agentleFS
gomarble-aigomarble-ai/marketing-agent/skills/google-impression-share/SKILL.md

google-impression-share

Skill15 starsChanged 36 days agoMITView on GitHub

Google Ads impression-share analysis to identify missed scaling opportunities and diagnose delivery constraints. Distinguishes Lost-IS (Budget) — addressable with money — from Lost-IS (Rank) — addressable with bids/quality. Disciplined: only recommends scaling on campaigns that are already profitable (≥30 conversions in 30d AND CPA at/below target). Read-only — recommends budgets, bids, holds; never executes. Use weekly or when planning where to deploy more spend.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user didn't name an account, list their connected accounts and ask which one to use.

    line 11

≈ “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 Impression Share Analysis (Read-Only)

For the Google Ads account the user names, analyze impression-share metrics across all active campaigns. Read-only — recommends only, never adjusts budgets or bids.

If the user didn't name an account, list their connected accounts and ask which one to use.

Constraints (do not violate)

  • Only consider campaigns with ≥ 30 conversions in last 30 days. Below that, the signal is too noisy.
  • Do not recommend budget increases for campaigns with CPA > 1.2× target. Throwing money at unprofitable campaigns wastes money.
  • Do not recommend bid increases if already above target CPA. Same logic.
  • Prioritize profitable scaling only.

Inputs (per campaign, last 30d)

  • Search Impression Share
  • Lost IS (Budget)
  • Lost IS (Rank)
  • Conversion volume + CVR
  • CPA vs target
  • ROAS
  • Current daily budget

Analysis buckets

Bucket A — Scaling opportunity (high Lost-IS Budget + strong CPA)

  • Lost IS (Budget) ≥ 20% AND CPA ≤ target
  • Recommendation: budget increase. Suggest exact % based on how much budget headroom the IS gap implies.

Bucket B — Bid / relevance issue (high Lost-IS Rank + good CVR)

  • Lost IS (Rank) ≥ 20% AND CVR ≥ campaign median
  • Recommendation: bid adjustment OR ad-strength / quality-score work. Suggest which.

Bucket C — Overexposure (high IS + poor CPA)

  • Search IS ≥ 75% AND CPA > target
  • Recommendation: HOLD. Do not scale. Profitability problem, not a reach problem.

Bucket D — Healthy (high IS + good CPA)

  • Search IS ≥ 80% AND CPA ≤ target
  • Recommendation: monitor. You're maxed out on demand for current keywords; growth requires new keyword expansion or new campaign types.

Output format

Three sections, each a vertical list:

📈 Scale (recommend budget increase)

  • [Campaign] — Lost IS (Budget) 32%, CPA 22% under target. Suggest +30% budget, expected +N conversions/day.

🔧 Fix (recommend bid / quality work)

  • [Campaign] — Lost IS (Rank) 28%, strong CVR. Suggest bid +15% OR ad-copy refresh — ad strength is "Average".

🛑 Hold (no action recommended)

  • [Campaign] — Overexposed (IS 88%, CPA 38% above target). Fix profitability before scaling.

For each campaign that hits the conversion-volume floor (< 30 conv / 30d), exclude it silently.

End with: _All recommendations — no budgets or bids changed. Ask explicitly to enact any of these._

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.