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.
npx skills add swan-gtm/gtm-skills --skill google-adsgit clone --depth 1 https://github.com/swan-gtm/gtm-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/swan-gtm/gtm-skills/google-ads)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/google-ads"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/google-ads/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/google-ads"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/google-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.01260 |
| Opus 5.5 | $0.00037 | $0.00504 |
| Sonnet 5.5 | $0.00018 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
google-ads 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Ads Management
Orchestrator for Google Ads strategy and campaign management. It grounds every recommendation in a consistent B2B demand-generation methodology.
Methodology
This skill implements an intent-first B2B demand generation approach for Google Ads. It captures existing demand through systematic keyword targeting, proves unit economics on the highest-intent terms first, then expands outward.
Core Philosophy
Intent is everything. Capture demand before you create it.
Google Ads is the strongest channel for capturing existing demand. People are actively searching for solutions - the job is to be there at the right moment with the right message. Start with high-intent keywords (brand and solution-aware), prove unit economics, then expand outward to medium and low intent, and finally to awareness.
Knowledge Base
Ground all strategy in these files. Read the relevant one before advising.
| File | Contains | Read When |
|---|---|---|
| references/intent-first-strategy.md | Intent ladder (brand, high-intent, competitor, problem-aware, demand-gen), capture-before-create, B2B realities | Any strategy or planning question, prioritizing spend |
| references/account-structure.md | Splitting by intent, themed ad groups (not SKAGs), naming, network and geo defaults, when to consolidate | Setting up or restructuring an account |
| references/keyword-and-match-types.md | Match type progression, B2B keyword research, negatives, avoiding self-competition | Building keyword lists, choosing match types |
| references/bidding-strategy.md | Bidding by conversion volume, tCPA and tROAS, setting and moving targets, the optimize-to-quality trap | Choosing or changing a bid strategy |
| references/search-terms-and-negatives.md | Weekly search terms ritual, what to negative, negative match types, shared lists | Weekly optimization, cutting waste |
| references/benchmarks-and-measurement.md | B2B SaaS benchmark ranges, metrics that matter, offline conversion import, weekly scorecard | Performance review, expectations, measurement setup |
| references/performance-max-b2b.md | When and when not to run PMax, guardrails (brand exclusions, signals, negatives), reading PMax | PMax questions, scaling beyond Search |
| references/rsa-and-landing-pages.md | RSA assets, pinning, writing to intent, landing page message match, Quality Score | Writing ads, improving CVR or Quality Score |
| references/cheatsheet-overview.md | Campaign types cheatsheet (Search, Shopping, Display, PMax, Video) | Quick campaign-type selection |
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/account-structure.md 2.6 KB
- references/benchmarks-and-measurement.md 2.3 KB
- references/bidding-strategy.md 2.7 KB
- references/cheatsheet-overview.md 1.4 KB
- references/intent-first-strategy.md 2.9 KB
- references/keyword-and-match-types.md 2.4 KB
- references/performance-max-b2b.md 2.3 KB
- references/rsa-and-landing-pages.md 2.6 KB
- references/search-terms-and-negatives.md 2.3 KB
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.
- 1mo ago First seen · 88 lines · 92 tokens per session scan A 63b47b79ea0d
google-ads is a skill published in the GitHub repository swan-gtm/gtm-skills (221 stars, last pushed 8d ago), licensed MIT. It adds 92 tokens to every session and 1,260 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.
paid-ad-copy-writer
Write paid ad copy for affiliate offers across ad platforms. Triggers on: "write ad copy", "Facebook ad for affiliate", "Google Ads copy", "TikTok ad script", "Pinterest ad", "paid traffic to affiliate", "create ad campaign", "ad headlines", "ad descriptions", "scale with paid ads", "run ads for my affiliate link"…
gooseworks
GooseWorks growth coworker and router for markets, competitors, audiences, creators, campaigns, ads, photos, graphics, video, content, email, SEO, social, leads and contacts. Use for brand facts or copy too, so offers, prices, rules, audience and bestsellers reach the brand's Marketing Brain.
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
yandex-direct
Skill "yandex-direct" from VKirill/claude-lane-stack, covering version requirements, usage, use this skill when, do not use this skill when and purpose.
yandex-direct-creatives
An advertising-writing guide for Yandex.Direct, a Russian online advertising platform. It turns keyword clusters from Key Collector, a keyword research tool, into campaigns, ad groups, and ads.