Report weekly Google Ads return on ad spend for every campaign

SKILL.md---
name: google-ads-roas-report
description: "Every Monday: last week's Google Ads conversion value against cost for the whole account and each campaign, set against your target ROAS. Use when the user asks for this, or when it runs on a schedule."
---

# Google Ads ROAS report

Every Monday: last week's Google Ads conversion value against cost for the whole account and each campaign, set against your target ROAS.

For a store, cost per conversion is half the picture. A $40 conversion is great on a $300 order and a loss on a $25 one. Return on ad spend puts the value back in, and it is usually the first number a founder asks about. Google Ads shows it as "Conv. value / cost", a column many accounts never add to their view.

The agent works it out every Monday for the account and each campaign, against the target ROAS you bid to. You see which campaigns pay back, which only look busy, and whether the account is moving the right way.

## Two ways to get the data

Use the API or MCP route when you have an MCP server, a CLI or an API token for the app. Otherwise, if you can drive a browser the user is signed in to (Claude in Chrome, a Playwright or Chrome DevTools MCP server), use the browser route. Say which one you used.

## Route A: API or MCP server

### What you need

- Read access to the Google Ads account, with conversion actions that carry a value (purchases with order value, or leads with a set value).
- Google Ads API access through a Google Cloud project with API access and OAuth credentials (developer tokens were retired in September 2026), or the official Google Ads MCP server, which is read-only.
- Your target ROAS, and your gross margin if you want the break-even ROAS in the report.

If something is missing, say what and stop; do not invent numbers.

### Steps

1. **Pull value and cost** (Google Ads): Run GAQL on `campaign` with `campaign.name`, `metrics.cost_micros`, `metrics.conversions_value` and `metrics.conversions`, `WHERE segments.date DURING LAST_7_DAYS`. ROAS is `conversions_value` divided by cost in currency units.
2. **Get each target** (Google Ads): Read `campaign.maximize_conversion_value.target_roas` or `campaign.target_roas.target_roas`, a ratio where 4.0 means 400%. Campaigns without a target use your account target.
3. **Compare with the week before**: Repeat for the previous 7 days. Flag campaigns more than 20% under target, and any campaign that spent over $500 at a ROAS under 1, which loses money before margins.
4. **Post the tile**: Account ROAS is the headline as a multiple (4.2x) with 8 weeks of history. The glance shows value, cost and the campaigns under target; the card opens to the campaign table and the break-even line when you gave a margin.

## Route B: the browser

### What you need

- Signed in to Google Ads with at least Read-only access to an account whose conversion actions carry a value.

If something is missing, say what and stop; do not invent numbers.

### Steps

Start at https://ads.google.com/aw/campaigns. The user is signed in already; never type passwords or codes, and ask if a sign-in page appears.

1. **Set the last 7 days with a comparison**: Open `https://ads.google.com/aw/campaigns`, pick the client account if asked, choose `Last 7 days` in the date picker and turn on `Compare` with `Previous period`.
2. **Add the value columns**: Under Columns, Modify columns, add `Cost`, `Conv. value`, `Conv. value / cost` and `Target ROAS` (Attributes), and filter to enabled campaigns. `Conv. value / cost` is ROAS as a ratio: 4.2 means 4.2x.
3. **Read the account and each campaign**: Account ROAS comes from the Total row. For each campaign note cost, conversion value, the ratio, its target ROAS and the change in the comparison row; campaigns with no target use your account target.
4. **Flag the losers**: Flag campaigns more than 20% under target, and any that spent over $500 at a ratio under 1. If you know the gross margin, break-even ROAS is 1 divided by the margin.

Note: The Conv. value / cost column uses primary conversion actions and the account's attribution model, so it will not match store revenue. Google Ads reports value in the account currency, converted at the time of the conversion.

## The report

- **Account ROAS** last week as a multiple, with an 8-week trend.
- **Conversion value and cost**, with the change on the week before.
- **By campaign**: cost, value, ROAS and target.
- **Below target** and **under 1x** campaigns, with the spend at stake.
- With a margin, the break-even ROAS (1 divided by the margin).

