agentleFS
Sign inStart free
gomarble-aigomarble-ai/marketing-agent/skills/google-search-audit/SKILL.md

google-search-audit

Skill15 starsChanged 37 days agoMITView on GitHub

Daily Google Ads Search morning briefing — compares last 3 days vs prior 3 days, segments brand vs non-brand (with different expectations for each), and surfaces specific recommendations across budget, impression share, bid adjustments, search-term waste, and query opportunities. Read-only — produces a CUT / FIX / SCALE recommendations list, never executes mutations. Use as your morning Google Search standup.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user didn't name an account, list their connected accounts and ask which one to use.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Google Ads Search Audit — Morning Briefing (Read-Only)

For the Google Ads account the user names, run a daily Search-campaigns operator pass. Compare last 3 days vs prior 3 days. Read-only — output is recommendations only, no mutations applied.

If the user didn't name an account, list their connected accounts and ask which one to use.

Step 1 — Brand vs Non-Brand classification (do first)

For every Search campaign, classify as Brand or Non-Brand before analyzing. Use campaign name, keyword content, and whether top queries contain the brand name.

TypeHealthy stateFocus
BrandIS > 85%, low CPA, query intent cleanEfficiency, waste reduction. Scaling is demand-limited, not budget-limited.
Non-BrandGrowth runway in IS, CPA at-or-below targetIS growth, budget scaling, volume expansion.

Surface recommendations against the correct expectation per type.

Step 2 — Metrics to pull

Per campaign, both 3d windows: CPA vs target, Conversion volume, Search Impression Share, Lost IS (Rank), Lost IS (Budget), Top-of-page rate, Absolute-top %, ROAS, Conversion Value (AOV trend).

Step 3 — Analysis tasks

Budget + efficiency

  • Campaign with rising CPA + stable/improving IS → likely demand issue, recommendation: reassess targeting or pause
  • Campaign with low IS + strong CPA → suggest budget increase with exact %
  • Campaign where CPA improved but ROAS declined → flag AOV / mix-shift issue

Impression share

  • Lost IS (Budget) > 20% → suggest budget increase, state %
  • Lost IS (Rank) > 20% → suggest bid adjustment or relevance work

Search-term waste

  • Identify queries spending > 2× target CPA with poor conversion intent
  • Suggest exact-match negative keywords (do not add them — recommend only)

Query-level opportunities

  • Identify high-converting queries not yet in exact match
  • Suggest exact-match keyword additions

Alerts

  • Flag any sudden drop > 25% in CVR, IS, conversions, or ROAS — surface as "investigate first"

Output format

Three sections, each a vertical list of recommendation lines:

🛑 CUT / WASTE

  • Suggest adding negative exact: "[query]" — spending $X at CPA $Y (3.2× target)

🔧 FIX

  • Suggest bid +15% on [ad group] — Lost IS (Rank) 28%, strong relevance signal

📈 SCALE

  • Suggest budget +20% on [campaign — Non-Brand] — Lost IS (Budget) 35%, CPA 18% under target

Skip a section entirely if it has no recommendations. End with: _All recommendations — no changes applied._

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free