agentleFS
kelpi-aikelpi-ai/google-ads-skills/skills/query-to-keyword-promoter/SKILL.md

query-to-keyword-promoter

Skill2 starsChanged 4 months agoMITView on GitHub

Give proven search queries deliberate keyword, ad-group, and landing-page coverage without creating duplicates or mixing intent. Use after a search-term review finds real demand worth owning.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    After search-term review finds converting or high-value queries that are only arriving through broader coverage.

    line 14
  2. Distinctive:

    Use a connected Google Ads MCP for read-only context, or paste search terms, current keywords, negatives, ad groups, ads, final URLs, and …

    line 15
  3. Distinctive:

    Use performance and business fit, not search volume alone.

    line 36
  4. Distinctive:

    Check current keywords, close intent, negatives, ad copy, and the final page before proposing a new keyword.

    line 37
  5. Distinctive:

    If there is no credible page or message for the query, hold it rather than sending it to the homepage by default.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Query to Keyword Promoter

Doctrine

A converting search term deserves a clear home only when the account can answer its intent. Promotion is not copying every winner into Exact. Check existing coverage, choose a match type for the job, route it to an ad group with the right promise, and hold the proposal if the landing page or ad message is missing.

When to use

  • After search-term review finds converting or high-value queries that are only arriving through broader coverage.
  • Use a connected Google Ads MCP for read-only context, or paste search terms, current keywords, negatives, ad groups, ads, final URLs, and business targets.
  • Include conversion lag and downstream lead quality when those affect the verdict.

Run it

Build a READ-ONLY query-to-keyword promotion plan. Use live account data for context if connected; otherwise use what I paste. Add nothing.

1. Confirm the date range, primary conversion, target CPA or ROAS, and conversion delay.
2. For each candidate query show: spend, conversions, value, CPA or ROAS, current triggering keyword, current match type, current ad group, and current final URL.
3. Check whether the same intent already has deliberate coverage. Do not create a duplicate just because the search term looks good.
4. For each real opportunity propose: keyword text, Exact or Phrase match, destination ad group, message promise, final URL, negative conflicts, and why this structure fits the query.
5. If the query needs a different promise or page, propose a new focused ad group or hold it. Do not route consultants into an agency ad group just because both are professional services.
6. Explain the match-type choice without promising that Exact or Phrase will match only one literal query.
7. Add a measurement plan with the success metric, comparison window, conversion-delay allowance, and review date.

Return opportunities, already covered queries, and held queries. Mark every proposed keyword or new ad group "approval required". End with "No changes were made."

Guardrails

  • Use performance and business fit, not search volume alone.
  • Check current keywords, close intent, negatives, ad copy, and the final page before proposing a new keyword.
  • One ad group should answer one clear search job. Shared industry labels are not enough to mix different buyer intents.
  • If there is no credible page or message for the query, hold it rather than sending it to the homepage by default.
  • Adding a keyword or ad group changes delivery. This skill drafts the change and never executes it.

Good output looks like

A small coverage plan where every proposed keyword has evidence, a match-type reason, one clear ad-group home, a credible page, and an approval gate.

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.