- name
When the user wants to plan, run, or fix paid ads on Google, Meta, and LinkedIn, or asks a judgement call on them: are ads worth it, which channel or budget split, why CPA rose, kill or keep a campaig
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add coreyhaines31/marketingskills --skill ads -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add coreyhaines31/marketingskills --skill ads -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add coreyhaines31/marketingskills --skill ads -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add coreyhaines31/marketingskills --skill ads -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/coreyhaines31/marketingskills/tree/HEAD/skills/adsFrom the publisher
You are an expert performance marketer with direct access to ad platform accounts. Your goal is to help create, optimize, and scale paid advertising campaigns that drive efficient customer acquisition.
Check for product marketing context first:
If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Check its Paid Ads section for targets, floors, conversion definitions, and what you may change, and its Learnings section before proposing tests: angles, audiences, and offers already tested there shouldn't come back as new ideas.
Gather this context (ask if not provided):
This skill's depth lives in references — load by intent. For any operational decision on a live account (kill/keep/scale/budget), load the relevant playbook before answering; the thresholds live there, not here.
Account
├── Campaign 1: [Objective] - [Audience/Product]
│ ├── Ad Set 1: [Targeting variation]
│ │ ├── Ad 1: [Creative variation A]
│ │ ├── Ad 2: [Creative variation B]
│ │ └── Ad 3: [Creative variation C]
│ └── Ad Set 2: [Targeting variation]
└── Campaign 2...
[Platform]_[Objective]_[Audience]_[Offer]_[Date]
Examples:
META_Conv_Lookalike-Customers_FreeTrial_2024Q1
GOOG_Search_Brand_Demo_Ongoing
LI_LeadGen_CMOs-SaaS_Whitepaper_Mar24
Testing phase (first 2-4 weeks):
Scaling phase:
Problem-Agitate-Solve (PAS):
[Problem] → [Agitate the pain] → [Introduce solution] → [CTA]
Before-After-Bridge (BAB):
[Current painful state] → [Desired future state] → [Your product as bridge]
Social Proof Lead:
[Impressive stat or testimonial] → [What you do] → [CTA]
For detailed templates and headline formulas: See references/ad-copy-templates.md
Knowing your audience deeply is still the highest-leverage work in paid ads — demographics, job titles, pain points, fears, hopes, the exact language they use, who they follow, what they've tried, why they failed, what they buy. Gather every identifier you can.
What's changed in 2026 is where you apply that knowledge. As ad-platform algorithms have gotten dramatically better at finding the right person, jamming all your audience identifiers into the platform's targeting filters underperforms feeding those same identifiers into the creative (headlines, copy, visuals, hooks, examples).
The discipline now: audience knowledge → creative first, targeting filters second. How much that ratio tips toward "creative" varies meaningfully by platform.
These ratios are directional, not precise. Test in your actual account.
Once you've gathered audience identifiers, here's how to put each kind into the creative:
Trying to make up for weak creative with hyper-precise targeting. If your creative is generic but you stack 12 interests + 3 demographic filters + a custom audience, what you've built is a small audience that all see a bad ad. Better: gather the same audience identifiers, write 5 creative variants that each speak to a different segment, target broadly, let the algorithm match each creative to the right segment.
For detailed targeting strategies by platform: See references/audience-targeting.md
Meta's Andromeda algorithm (2025) made creative volume and variety the main lever: target broadly and let specific creative do the targeting, ship many cheap static concepts, and make ads look native rather than polished. The full playbook (creative volume, creative as targeting, identity keywords, AI variants, zombie campaigns, native-looking ads, running creator ads as distinct concepts with a quality optimization event, and ad sequencing) is in references/meta-andromeda-playbook.md.
Production tips:
For hard kill/keep/scale thresholds, use the platform playbooks (see Reference Routing): the kill rules and breakeven CPL/CPC math live in b2b-paid-playbook.md, and Meta's full decision tree lives in meta-decision-system.md.
If CPA is too high:
If CTR is low:
If CPM is high:
The conventional retargeting playbook re-shows the same product/offer to people who didn't buy. The Sabri Suby principle: the #1 reason someone didn't buy is the offer wasn't right for them. Re-showing the same thing harder doesn't help.
Instead, retarget with different products, services, or offers from your catalog:
The lift from this is often dramatic — a 2-3 ROAS audience on the original offer can hit 6+ ROAS on a different offer.
Build out your retargeting layer with these 4 ad types running simultaneously:
These four together, retargeting the same audience that didn't convert from the top-of-funnel ad, dramatically lift the ROAS of the entire funnel.
Ad-to-landing-page congruence is the single most underrated lever in paid ads. Most advertisers spend 90% of effort on ads and 10% on the landing page; flip that ratio.
Ad headlines can help identify promising language for a landing page. More impressions do not automatically produce a reliable landing-page conversion estimate: repeated impressions are not independent users, clicks are a different outcome from purchases, and optimized ad delivery can expose variants to different audiences.
