agentleFS
kastriasanikastriasani/google-ads-skills/skills/google-ads-ad-copy/SKILL.md

google-ads-ad-copy

Skill1 starsChanged 5 months agoMITView on GitHub

Write and validate Google Ads Responsive Search Ads and Performance Max assets against character limits, Ad Strength, and editorial policy. Generates headline and description variants from proven copy formulas, checks every asset against the 30 and 90 character limits, flags trademark, superlative, ALL CAPS, punctuation, and prohibited-claim policy risks, and estimates the Ad Strength rating (Poor, Average, Good, Excellent) with specific fixes. Use when the user wants to write Google Ads copy, create RSAs or responsive search ads, write PMax or Performance Max assets, generate ad headlines and descriptions, validate ad copy against character limits, check Ad Strength, review ads for policy or trademark issues, or improve a Poor or Average ad. Triggers on phrases like write Google Ads, RSA copy, ad headlines, ad descriptions, Ad Strength, character limit check, policy check, and Performance Max assets.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write Responsive Search Ad and Performance Max copy that fits Google's limits, passes editorial policy, and earns a Good or Excellent Ad …

    line 12
  2. Distinctive:

    Use this skill when the user wants to:

    line 18
  3. Distinctive:

    Write RSA headlines and descriptions, or PMax text assets.

    line 20
  4. Distinctive:

    Check or improve Ad Strength (turn a Poor/Average ad into Good/Excellent).

    line 22
  5. Very specific:

    Write the assets. Use the formulas in references/copy-frameworks.md.

    line 36

≈ “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 Ad Copy

Write Responsive Search Ad and Performance Max copy that fits Google's limits, passes editorial policy, and earns a Good or Excellent Ad Strength, then prove it with two validators before the copy ever reaches the account.

When to use

Use this skill when the user wants to:

  • Write RSA headlines and descriptions, or PMax text assets.
  • Validate existing ad copy against character limits and policy.
  • Check or improve Ad Strength (turn a Poor/Average ad into Good/Excellent).
  • Review ads for trademark, superlative, or prohibited-claim risk.

This skill produces the copy that the google-ads-campaign-setup CSV generator imports. Write the RSAs here, validate them, then add them to the structure JSON as the rsas for each ad group.

Workflow

  1. Gather the brief. Per ad group you need: the single query intent / keyword, the core value proposition, 1-2 proof points (numbers, customer counts), the offer (free trial, demo, pricing), and the final URL. One ad group = one intent = one ad; do not write a single ad to cover several themes.
  2. Write the assets. Use the formulas in references/copy-frameworks.md. For an RSA, write all 15 headlines spanning several angles (value props, features, social proof, CTAs, keyword-bearing) and 4 distinct descriptions. Lead with specifics and benefits, not the brand name, because search traffic is already high intent. Vary headline length so the set has short, medium, and long.
  3. Validate limits and policy. Run scripts/rsa_validator.py to check every asset against the 30 and 90 character limits and to flag ALL CAPS, excessive punctuation, trademarked terms, superlatives, prohibited phrases, and suspicious claims, scoring 0-100. Example: python3 scripts/rsa_validator.py --file rsa.json Fix everything until the score is at least 70 and no policy flags remain. Why: over-limit assets are rejected on import and policy violations get the ad disapproved. See references/policy-checklist.md.
  4. Estimate Ad Strength. Run scripts/ad_strength_estimator.py to predict the Poor / Average / Good / Excellent rating from headline count, uniqueness, keyword inclusion, length variety, formula signals, and pinning, and to get specific recommendations. Example: python3 scripts/ad_strength_estimator.py --file rsa.json --keyword "project management software" Iterate on the recommendations until the rating is Good or Excellent. Why: stronger ads win more auctions; this catches a weak ad before launch rather than after Google rates it. See references/rsa-pmax-specs.md.
  5. Hand off. Deliver the validated asset set. To launch, add it to the campaign-setup structure JSON as the ad group's rsas and regenerate the Editor CSV.

Inputs and data sources

This skill runs standalone. The validators ship with embedded --demo samples and accept pasted or filed JSON, so they work with zero account access. Quality improves with real inputs:

  • Pasted text or JSON: the value prop, proof points, offer, keyword, and final URL per ad group is enough to write and validate a full RSA.
  • Existing ads (paste or JSON): validate and improve copy you already run.
  • Google Ads API: pull live RSAs and their reported Ad Strength to prioritize which to rewrite.
  • GA4 / Search Console: find the highest-converting queries and benefits to lead the copy with.
  • Google Sheets: store approved asset sets and the validator output.

Outputs

  • A complete, validated RSA asset set (up to 15 headlines, 4 descriptions, paths, final URL) or PMax text asset group.
  • A limits-and-policy report with a 0-100 score and specific flags.
  • An estimated Ad Strength rating with prioritized recommendations.

References

  • references/rsa-pmax-specs.md - exact character limits and asset counts for RSA, PMax, and Responsive Display, plus how Ad Strength and pinning work.
  • references/copy-frameworks.md - headline and description formulas, the CTA library, persuasion angles, and anti-patterns.
  • references/policy-checklist.md - Google editorial and policy red flags: superlatives, claims, capitalization, trademark, clickbait, and landing-page message match.

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.