## Post it to Briefkin

When `BRIEFKIN_TOKEN` is set, or `~/.config/briefkin/env` exists (the installer from https://briefkin.dev/docs writes it), also send the result to the user's Briefkin board as one card. Keep the `item_key` the same on every run so the card updates in place, use a new `event_id` per run, and put today's real numbers in place of the example ones. If the request fails, say so once and carry on.

```bash
[ -n "${BRIEFKIN_TOKEN:-}" ] || . ~/.config/briefkin/env
curl -sS -X POST "${BRIEFKIN_URL:-https://briefkin.dev}/v1/events" \
  -H "authorization: Bearer $BRIEFKIN_TOKEN" \
  -H "content-type: application/json" \
  -d @- <<'JSON'
{
  "v": 1,
  "event_id": "google-ads-roas-report/<date of this run, e.g. 2026-10-16>",
  "item_key": "google-ads-roas-report",
  "project": "Acme Store",
  "source": "Google Ads ROAS report skill",
  "kind": "metric",
  "title": "ROAS at 4.2x, the best in 8 weeks",
  "metric": {
    "label": "ROAS",
    "value": 4.2,
    "unit": "x",
    "better": "higher",
    "period_start": "<start of the period, ISO 8601>",
    "period_end": "<end of the period, ISO 8601>"
  },
  "glance": {
    "type": "Grid",
    "props": {
      "columns": 3
    },
    "children": [
      {
        "type": "Stat",
        "props": {
          "label": "Conv. value",
          "value": 41412,
          "prefix": "$",
          "delta": 9
        }
      },
      {
        "type": "Stat",
        "props": {
          "label": "Cost",
          "value": 9860,
          "prefix": "$",
          "delta": 1
        }
      },
      {
        "type": "Stat",
        "props": {
          "label": "Below target",
          "value": "2 campaigns",
          "tone": "warn"
        }
      }
    ]
  },
  "widget": [
    {
      "type": "Table",
      "props": {
        "columns": [
          "Campaign",
          "Cost",
          "Conv. value",
          "ROAS",
          "Target"
        ],
        "align": [
          "left",
          "right",
          "right",
          "right",
          "right"
        ],
        "rows": [
          [
            "Brand Search",
            "$1,240",
            "$11,780",
            "9.5x",
            "6.0x"
          ],
          [
            "Performance Max",
            "$4,980",
            "$21,912",
            "4.4x",
            "4.0x"
          ],
          [
            "Non-brand Search",
            "$2,860",
            "$6,292",
            "2.2x",
            "3.5x"
          ],
          [
            "Display Remarketing",
            "$780",
            "$1,428",
            "1.8x",
            "3.0x"
          ],
          [
            "Account",
            "$9,860",
            "$41,412",
            "4.2x",
            "4.0x"
          ]
        ]
      }
    },
    {
      "type": "Callout",
      "props": {
        "text": "Non-brand Search spent $2,860 at 2.2x against a 3.5x target. At a 40% margin break-even is 2.5x, so it is losing money.",
        "tone": "bad"
      }
    }
  ],
  "size": "md"
}
JSON
```

Widgets come from the Briefkin catalog (https://briefkin.dev/v1/catalog). Without a token, just give the user the report.

Set `period_start` and `period_end` to the window the number covers: the tile names it from them ("Last 7 days", "Today", "This month"). For a count right now (open items, a balance), send `"period_label": ""` so no period shows; for another name, send it as `period_label` (at most 24 characters).

## Run it on a schedule

Suggested: Mondays at 9:00 (`0 9 * * 1`). From cron, with the agent signed in on that machine:

```bash
0 9 * * 1 claude -p "Run the google-ads-roas-report skill"
# Codex: codex exec, Gemini CLI: gemini -p, Copilot CLI: copilot -p, OpenCode: opencode run
```

Or use the agent's own scheduler (Claude Code routines, Codex automations, Claude or ChatGPT scheduled tasks): https://briefkin.dev/skills/google-ads-roas-report#schedule

Source: https://briefkin.dev/skills/google-ads-roas-report