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

google-search-term-audit

Skill15 starsChanged 37 days agoMITView on GitHub

Forensic Google Ads Search-term waste audit. Pareto-filters down to the 80% of spend that matters (campaign-level, then search-term-level), then flags wasteful terms using campaign-relative triggers: low engagement (CTR ≥40% below campaign avg) and low conversion (CVR ≥40% below campaign avg, including zeros). Surfaces a "Red List" with suggested negative-keyword exclusions and identifies common "waste words" for root-level negatives. Read-only — proposes exclusions, never executes them. Use weekly for waste cleanup.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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
  2. Distinctive:

    Campaign filter: Search campaigns only (exclude Shopping, PMax, Display).

    line 15
  3. Distinctive:

    Search term spend ≥ 5% of campaign total, AND

    line 26
  4. Distinctive:

    Search-term CTR ≥ 40% lower than the specific campaign's average CTR

    line 27
  5. Distinctive:

    Search-term CVR ≥ 40% lower than the specific campaign's average CVR (zero conversions counts)

    line 31
  6. Distinctive:

    If 3+ Red List terms share a common waste word, recommend a single root negative that covers them all instead of a list of individual …

    line 40

≈ “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 Search Term Audit — Waste Forensics (Read-Only)

For the Google Ads account the user names, run a forensic search-term waste audit. Read-only — produces a suggested-exclusion list, never executes mutations.

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

Phase 1 — Data selection + Pareto filtering

  1. Campaign filter: Search campaigns only (exclude Shopping, PMax, Display).
  2. Campaign Pareto: Identify the campaigns that account for 80% of total Search spend.
  3. Search-term Pareto (per campaign): Within each selected campaign, pull the search terms that account for 80% of that campaign's spend.

This focuses the audit on the spend that actually matters.

Phase 2 — Waste identification (the "Red List")

For each high-spend search term, compare against its own campaign's averages (not account averages — relativity matters).

Trigger 1 — Low Engagement Red Flag

  • Search term spend ≥ 5% of campaign total, AND
  • Search-term CTR ≥ 40% lower than the specific campaign's average CTR

Trigger 2 — Low Conversion Red Flag

  • Search term spend ≥ 8% of campaign total, AND
  • Search-term CVR ≥ 40% lower than the specific campaign's average CVR (zero conversions counts)

Any term hitting either trigger goes on the Red List.

Phase 3 — Root-cause analysis

Review the Red List for common "waste words" — patterns that appear across multiple flagged terms. Examples:

  • "free [product]", "how to [verb]", "diy [thing]", "jobs", "salary", "reviews of [competitor]"

If 3+ Red List terms share a common waste word, recommend a single root negative that covers them all instead of a list of individual negatives. Saves ad-group bloat.

Output

Section 1 — Red List table

Search termCampaignTerm spend% of camp spendTerm CTRCamp avg CTRTerm CVRCamp avg CVRTriggerSuggested negative

Sort by term spend descending. Cap at top 30.

Section 2 — Root negative recommendations

For each common waste word found:

  • Suggested root negative: "[word]" (phrase match) — covers N terms on the Red List, $X total wasted spend

Section 3 — Per-campaign exclusion summary

For each campaign with Red List terms:

  • Total Red List spend
  • Total Red List conversions
  • Estimated monthly savings if all suggested negatives applied
  • One-line take: Recommend adding NN exact negatives + N phrase root negatives to [campaign]

End with: _All recommendations — no negatives added. Use the google-ads-search-execution skill to enact any subset of these exclusions._

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