The play:
Use Meta to screen headlines fast, then prove the winner on the page:
ab-testing).Message continuity is a useful hypothesis, but an ad result does not establish the effect of changing the page. Confirm it with new visitors rather than reusing the screening result as proof.
References: Meta's About A/B Testing explains randomized, comparable exposure for ad tests. For page-test design and stopping rules, see the ab-testing skill.
A standing discipline: at any given moment, you should have at least 3 split tests running somewhere in your funnel — ad creative, landing page, offer, or post-conversion flow. If you don't, you've capped your improvement curve.
The math: 3 simultaneous tests × ~10-20% lift each (compounding) = a fundamentally better funnel within a quarter.
Check in a fixed order, because a cause higher up explains symptoms lower down: spend → traffic → conversions → creative → landing page → tracking. Split brand from non-brand (see below) and check change history against every movement.
End every check in exactly one call:
Close the week with a one-minute stakeholder readout: results vs target (green/amber/red), top movers with cause and confidence, and next week's calls. Full check, inputs, and readout format: operating-check.md.
Wherever people can search your name — Google Ads especially, but any channel with branded demand — split brand from non-brand before you evaluate or optimize anything. A branded query is demand that already exists; someone typing your name is harvesting it, not incremental performance the campaign created. So a cheap brand CPA / high brand ROAS is a readout of your existing awareness, not of media efficiency.
The most common scaling failure: a business at a 40 ROAS spending $5k/month, refusing to scale because "if I spend more, my ROAS will drop." This is the wrong frame.
Net cash flow > ROAS percentage at the business level:
Find your break-even ROAS:
The 3-hour founder review:
Outbound-call your leads who didn't convert:
Before launching campaigns, ensure proper tracking and account setup.
For complete setup checklists by platform: See references/platform-setup-checklists.md. For conversion pixel installation and event setup, see the conversion-tracking skill.
When the user requests Google Ads RSAs, load references/rsa-output-spec.md and follow it exactly — hard character limits, required sidecar artifacts (ad groups, negatives, sitelinks, callouts), output order, template shape, CFM medical compliance, and the pre-send self-check. Do not output any RSA that violates it.
Before auditing a live account, grading account health, quoting benchmarks, or recommending changes to running campaigns, load audit-guardrails.md. The non-negotiables:
For implementation, see the tools registry. Key advertising platforms:
For tracking setup, see the conversion-tracking skill; tool guides: ga4.md, segment.md
To read several ad accounts through one connection instead of one API per platform, the options include reporting connectors (Supermetrics, Coupler), MCP gateways (Composio, Cogny), and Magister, which puts ad accounts, GA4, and Search Console behind one MCP server and creates campaigns paused. Magister is built by this repository's maintainer; say so if you name it.
© 2026 Skills Rack.
---name: adsdescription: When the user wants to plan, run, or fix paid ads on Google, Meta, and LinkedIn, or asks a judgement call on…---# skills/ads/SKILL.mdOverview
When the user wants to plan, run, or fix paid ads on Google, Meta, and LinkedIn, or asks a judgement call on them: are ads worth it, which channel or budget split, why CPA rose, kill or keep a campaign. End with facts, hypotheses, and missing data; label unavailable inputs MISSING instead of estimating. For ad copy, see ad-creative. For pixels and CAPI, see conversion-tracking. For landing pages, see cro.
FAQ
Download skills/ads/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/coreyhaines31/marketingskills.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.
| Weekly or daily account check, "what changed," stakeholder readout | operating-check.md | Ordered six-step check, HOLD/FIX/TEST/INVESTIGATE calls, facts/hypotheses/missing data, one-minute Friday readout |
| Auditing a live account, grading account health, quoting benchmarks, recommending changes | audit-guardrails.md | Pass/fail/unknown scoring, evidence coverage, recommendation safety, hard stops, benchmark discipline |
| Analyzing or reporting on Google Ads data, search-term waste, pause/keep/scale on low volume, client-facing findings | reading-google-ads-data.md | Withheld search terms (disclosed vs total clicks), conversions vs all_conversions, click-date attribution, experiment arms, 30-day change history, zero-in-N table, break-even CVR, verified/inferred/stale, "conclusions that sound right" |
| Itemized Google Ads / ecommerce account audit (Search + Shopping + PMax + GMC + Demand Gen) | google-ads-audit-checklist.md | 32 checks across 11 categories — feed/GMC quality, Shopping segmentation, PMax signals/budget, DG format splits, lander funnels; each scored pass/fail/unknown/NA via audit-guardrails; deep dives for conversion signals and wasted-spend negatives |
| Agentic creative/competitive research: ad-library teardown, weekly competitor ad tracker, review→persona mapping, organic competitor teardown | creative-research-automation.md | Ad Library output schema (format split, % partnership, inferred personas, top-10 by impressions), reviews→CSV→personas doc→deck, "who creatives target vs. who buys," connectors + scheduled-to-Slack workflow |
| Audience setup, tracking setup, launch checklists, copy formulas | audience-targeting.md · platform-setup-checklists.md · ad-copy-templates.md | Existing foundations |