to skim past, and the exception that matters hides in the noise.

What you get

One report that flags only the moves breaching the brand’s own confidence intervals, ranked by revenue impact, so you open the accounts that actually need you and leave the quiet ones alone.

What your agent can do

  • 01

    Surface spend and ACoS anomalies that breach percentile-based confidence intervals

  • 02

    Break results into campaign-type, objective, and item-group cuts

  • 03

    Rank exceptions by revenue impact so you triage the right accounts first

  • 04

    Output a structured morning report your agent can paste into client comms

StatusLive
CategoryAdvertising
Brand contextRequired
Hosts
Claude CoworkClaude CodeMixShift CLI
Get the plugin

New or existing MixShift customer, both paths start here.

Talk to us

Before you run

Requires brand setup

This skill reads a brand’s context to calibrate its output. Build it once per brand, then every teammate runs on the same shared context.

/mixshift-ai:mx-brand-context <brand>How brand setup works →
What it reads from your brand context
  • ACoS targets and anomaly confidence intervals: the thresholds every move is measured against
  • Campaign-structure and item-group mapping: how the results are cut
  • Seller Central vs Vendor Central account type: selects the data path
Gets sharper over time

As targets get calibrated and your team logs events like promotions, stockouts, and price tests on the brand timeline, the check stops flagging moves it can now explain and tightens its thresholds as history builds, so you get fewer false alarms and faster triage.