Agent skill

Google Ads Tracking

by TheMattBerman in TheMattBerman/google-ads-copilot

Diagnose whether a Google Ads account's conversion tracking is trustworthy enough to optimize.

MITAuto-check passedMarketing & SEO

Install Google Ads Tracking

skills CLI
$ npx skills add TheMattBerman/google-ads-copilot --skill google-ads-tracking -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TheMattBerman/google-ads-copilot google-ads-tracking --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/google-ads-tracking .claude/skills/google-ads-tracking && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
google-ads-tracking
GitHub stars
238
Token cost
~1.8k tokens
SKILL.md length
704 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

Diagnose whether a Google Ads account's conversion tracking is trustworthy enough to optimize.

  • Works in 3 steps: Can we trust the account? → What to check → Impact assessment
  • Tasks that involve Paid advertising
  • SKILL.md covers Data Acquisition, Diagnostic Framework, Draft Output and Output Shape, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Google Ads Tracking is an agent skill from TheMattBerman/google-ads-copilot. Diagnose whether a Google Ads account's conversion tracking is trustworthy enough to optimize. Pulls live data via MCP or works with manual exports. Produces tracking fix drafts when problems are found.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Paid advertising. It works with Google Ads and Model Context Protocol. The repository describes itself as: Google Ads Copilot: operator kit for audits, MCP-connected reads, export-mode analysis, and draft/apply workflows. The licence is MIT.

When your agent uses it

  • Tasks that involve Paid advertising

Example prompts

  • “/google-ads-tracking”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Can we trust the account?
  2. What to check
  3. Impact assessment

What it can do on your machine

Read from SKILL.md and the folder at commit 2c253ee. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are sql).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Google Ads Tracking loads about 1.8k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 704 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TheMattBerman/google-ads-copilot at commit 2c253ee, republished under its MIT licence (© TheMattBerman). 704 words, ~1,800 tokens.

Download SKILL.mdSave it as .claude/skills/google-ads-tracking/SKILL.md (or your agent's skills folder).
name
google-ads-tracking
description
Diagnose whether a Google Ads account's conversion tracking is trustworthy enough to optimize. Pulls live data via MCP or works with manual exports. Produces tracking fix drafts when problems are found.

Google Ads Tracking

Read first:

  • google-ads/references/operator-thesis.md
  • google-ads/references/tracking-playbook.md
  • google-ads/references/deliverable-templates.md

Read workspace if available:

  • workspace/ads/account.md
  • workspace/ads/goals.md
  • workspace/ads/findings.md
  • workspace/ads/change-log.md
  • workspace/ads/learnings.md

Data Acquisition

Connected Mode (MCP available)

Pull via the search tool on google-ads-mcp:

Primary: Conversion actions and configuration:

sql
SELECT
  conversion_action.id,
  conversion_action.name,
  conversion_action.type,
  conversion_action.category,
  conversion_action.status,
  conversion_action.counting_type,
  conversion_action.include_in_conversions_metric,
  conversion_action.value_settings.default_value
FROM conversion_action
WHERE conversion_action.status = 'ENABLED'

Primary: Conversion performance by action (detect duplicates/pollution):

sql
SELECT
  conversion_action.name,
  conversion_action.type,
  conversion_action.category,
  metrics.conversions,
  metrics.conversions_value,
  metrics.all_conversions
FROM conversion_action
WHERE segments.date DURING LAST_30_DAYS
  AND conversion_action.status = 'ENABLED'
ORDER BY metrics.conversions DESC

Supplementary: Account auto-tagging status:

sql
SELECT
  customer.id,
  customer.descriptive_name,
  customer.auto_tagging_enabled
FROM customer

Supplementary: Campaign-level conversion metrics (look for anomalies):

sql
SELECT
  campaign.name,
  metrics.conversions,
  metrics.all_conversions,
  metrics.conversions_value,
  metrics.cost_micros,
  metrics.cost_per_conversion
FROM campaign
WHERE campaign.status = 'ENABLED'
  AND segments.date DURING LAST_30_DAYS
ORDER BY metrics.conversions DESC

See data/gaql-recipes.md for additional queries.

Date Range Fallback

Conversion action configuration queries (no date range) always work. For conversion performance queries, if LAST_30_DAYS returns zero data, fall back to LAST_90_DAYS, then all-time. Configuration queries don't need fallback — they reflect current state regardless. Always state the date range used.

Export Mode (no MCP)

Ask the user for:

  • Conversion actions list (name, type, counting, include in conversions, value settings)
  • Google Tag Assistant screenshot or diagnosis notes
  • GA4 conversion import settings (if applicable)
  • Any notes on tracking implementation

See data/export-formats.md for recommended format.


Diagnostic Framework

1. Can we trust the account?

Assign a tracking confidence level immediately using the rubric in google-ads/references/tracking-playbook.md.

