agentleFS
kastriasanikastriasani/google-ads-skills/skills/google-ads-media-plan/SKILL.md

google-ads-media-plan

Skill1 starsChanged 5 months agoMITView on GitHub

Build a quarterly Google Ads media plan, budget, and 90-day rollout roadmap. Allocates a monthly or quarterly budget across campaign types (Brand Search, Non-brand Search, Shopping, Performance Max, Demand Gen, Display, YouTube) by CAC, CPA, and ROAS efficiency, with conservative, moderate, and aggressive scenarios and a phased launch plan. Use when the user asks to plan a Google Ads budget, build a paid search media plan or roadmap, split spend across campaign types, forecast conversions or ROAS, decide brand vs non-brand allocation, size a quarterly or monthly PPC budget, or plan a phased campaign rollout. Triggers on phrases like media plan, budget allocation, campaign roadmap, paid search forecast, how much should I spend on Google Ads, and quarterly PPC plan.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants to:

    line 19
  2. Very specific:

    If the user instead wants to build the actual account structure and upload file, use google-ads-campaign-setup.

    line 28
  3. Distinctive:

    Search Console: query and impression data to size non-brand opportunity.

    line 76
  4. Distinctive:

    When the user has no data, state that the numbers are benchmark estimates and must be re-forecast after 30 days of actuals.

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Media Plan

Turn a budget and a goal into an approved quarterly Google Ads media plan: how much to spend, on which campaign types, to hit which target, and in what order to launch. This is the planning document a client or finance team signs off on before a single campaign goes live.

When to use

Use this skill when the user wants to:

  • Plan or size a Google Ads budget for a month or quarter.
  • Decide how to split spend across campaign types (Brand, Non-brand Search, Shopping, Performance Max, Demand Gen, Display, YouTube).
  • Forecast conversions, CPA, or ROAS for a planned budget.
  • Settle the brand vs non-brand allocation question.
  • Produce a phased 90-day rollout roadmap with launch gates.

If the user instead wants to build the actual account structure and upload file, use google-ads-campaign-setup. If they want ad copy, use google-ads-ad-copy.

Workflow

  1. Gather the essentials. Ask only for what is missing: total budget and period (month or quarter), primary goal (lead gen or ecommerce sales), conversion definition, target CPA or target ROAS, and average revenue per conversion (AOV, or pipeline value x close rate for lead gen). If the user pastes a CSV of historical campaign performance, use those CPC and CVR numbers instead of defaults.
  2. Allocate the budget. Run scripts/budget_allocator.py to split the budget across campaign types by efficiency and produce conservative / moderate / aggressive scenarios. The script ranks each type by CPA (lead gen) or ROAS (ecommerce), nudges high-intent capture ahead of cold reach, and fills to realistic capacity ceilings. Example: python3 scripts/budget_allocator.py --budget 90000 --period quarter --goal sales --aov 120 Why: funding the demand you can convert most efficiently first protects CPA before you pay to create new demand. See references/budget-allocation.md.
  3. Forecast the ramp. Run scripts/growth_simulator.py to project month-by-month spend, conversions, revenue, and cumulative ROAS across three rollout paces (Steady / Balanced / Fast), accounting for the learning period and efficiency improvement. Example: python3 scripts/growth_simulator.py --start-budget 20000 --months 6 --cpa 45 --aov 120 Why: a budget total hides the truth that month 1 runs inefficiently while the account learns. The simulator shows when the plan reaches break-even.
  4. Assemble the plan. Fill in the sections in references/media-plan-template.md: summary, goal and economics, allocation table, scenario forecast, the 90-day phased rollout, measurement plan, and risks. Present the moderate scenario as the recommendation with conservative and aggressive as the sensitivity band.
  5. Sequence the rollout. Use the phased rollout table in the template. Launch high-intent capture first, prove CPA, then scale and add prospecting. State the exit gate for each phase so scaling is earned, not assumed.

Inputs and data sources

This skill runs standalone. The minimum input is a budget and a goal; the scripts ship with defensible benchmark defaults so they produce a full plan with no account data. Quality improves with real data:

  • Pasted CSV or numbers: historical CPC, CVR, CPA, or ROAS per campaign type. Pass overrides to the allocator via a --file JSON.
  • Google Ads API: pull actual campaign-type performance to replace benchmarks.
  • GA4: conversion values and assisted-conversion data for demand-gen channels.
  • Search Console: query and impression data to size non-brand opportunity.
  • Google Sheets / BigQuery: store the plan and forecast outputs for sharing.

When the user has no data, state that the numbers are benchmark estimates and must be re-forecast after 30 days of actuals.

Outputs

  • A quarterly media plan document following references/media-plan-template.md.
  • A budget allocation table across campaign types with shares and target CPA/ROAS.
  • A three-scenario forecast (conservative / moderate / aggressive).
  • A month-by-month ramp projection with break-even.
  • A 90-day phased rollout roadmap with per-phase launch gates.

References

  • references/media-plan-template.md - the full quarterly plan sections plus the 90-day phased rollout table and pacing rules.
  • references/budget-allocation.md - allocation frameworks, percentage splits by business model, the brand vs non-brand discipline, and the testing reserve.

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.