Demographic and device review
Reads results by age group, gender and device on Google Ads, Meta Ads and TikTok Ads, and the same cuts in Google Analytics 4, to see who converts and on which screen.
| Item | Value |
|---|---|
| Skill name | demographic-and-device-review |
| Required MCP server | Pilot MCP, https://app.pilot.braike.com/mcp |
| Writes | None: the skill only reads |
| Download | demographic-and-device-review.zip |
MCP tools used
| Tool | Platform |
|---|---|
google_list_accounts | Google Ads |
google_run_query | Google Ads |
google_list_campaign_bid_modifiers | Google Ads |
meta_list_accounts | Meta Ads |
meta_get_account_insights | Meta Ads |
tiktok_get_advertiser_info | TikTok Ads |
tiktok_get_age_gender_performance | TikTok Ads |
google_analytics_run_report | Google Analytics 4 |
Optional MCP servers
A file storage server to keep the result, a team messaging server to share it, a note-taking server to archive it. None is needed: the skill works with Pilot MCP alone.
Example requests
- "Which age groups and devices convert best?"
- "How does mobile compare with desktop on each platform?"
What the skill returns
Who converts and on which device in three lines, a table per platform for age and gender, another for devices with the adjustments already set, and the adjustments to test.
Install
Download demographic-and-device-review.zip, then follow the steps for your client: install a skill. With the Pilot CLI, one command is enough:
npx @braike/pilot skills install demographic-and-device-reviewThe SKILL.md file
See the file as your assistant reads it
---
name: demographic-and-device-review
description: "Reviews advertising results by age, gender and device through the Pilot MCP server: Google Ads age and gender views and device segments, Meta Ads and TikTok Ads breakdowns, and the same cuts in Google Analytics 4, then shows which groups and devices convert, which only cost, and what bid or targeting change to test. Use when the user asks who converts, how mobile compares with desktop, or which age groups to target. Triggers: demographics report, age and gender performance, mobile versus desktop, device performance. Déclencheurs : performance par âge et sexe, démographie, mobile contre ordinateur, performance par appareil, qui convertit."
compatibility: "Requires the Pilot MCP server (https://app.pilot.braike.com/mcp) connected in the client and authorized on a workspace with Google Ads, Meta Ads or TikTok Ads attached."
metadata:
pilot-mcp-server: "https://app.pilot.braike.com/mcp"
pilot-mcp-tools: "google_list_accounts google_run_query google_list_campaign_bid_modifiers meta_list_accounts meta_get_account_insights tiktok_get_advertiser_info tiktok_get_age_gender_performance google_analytics_run_report"
pilot-mcp-read-only: "true"
---
# Demographic and device review
Show which age groups, genders and devices bring results on each platform, and which ones only cost. Answer in the user's language.
## Requirements
- **Required MCP server:** Pilot MCP (`https://app.pilot.braike.com/mcp`), authorized on the workspace concerned.
- **Optional MCP servers:** a chart server to draw the splits. None is needed.
- **Read-only:** never change bids or targeting. Proposals are for a person to apply.
## Tools
- `google_list_accounts`: the Google Ads accounts attached to the workspace.
- `google_run_query`: a read-only GAQL query, here on the age, gender and campaign views of Google Ads.
- `google_list_campaign_bid_modifiers`: device bid adjustments already set on campaigns.
- `meta_list_accounts`: the Meta ad accounts attached to the workspace.
- `meta_get_account_insights`: Meta results split by `age`, `gender` or `device_platform`.
- `tiktok_get_advertiser_info`: the TikTok advertiser and its currency.
- `tiktok_get_age_gender_performance`: TikTok results by age group and gender.
- `google_analytics_run_report`: GA4 sessions and key events by device, age and gender.
## Steps
1. Set the period: the last 30 days by default.
2. Google Ads: `google_list_accounts`, then three `google_run_query` calls:
- age: `SELECT ad_group_criterion.age_range.type, metrics.cost_micros, metrics.conversions, metrics.conversions_value FROM age_range_view WHERE segments.date DURING LAST_30_DAYS`
- gender: the same fields with `ad_group_criterion.gender.type` from `gender_view`
- device: `SELECT segments.device, metrics.cost_micros, metrics.conversions, metrics.conversions_value FROM campaign WHERE segments.date DURING LAST_30_DAYS`
Then `google_list_campaign_bid_modifiers` to see the device adjustments in place.
3. Meta Ads: `meta_list_accounts`, then `meta_get_account_insights` with `date_preset: "last_30d"` and `breakdowns: ["age", "gender"]`, then with `breakdowns: ["device_platform"]`.
4. TikTok Ads, if attached: `tiktok_get_advertiser_info`, then `tiktok_get_age_gender_performance` over the period.
5. GA4: `google_analytics_run_report` with `dimensions: ["deviceCategory"]`, then `["userAgeBracket", "userGender"]`, and `metrics: ["sessions", "keyEvents"]`. Age and gender exist in GA4 only when Google signals is on and above its thresholds.
6. For each cut, compare each group's share of spend with its share of conversions, and its CPA or ROAS with the average.
## Output
1. **Summary**: who converts and on which device, in three lines.
2. **By age and gender**: a table per platform with spend, conversions, CPA and ROAS per group.
3. **By device**: the same for mobile, desktop and tablet, with the adjustments already set.
4. **To test**: bid adjustments or exclusions worth testing, for a person to decide.
## Rules
- Google amounts are in micros: divide by 1,000,000.
- An "undetermined" or "unknown" group is reported as such, never spread over the others.
- A group with few conversions is not judged.
- Never sum amounts in different currencies; name the period.
- Some sectors cannot target by age or gender: say so before proposing an exclusion.
## Examples
- "Which age groups and devices convert best?"
- "Compare mobile et ordinateur sur Google Ads, Meta et TikTok."
- "Qui achète vraiment, par âge et par sexe ?"Geo performance review
Compares spend, conversions, cost per acquisition and ROAS by location on Google Ads, Meta Ads and TikTok Ads, sets where people really were against the locations targeted, and reads traffic by country in Google Analytics 4.
Google Ads account audit
Reviews a Google Ads account and returns findings ranked by money at stake: structure, spend without conversions, search terms, bidding, conversion tracking, ad strength, recommendations and recent changes.