{
 "schema": "aiblocks-page/1",
 "id": "meta-ads-weekly-account-keeper",
 "type": "agent",
 "name": "Meta Ads weekly account reviewer",
 "summary": "Compare Meta Ads with store results and costs. Investigate drops and get a ranked change list before raising spend.",
 "headline": "Meta Ads weekly account reviewer",
 "subhead": "Share two weeks of Meta exports, matching store totals and your costs. It compares results, investigates weak steps and checks how reported ad returns fit the wider business. You get changes to approve and the numbers to watch. Missing store totals or a weak trust check blocks a budget increase.",
 "job": {
  "id": "launch-and-scale-ads",
  "name": "Launch and scale Meta and TikTok ads"
 },
 "level": "intermediate",
 "thinking": "high",
 "tested": true,
 "updated": "2026-10-28",
 "first_published": "2026-10-21",
 "inputs": [
  {
   "type": "performance_sheet",
   "required": true,
   "label": "Performance sheet",
   "what": "ad or store performance export for a closed date window, with definitions"
  },
  {
   "type": "product_data",
   "required": true,
   "label": "Product data",
   "what": "one product's facts: price, variants, ingredients or materials, how it is used, photos by job"
  },
  {
   "type": "brand_brain",
   "required": false,
   "label": "Brand brain",
   "what": "the brand's facts, voice, products, offers (with effective dates), claims register, personas and look"
  }
 ],
 "outputs": [
  {
   "type": "audit_report",
   "required": true,
   "label": "Audit report",
   "what": "findings with evidence, severity, missing inputs and next actions"
  },
  {
   "type": "plan",
   "required": true,
   "label": "Plan",
   "what": "a dated plan: what to do, in what order, with a decision rule for each step"
  }
 ],
 "you_give": [
  "Meta results for this week and last week, at campaign, ad set and ad level, with spend, purchases, purchase value and frequency",
  "Your store totals for the same dates, with new-customer revenue",
  "Your order value, product cost, shipping, fees and margin, the first time",
  "Cash free for ads and stock levels (advised)",
  "What changed this week, such as a sale or a new offer (optional)"
 ],
 "you_get": [
  "This week against last week and against break-even, with the sums",
  "The link that broke, if results fell, and what to check",
  "How far to trust Meta's ROAS, as a score out of 100",
  "One ranked list of changes to approve, each with its size and reason",
  "A raise, hold or cut call on spend, with the numbers behind it",
  "A check on whether last week's changes worked"
 ],
 "use_when": [
  "You run Meta ads for your store and want the weekly checks done the same way every Monday.",
  "Results dropped and you want to know which part broke before you change anything.",
  "Meta says your ROAS is great but your bank balance does not agree.",
  "You want to raise spend, but only when your own numbers say it is safe."
 ],
 "skip_when": [
  "You run fewer than a few sales a day: the weekly numbers swing too much, so use a monthly view of your results instead.",
  "You only want to know your break-even ROAS once: use a break-even calculator or a simple sum of margin and order value.",
  "You want an agent to change your account on its own: this one never does, so ask a person on your team to make the approved changes."
 ],
 "output_sample": {
  "input": [
   "This week's and last week's Meta exports, by campaign, ad set and ad",
   "Your store totals for the same dates, with new-customer revenue",
   "Your order value, product cost, shipping, fees and returns (first run)",
   "Cash available for ads and stock levels (advised)",
   "What changed this week, such as a sale or new offer (optional)"
  ],
  "prerequisites": [
   "An AI that can read your export files, such as Claude Code",
   "Last week's memory file, if this is not your first run"
  ],
  "output": [
   {
    "name": "This week",
    "contains": "Spend, purchases, 7-day click ROAS and cost per sale against last week and break-even, with a trust score."
   },
   {
    "name": "Path taken",
    "contains": "Whether it ran a drop analysis, a delivery check, a scale check or a routine week, and why."
   },
   {
    "name": "Changes to approve",
    "contains": "A ranked list of changes, each with where, size, the step that proposed it and the reason."
   },
   {
    "name": "Scale call",
    "contains": "A raise, hold or cut call on spend, with blended ROAS and 30-day cash behind it."
   },
   {
    "name": "Last week's changes",
    "contains": "Whether each change you approved last week worked, too early to tell, or did not work."
   },
   {
    "name": "Watch next week",
    "contains": "The one to three numbers that decide next week's path."
   },
   {
    "name": "Files and missing",
    "contains": "Each step's saved file, and every MISSING line in one list."
