agentleFS
kastriasanikastriasani/google-ads-skills/skills/google-ads-campaign-setup/SKILL.md

google-ads-campaign-setup

Skill1 starsChanged 5 months agoMITView on GitHub

Design a Google Ads account structure and produce a Google Ads Editor bulk-upload CSV ready to import. Builds the campaign, ad group, keyword, match-type, and negative-keyword tree with proper naming conventions, then generates the exact Editor-compatible CSV. Use when the user wants to set up a new Google Ads account or campaign, build account structure, organize campaigns and ad groups, choose match types, create keyword and negative keyword lists, generate a Google Ads Editor import or bulk upload file, produce an Editor CSV, or run a pre-launch checklist before going live. Triggers on phrases like set up Google Ads, build campaign structure, account structure, Editor CSV, bulk upload, import file, keyword match types, negative keywords, and pre-launch checklist.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants to:

    line 18
  2. Very specific:

    If the user instead needs to plan budget and allocation across campaign types, use google-ads-media-plan.

    line 26
  3. Very specific:

    Add ad copy. RSAs come from google-ads-ad-copy.

    line 51
  4. Very specific:

    Run the pre-launch gate. Walk references/launch-checklist.md before any spend.

    line 65
  5. Distinctive:

    Search Console / GA4: identify high-value queries and conversion pages to seed themes and landing-page final URLs.

    line 77

≈ “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

Google Ads Campaign Setup

Turn a brief into a launch-ready Google Ads account: a clean campaign and ad group structure with the right match types and negatives, then the exact Google Ads Editor CSV you import to build it all in one pass.

When to use

Use this skill when the user wants to:

  • Set up a new Google Ads account or a new set of campaigns.
  • Design account structure: campaigns, ad groups, keyword themes, match types.
  • Build negative keyword lists.
  • Generate a Google Ads Editor bulk-upload CSV / import file.
  • Work through a pre-launch checklist before turning on spend.

If the user instead needs to plan budget and allocation across campaign types, use google-ads-media-plan. If they need the actual ad copy, use google-ads-ad-copy, then feed its RSAs back into the CSV generator here.

Workflow

  1. Gather the brief. Ask only for what is missing: brand name, vertical / what they sell, geo, monthly budget, goal (lead gen or ecommerce sales), and a list of keyword themes (the distinct things people search for). If the user has existing keyword research, use it; otherwise the structure builder seeds a starter set per theme.
  2. Build the structure. Run scripts/campaign_structure_builder.py to generate the recommended account tree: a Brand campaign (Exact match, capped budget), a Non-brand campaign with one tight ad group per theme, seed keywords in Phrase and Exact, the universal negative list, and consistent GOOG_Type_Theme_Geo naming. Example: python3 scripts/campaign_structure_builder.py --brand "Acme" --vertical "project management software" --geo US --budget 15000 --goal leads --themes "project management,team collaboration,task tracking" --json Why one theme per ad group: a single ad can only be relevant to one query intent, and relevance drives Quality Score. See references/account-structure.md.
  3. Review and adjust the structure. Walk the user through the outline (omit --json for the readable view). Confirm themes, match types, and the brand/non-brand budget split. Edit the JSON directly for any changes.
  4. Add ad copy. RSAs come from google-ads-ad-copy. Add an rsas list to each ad group in the structure JSON (headlines, descriptions, paths, final URL). The structure builder leaves an rsa_brief per ad group describing what each ad should say.
  5. Generate the import CSV. Run scripts/editor_csv_generator.py to emit a Google Ads Editor compatible bulk CSV. It writes one flat table with the real Editor column headers; campaign, ad group, keyword, negative, and RSA rows are distinguished by which columns are filled. Example: python3 scripts/editor_csv_generator.py --file structure.json > import.csv Why: Editor imports a single flat CSV with blank cells for unused columns; getting the headers and Criterion Type values exactly right is what makes the import succeed. See references/editor-csv-format.md.
  6. Run the pre-launch gate. Walk references/launch-checklist.md before any spend. Conversion tracking working and tested is a hard gate, not a nice-to-have.

Inputs and data sources

This skill runs standalone from a pasted brief. Quality improves with real data:

  • Pasted text: brand, vertical, geo, budget, goal, and keyword themes is enough to produce a full structure and CSV.
  • Existing keyword research (CSV or paste): replace the seed keywords with the user's researched terms in the structure JSON.
  • Google Ads API: pull existing account structure to extend rather than duplicate.
  • Search Console / GA4: identify high-value queries and conversion pages to seed themes and landing-page final URLs.
  • Google Sheets: store and share the structure JSON or the generated CSV.

Outputs

  • A recommended account structure (readable outline + structure JSON).
  • Seed keyword sets per theme with launch match types (Phrase + Exact).
  • A universal negative keyword list applied at the campaign level.
  • A Google Ads Editor compatible bulk-import CSV ready to post.
  • A completed pre-launch checklist.

References

  • references/account-structure.md - hierarchy, campaign priority, one-theme-per ad-group rule, match-type strategy, naming conventions, bid-strategy progression.
  • references/launch-checklist.md - the pre-launch gate (tracking, audiences, extensions, brand protection) and the Editor import steps.
  • references/editor-csv-format.md - the exact Editor column headers, Criterion Type values, and per-row recipes.
  • references/negative-keyword-lists.md - the universal negatives, the four negative-list categories, match types, and search-terms-report mining.

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.