memstack-marketing-google-ad

A planner for paid advertisements that appear in Google search results and other Google ad placements.

In plain words
What is it for?
Creating keyword groups, ad headlines and descriptions, bidding plans, ad extensions, and plans for improving Google’s ad relevance score.
Why use it?
It helps organize search terms and ad text so campaigns target relevant searches and avoid wasting budget on unrelated ones.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/cwinvestments/memstack/google-ad
Any agent
npx skills add cwinvestments/memstack --skill google-ad
Clone the repo
git clone --depth 1 https://github.com/cwinvestments/memstack

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00067 $0.02801
Opus 5 $0.00034 $0.01401
Sonnet 5 $0.00013 $0.00560
Haiku 4.5 $0.00007 $0.00280

Measured 2d ago against content hash a5a141f44fa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memstack-marketing-google-ad scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/marketing/google-ad/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Designs search and display campaigns with keyword groups, bidding strategy, responsive search ads, ad extensions, and Quality Score optimization for Google Ads.

Activation

When this skill activates, output:

Google Ad — Creating Google Ads campaign...

Then execute the protocol below.

Context Guard

Context Status
User says "Google ad", "search ad", "PPC", "Google Ads" ACTIVE
User says "responsive search ad" or "ad extensions" ACTIVE
User wants to run paid search or display campaigns ACTIVE
User wants Facebook/Meta/Instagram ads DORMANT — use Facebook Ad
User wants organic SEO ranking DORMANT — use SEO skills

Common Mistakes

Mistake Why It's Wrong
"Bid on your brand name? That's free in organic" Competitors bid on your brand. Brand campaigns have 5-10x ROAS and protect your traffic.
"Use broad match for everything" Broad match burns budget on irrelevant queries. Start with phrase and exact match.
"One ad group, all keywords" Keyword-to-ad relevance drives Quality Score. Group tightly themed keywords (5-15 per ad group).
"Set it and forget it" Check search term reports weekly. Negative keywords save 20-30% of wasted spend.
"More keywords = more traffic" 10-20 high-intent keywords outperform 200 broad keywords every time.

Protocol

Step 1: Gather Campaign Requirements

If the user hasn't provided details, ask:

  1. Product/service — what are you advertising? (name, URL, price point)
  2. Campaign type — Search, Display, Shopping, or Performance Max?
  3. Target location — countries, states, cities, or radius?
  4. Monthly budget — total ad spend available?
  5. Goal — sales, leads, phone calls, or website traffic?
  6. Competitors — who else bids on these terms?

Step 2: Keyword Research & Grouping

Keyword intent tiers:

Tier Intent Match Type Example Priority
Tier 1 Bottom-funnel (buy now) Exact [buy crm software] Highest
Tier 2 High-intent (solution-aware) Exact/Phrase "best crm for small business" High
Tier 3 Mid-intent (problem-aware) Phrase "how to manage customer data" Medium
Tier 4 Brand terms Exact [your brand name] Always on

Read the full file on GitHub · 289 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 289 lines · 67 tokens per session scan A a5a141f44fa9

Subscribe to this mod's changes

memstack-marketing-google-ad is a skill published in the GitHub repository cwinvestments/memstack (417 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 2,801 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

frontend-design-landing-page

Marketing landing page and conversion-focused product page reference. Use this skill when building hero sections, feature grids, pricing pages, testimonials, CTAs, footers, navigation bars, or any public-facing marketing surface. Covers a warm, professional, developer-friendly design language (cream backgrounds…

cloudflare/vibesdk · 106 tokens

plan-ceo-review

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…

GCWing/BitFun · 143 tokens

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, and create a PR. Use for an explicit /ship invocation or when the user requests the full ship, release, or deploy workflow. For an ordinary commit, push, or pull-request publishing request, use the built-in…

GCWing/BitFun · 88 tokens

design-review

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…

GCWing/BitFun · 125 tokens

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…

GCWing/BitFun · 116 tokens

pre-landing-review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…

GCWing/BitFun · 74 tokens