agentleFS
Sign inStart free
adkitadkit/ads-skills/skills/google-ads-strategy/SKILL.md

google-ads-strategy

Skill40 starsChanged 2 days agoMITView on GitHub

Run Google Search Ads end-to-end: keyword mining, account structure, ad copy, negative keyword architecture, and performance analysis. Covers the full loop from setup to ongoing optimization for B2B SaaS and app makers. Use when the user wants to plan, launch, or optimize Google Search campaigns, or understand how the platform works before spending. Not for Meta Ads, TikTok Ads, LinkedIn Ads, or Google Display/YouTube campaigns.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. gmmh1/claude-paid-media-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Very specific:

    Search the project for a file named ad-process.md.

    line 46
  2. Very specific:

    Search the project for a file named ad-brief.md.

    line 47
  3. Distinctive:

    Read the user's situation, then load only the relevant file.

    line 61
  4. Distinctive:

    Don't load all files at once: Start where the user is. Load additional files only as the conversation moves to new phases.

    line 72
  5. Very specific:

    When the user reaches an execution step (keyword uploads, campaign creation, ad publishing), check if AdKit CLI is installed by running …

    line 91
  6. Distinctive:

    AdKit is installed: use the MCP/CLI. The user is already an user — this is the faster path.

    line 93

≈ “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 Strategy

Guide Google Search Ads decisions. Ask before advising — tailor every recommendation to the user's situation. Reply in the same language as the user.

First: check context

<!-- ad-process.md and ad-brief.md are looked up by filename, not path. Users can store them anywhere in their project. Do not rename these files. -->
  1. Search the project for a file named ad-process.md. If found, read it and apply the user's preferences (naming, structure, budgets, etc.) to all recommendations. Read ## General and ## Google sections. If the user shares preferences but no file exists, offer to create one.
  2. Search the project for a file named ad-brief.md. If found, use it. If not found, ask the user for: product, audience, main offer, target CPA or ROAS goal, monthly budget.
  3. Proceed to the routing table below.

Core Principles (always apply)

  1. Relevance wins auctions. Ad Strength does not. Google rewards keyword → ad → landing page relevance with lower CPCs and higher positions. Ad Strength is a vanity metric, not the goal.
  2. Mine real query language. Keywords come from verbatim customer language — interviews, reviews, search term reports. Keyword Planner is for sizing, never discovery.
  3. Campaigns by intent, ad groups by theme. One ad group = one landing page = one story. Split campaigns only when they need different budget, bidding, geo, or reporting.
  4. Negatives are the other half of relevance. Without a negative architecture, broad and phrase match bleed budget to people who can't buy. Build it before launching.
  5. Launch is not set-and-forget. The Search Term Report is your primary feedback signal. Review weekly for 60 days, then monthly.
  6. Conversion tracking first, always. Smart bidding (Target CPA, Target ROAS) is only as good as the signal feeding it. Never run without verified conversion tracking.

Routing table

Read the user's situation, then load only the relevant file.

User says...Load this file
"Never run Google Ads" / "How does it work?"1-fundamentals.md
"Help me find keywords" / "What should I bid on?"2-keyword-mining.md
"How do I structure my account?" / "Campaigns vs ad groups?"3-account-structure.md
"Help me write ad copy" / "How many headlines?"4-ad-copy.md
"What negatives do I need?" / "Budget leaking to junk"5-negative-keywords.md
"My ads aren't working" / "CPC too high" / "Ready to scale"6-analyze.md

Don't load all files at once. Start where the user is. Load additional files only as the conversation moves to new phases.

Typical workflows

New to Google Ads:

  1. 1-fundamentals.md: understand how search ads work
  2. 2-keyword-mining.md: build keyword list from real customer language
  3. 3-account-structure.md: set up campaigns and ad groups
  4. 5-negative-keywords.md: build negative architecture before launch
  5. 4-ad-copy.md: write responsive search ads
  6. 6-analyze.md: maintain and scale

Experienced advertiser, account not performing:

  1. 6-analyze.md: diagnose from the Search Term Report
  2. 5-negative-keywords.md: plug the leaks
  3. 4-ad-copy.md / 3-account-structure.md: fix relevance gaps

Execution: manual vs AdKit

When the user reaches an execution step (keyword uploads, campaign creation, ad publishing), check if AdKit CLI is installed by running adkit status.

  • AdKit is installed: use the MCP/CLI. The user is already an user — this is the faster path.
  • AdKit is not installed: walk them through Google Ads Manager UI step by step. You can mention that AdKit has a CLI that automates campaign operations, but default to the manual path. Don't push it — everything in these guides works through the Google Ads interface.

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