LevelMeaningAction
HighClean primary conversion, no duplicates, correct counting, ≥15 conv/30dOptimize freely
MediumMinor issues (micro-conversions in primary, 5-14 conv/30d, possible over-count)Optimize cautiously, fix issues
LowMajor problems (duplicates, wrong counting, <5 conv/30d, polluted signal)Fix tracking FIRST, block budget scaling
BrokenNo meaningful conversion signalStop. Fix tracking. Nothing else matters.

Threshold checklist (from tracking-playbook.md):

  • Count primary conversion actions (should be 1-2 clear ones)
  • Check include_in_conversions_metric — are micro-conversions polluting primary?
  • Compare conversions vs all_conversions — if ratio is >2x, investigate
  • Check counting type — "One" for leads, "Every" for e-commerce only
  • Check for duplicate sources — same event tracked by both native tag AND GA4 import?
  • Check auto-tagging status
  • Verify conversion volume (≥15/30d for HIGH, 5-14 for MEDIUM, <5 for LOW)
2. What to check

Duplicate counting:

  • Same conversion tracked by both native tag AND GA4 import
  • Multiple conversion actions for the same event
  • "Every" counting type on lead/form events (should be "One")

Micro-conversion pollution:

  • Page views, scroll depth, time on site set as primary conversions
  • These inflate conversion count and deflate apparent CPA
  • Smart bidding optimizes toward them instead of real conversions

Missing conversions:

  • Key events not tracked at all
  • Phone calls without call tracking
  • Form submissions without confirmation page or event tracking

Attribution concerns:

  • Auto-tagging disabled (GCLID not passing)
  • Cross-domain tracking gaps
  • Conversion window too short or too long

Value quality:

  • All conversions have the same default value
  • Values don't reflect actual revenue
  • Missing value tracking on e-commerce
3. Impact assessment

For each problem found, assess:

  • How much is this distorting reported performance?
  • Which campaigns are most affected?
  • Is smart bidding learning from bad signal?
  • What decisions should wait until this is fixed?
Show full SKILL.md (265 more words)Show less

Draft Output

Tracking Fix Draft

Trigger: Any tracking problem at Medium confidence or lower.

Create using drafts/templates/tracking-draft.md:

  • Write to workspace/ads/drafts/YYYY-MM-DD-[account-slug]-tracking-fix.md
  • Include specific fixes: what to change, current vs. proposed state
  • Note the impact on reported conversions ("Conversions will appear to drop ~40%")
  • Note the impact on smart bidding ("2-3 week recalibration period")
  • Critically: list which optimization decisions should wait until tracking is fixed
  • Update workspace/ads/drafts/_index.md
Blocking behavior

When tracking confidence is Low or Broken, the draft should include a "blocked decisions" section that explicitly names what other skills/drafts should NOT proceed until tracking is resolved:

  • Budget scaling → blocked
  • Structure changes → proceed with caution
  • Negatives → can proceed (waste is waste regardless of tracking)
  • RSA changes → can proceed (copy quality is independent)
Always update workspace memory:
  • workspace/ads/findings.md — tracking diagnosis and confidence level
  • workspace/ads/account.md — update tracking status if it has changed
  • workspace/ads/learnings.md — what we learned about this account's tracking

Output Shape

  1. Account Status block — account name, CID, status, date range used, tracking confidence, mode
  2. Conversion actions inventory (what's tracked, how, counting type)
  3. Problems identified (with severity and evidence)
  4. Impact assessment (what's distorted, which campaigns affected)
  5. Recommended fixes (specific changes)
  6. Blocked decisions (what should wait)
  7. Draft created (path and summary)
  8. Memory updates

Rules

  • If tracking is unreliable, say it early.
  • Do not bury trust issues under optimization tips.
  • Explain what decisions should wait until tracking is fixed.
  • Tracking confidence is a gate. If it's Low or Broken, other skills should know.
  • The most dangerous Google Ads accounts look great on paper because tracking is counting the wrong things. Surface this clearly.

© TheMattBerman, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/google-ads-tracking of TheMattBerman/google-ads-copilot.

Open the folder on GitHubat commit 2c253ee

Compare with similar skills

Google Ads Tracking next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Google Ads Tracking compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Google Ads Tracking this skillTheMattBerman/google-ads-copilot238—~1.8kAutomated safety check: PassMIT
Google Ads Landing Page Auditnowork-studio/notfair-plugin3.9k—~2.7kAutomated safety check: PassMIT
Google Ads API MCP Setupgoogle/skills21k—~6.1kAutomated safety check: NotesApache-2.0
21 Audit Ads Performanceminhnv0807/ai-business-skills608—~4.6kAutomated safety check: PassMIT
Connectindranilbanerjee/digital-marketing-pro8551 repos~2kAutomated safety check: PassMIT
Launch Ad Campaignindranilbanerjee/digital-marketing-pro8551 repos~3.9kAutomated safety check: PassMIT

Similar skills

  • Google Ads Landing Page Audit

    nowork-studio/notfair-plugin

    Scores Google Ads landing pages on five weighted dimensions and diagnoses why high-CTR ad groups convert poorly, with concrete fixes for each page.

    3.9k GitHub stars~2.7k tokensUpdated 7 days ago
    Marketing & SEOAuto-check passed
  • Official

    Guides developers through downloading, configuring, and installing the official open-source Google Ads MCP Server.

