agentleFS
gomarble-aigomarble-ai/marketing-agent/skills/google-ads-search-execution/SKILL.md

google-ads-search-execution

Skill15 starsChanged 37 days agoMITView on GitHub

Use when making changes to Google Ads Search campaigns: tool parameters for bid adjustments, budget changes, negation, query isolation.

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:

    ALL must be true: majority Q1 queries, CPA ≤ target, Rank Pressure = HIGH

    line 15
  2. Distinctive:

    ALL must be true: CPA stable, Q1–Q3 spend share ≥ 60%, Budget Pressure = HIGH

    line 26
  3. Distinctive:

    When Q1 queries are mixed with Q2–Q5 and CPA on Q1 is below target but overall CPA is above target:

    line 40
  4. Distinctive:

    Create new campaign or ad group for isolated Q1 terms

    line 43
  5. Distinctive:

    Add Q1 queries as Exact match keywords in the new structure

    line 44
  6. Distinctive:

    Add the same terms as negatives in the original campaigns to prevent overlap

    line 45

≈ “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 — Execution Rules

Tool parameters and processes for implementing search campaign changes. Load this after completing analysis with google-ads-search-analysis.

Bid Adjustments

When to increase bids (5–10%):

  • ALL must be true: majority Q1 queries, CPA ≤ target, Rank Pressure = HIGH

Keyword-level bid change: google_ads_propose_update_adgroups on the keyword's ad group, with a keyword_changes entry for the keyword and its new cpc_bid_micros = current bid × 1.05–1.10, in account currency (divide the GAQL micros value by 1,000,000; e.g. 1.5 for $1.50).

Ad group-level bid change: google_ads_propose_update_adgroups with the new cpc_bid_micros = current bid × 1.05–1.10, in account currency.

Dry-run first; apply only after the user approves.

Budget Adjustments

When to increase budget (10–20%):

  • ALL must be true: CPA stable, Q1–Q3 spend share ≥ 60%, Budget Pressure = HIGH

Tool: google_ads_propose_update_campaigns with the new daily budget_micros = current budget × 1.10–1.20, in account currency (e.g. 50 for $50; divide the GAQL amount_micros by 1,000,000). Dry-run first; apply only after the user approves.

Query Negation

Immediate negation (Q5): free, cheap, diy, how to, job, salary, course, pdf, meaning, used, repair.

Conditional negation (Q4): Cost ≥ 1× target CPA AND conversions = 0, OR CPA ≥ 1.5× target.

Action: Add terms to shared negative keyword list at campaign or account level.

Query Isolation (Q1)

When Q1 queries are mixed with Q2–Q5 and CPA on Q1 is below target but overall CPA is above target:

  1. Identify top Q1 queries sorted by conversions
  2. Create new campaign or ad group for isolated Q1 terms
  3. Add Q1 queries as Exact match keywords in the new structure
  4. Add the same terms as negatives in the original campaigns to prevent overlap
  5. Set budget independently for the isolated campaign

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.