   }
  ]
 },
 "output_shape": "THIS WEEK\n  Spend <amount> | Purchases <n> | 7-day click ROAS <x> vs break-even <x> | Cost per sale <amount> vs break-even <amount> | change vs last week | trust <n>/100\n\nPATH TAKEN\n  <drop analysis | delivery check | routine | scale check>: <why>\n\nCHANGES TO APPROVE (most important first)\n  1. <change> | where: <campaign or ad set> | size: <amount> | from: <step> | why: <reason>\n\nSCALE CALL\n  <raise | hold | cut> | blended ROAS <x> | 30-day cash <amount>\n\nLAST WEEK'S CHANGES\n  <change>: <worked | too early | did not work> | <numbers>\n\nWATCH NEXT WEEK\n  <1 to 3 numbers>\n\nFILES AND MISSING\n  <each step's file> | MISSING: <every line>",
 "how_to_use": [
  "Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run this week's check.",
  "Put this week's and last week's exports in one folder, or attach them in the chat.",
  "The first time, give it your order value and costs. It saves your break-even numbers and reuses them.",
  "Read the change list. Make the changes you agree with in Ads Manager, or say yes to each one and let it make only those if it is connected.",
  "Run it again next Monday. It reads its memory file and checks last week's changes."
 ],
 "checks": [
  "Every call is measured against your break-even numbers, and the sums are shown.",
  "A sharp drop was traced to a link before any cut was proposed.",
  "No spend raise is proposed in a week with an unexplained drop or a low trust score.",
  "Each change says which step proposed it and why.",
  "Nothing in your account was changed without your clear yes."
 ],
 "steps": [
  {
   "position": 1,
   "id": "break-even-roas-and-cpa-calculator",
   "name": "Break-even ROAS and CPA calculator",
   "summary": "Share order value, costs and ad figures. Get ad-cost limits, a matching cost check and clear gaps before choosing a test.",
   "url": "https://useaiblocks.com/skills/break-even-roas-and-cpa-calculator"
  },
  {
   "position": 2,
   "id": "ad-sales-drop-analyst",
   "name": "Ad sales drop analyst",
   "summary": "Share two periods of ad totals and your target. Get the weakest link, ranked possible causes, next checks and a target-based score.",
   "url": "https://useaiblocks.com/skills/ad-sales-drop-analyst"
  },
  {
   "position": 3,
   "id": "meta-delivery-troubleshooter",
   "name": "Meta delivery troubleshooter",
   "summary": "Share at least seven days of ad data. Get a cautious diagnosis, one change to test and a comparison plan.",
   "url": "https://useaiblocks.com/skills/meta-delivery-troubleshooter"
  },
  {
   "position": 4,
   "id": "platform-roas-reality-check",
   "name": "Ad return evidence checker",
   "summary": "Share ad reports and store totals. Get matched comparisons, evidence gaps and a custom review score, without a causal sales claim.",
   "url": "https://useaiblocks.com/skills/platform-roas-reality-check"
  },
  {
   "position": 5,
   "id": "meta-campaign-purpose-checker",
   "name": "Meta campaign purpose checker",
   "summary": "Check your Meta campaigns with this campaign purpose checker. Get a keep, merge or cut call for each, a list of setup errors and a score out of 100.",
   "url": "https://useaiblocks.com/skills/meta-campaign-purpose-checker"
  },
  {
   "position": 6,
   "id": "creative-test-reader",
   "name": "Ad creative test analyst",
   "summary": "Paste your ad test results by ad set. Get keep, leave or replace calls for each ad, false winners flagged and a score for how safe the read is.",
   "url": "https://useaiblocks.com/skills/creative-test-reader"
  },
  {
   "position": 7,
   "id": "meta-scaling-campaign-planner",
   "name": "Meta campaign growth planner",
   "summary": "Plan how to scale winning Meta ads without losing money. Give your costs and results. You get a break-even ROAS, a spend ladder and stop rules.",
   "url": "https://useaiblocks.com/skills/meta-scaling-campaign-planner"
  }
 ],
 "next": [
  {
   "name": "Meta test campaign planner",
   "url": "https://useaiblocks.com/skills/meta-test-campaign-planner",
   "why": "Plan what to test"
  }
 ],
 "source": null,
 "credits": [],
 "files": [],
 "links": {
  "page": "https://useaiblocks.com/agents/meta-ads-weekly-account-keeper",
  "markdown": "https://useaiblocks.com/agents/meta-ads-weekly-account-keeper.md",
  "json": "https://useaiblocks.com/agents/meta-ads-weekly-account-keeper.json",
  "instructions": "https://useaiblocks.com/skills/meta-ads-weekly-account-keeper/SKILL.md",
  "api_item": "https://useaiblocks.com/api/v1/items/meta-ads-weekly-account-keeper",
  "api_document": "https://useaiblocks.com/api/v1/documents/agent/meta-ads-weekly-account-keeper",
  "mcp": "https://useaiblocks.com/mcp"
 }
}