    21k GitHub stars~6.1k tokensUpdated today
    Marketing & SEOAuto-check: notes
  • 21 Audit Ads Performance

    minhnv0807/ai-business-skills

    Dung khi can ra soat CAU HINH tai khoan quang cao mot cach he thong — 6 khau tu account, campaign, adset, creative, landing den tracking, cham Health Score 0-100 va liet ke Quick Wins.

    608 GitHub stars~4.6k tokensUpdated 26 days ago
    Marketing & SEOAuto-check passed
  • Connect

    indranilbanerjee/digital-marketing-pro

    Guide the connection of a known MCP integration to the plugin — looks up the connector registry via connector-status.py, checks current status, and returns transport-specific setup steps (OAuth for…

    855 GitHub starsUsed in 1 repo~2k tokens
    Marketing & SEOAuto-check passed
  • Launch Ad Campaign

    indranilbanerjee/digital-marketing-pro

    Create and launch a paid ad campaign on Google, Meta, LinkedIn, or TikTok through the connected ad-platform MCP — campaign structure, audience targeting, bid strategy, negative targeting, creative…

    855 GitHub starsUsed in 1 repo~3.9k tokens
    Marketing & SEOAuto-check passed
  • Blog Google

    AgriciDaniel/claude-blog

    Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity…

    2.3k GitHub starsUsed in 1 repo~3.3k tokens
    Marketing & SEOAuto-check: notes

More from TheMattBerman/google-ads-copilot

All 16 skills in this repo
  • Google Ads

    TheMattBerman/google-ads-copilot

    Google Ads operator system for search-term analysis, intent mapping, wasted spend control, account structure decisions, tracking diagnostics, RSA generation, budget review, account planning, and…

    238 GitHub stars~4.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Apply

    TheMattBerman/google-ads-copilot

    Execute approved draft actions in Google Ads accounts. An agent skill from TheMattBerman/google-ads-copilot.

    238 GitHub stars~2.7k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Audit

    TheMattBerman/google-ads-copilot

    Full Google Ads review that synthesizes tracking, search terms, intent mapping, negatives, structure, RSAs, budget decisions, and PMax context into a single operator read.

    238 GitHub stars~2.7k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Budget

    TheMattBerman/google-ads-copilot

    Review Google Ads budget allocation and scaling decisions based on signal quality, intent clarity, tracking confidence, and structural health.

    238 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Connect

    TheMattBerman/google-ads-copilot

    Connected-mode onboarding, health check, and customer selection for Google Ads Copilot.

    238 GitHub stars~2.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Daily

    TheMattBerman/google-ads-copilot

    Daily operator review for Google Ads. An agent skill from TheMattBerman/google-ads-copilot.

    238 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Google Ads Tracking

What does Google Ads Tracking do?

Diagnose whether a Google Ads account's conversion tracking is trustworthy enough to optimize. Google Ads Tracking is an agent skill from TheMattBerman/google-ads-copilot. Diagnose whether a Google Ads account's conversion tracking is trustworthy enough to optimize.

When should I use Google Ads Tracking?

Google Ads Tracking fits situations like: tasks that involve Paid advertising.

How do I install Google Ads Tracking in Claude Code?

Run `npx skills add TheMattBerman/google-ads-copilot --skill google-ads-tracking -a claude-code`. Or copy the skill folder (skills/google-ads-tracking in TheMattBerman/google-ads-copilot) into .claude/skills/google-ads-tracking in your project. Claude Code loads it when a task matches its description.

How do I install Google Ads Tracking in Codex?

Run `npx skills add TheMattBerman/google-ads-copilot --skill google-ads-tracking -a codex`. Or copy the skill folder (skills/google-ads-tracking in TheMattBerman/google-ads-copilot) into .agents/skills/google-ads-tracking in your project. Codex loads it when a task matches its description.

Can I use Google Ads Tracking in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheMattBerman/google-ads-copilot --skill google-ads-tracking -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/google-ads-tracking, .gemini/skills/google-ads-tracking, .github/skills/google-ads-tracking and .opencode/skills/google-ads-tracking in your project.

What does Google Ads Tracking need to run?

SKILL.md names no scripts, command-line tools or credentials: Google Ads Tracking is instructions for the agent only.

Does Google Ads Tracking access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Google Ads Tracking safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Google Ads Tracking use?

Google Ads Tracking is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Google Ads Tracking use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Google Ads Tracking?

Skills that share tags, products or a category with Google Ads Tracking: Google Ads Landing Page Audit (nowork-studio/notfair-plugin, 3.9k stars), Google Ads API MCP Setup (google/skills, 21k stars), 21 Audit Ads Performance (minhnv0807/ai-business-skills, 608 stars) and Connect (indranilbanerjee/digital-marketing-pro, 855 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Google Ads Tracking?

TheMattBerman (a GitHub user) maintains it in TheMattBerman/google-ads-copilot, which has 238 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on June 10, 2026.

Source: TheMattBerman/google-ads-copilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.