agentsclimarketplace

Gads audit

Skill arcbaslow/google-ads-agents/skills/gads-audit

Full Google Ads account audit. Fans out to every analysis agent in parallel, gates on auth and 24h session, then renders a markdown report.From its SKILL.md

Install
npx -y skills add arcbaslow/google-ads-agents --skill gads-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.6 KB, as published. Nobody here has run it

Audit orchestrator

/gads audit <customer-id> [--days N]

Sequence

  1. Auth + session gate. Run python scripts/gads_auth.py --check. If the session is expired or the developer token is missing, stop and instruct the user to re-authenticate. Do not proceed.

  2. Pre-flight gates, in series. These determine whether the rest of the audit can be trusted:

    • gads-conversions — if there are no primary conversion actions, the rest of the audit's bid-strategy critique is meaningless. Note that in the report and continue with reduced confidence.
    • gads-gtag — if gtag/GA4 isn't installed, conversion data is unreliable. Note and continue.
  3. Fan out in parallel (one subagent per domain):

    • gads-search
    • gads-pmax
    • gads-uac
    • gads-display
    • gads-shopping
    • gads-youtube
    • gads-keywords (skip unless --seeds provided)
    • gads-competitors
    • gads-placements
  4. Merge results. Each agent returns JSON with summary, findings, and metrics. Concatenate findings, group by severity, build the action plan.

  5. Render via python scripts/gads_report.py --input <merged.json> to markdown by default. HTML and PDF via --format html|pdf.

Output

A single markdown file under ~/.claude/gads-audit-<customer>-<date>.md plus the ~/.claude/gads-audit-<customer>-<date>.json raw merge for reference.

Keep looking

Skills are one crate of 609,689. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.