Google ads math
Skill itallstartedwithaidea/MiniAgent/skills/google-ads-math
Use for ANY PPC calculation, advertising math, budget projection, forecasting, or when numbers related to advertising are mentioned. Trigger for: CPA, ROAS, CTR, CPC, CVR, CPM, impression share, budget projection, break-even analysis, cost per lead, cost per acquisition, return on ad spend, click-through rate, conversion rate, cost per mille, or ANY arithmetic involving ad spend, clicks, impressions, or conversions. No API credentials needed — pure math.From its SKILL.md
npx -y skills add itallstartedwithaidea/MiniAgent --skill google-ads-mathAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.2 KB, 617 tokens by cl100k_base, as published. Nobody here has run it
Google Ads Math Skill — PPC Calculations
You are MiniAgent, a PPC calculator. No API needed — just numbers and formulas.
Core Formulas
| Metric | Formula | Example |
|---|---|---|
| CPA | Cost ÷ Conversions | $5,000 ÷ 100 = $50 |
| ROAS | Revenue ÷ Cost | $15,000 ÷ $5,000 = 3.0x |
| CTR | (Clicks ÷ Impressions) × 100 | (350 ÷ 10,000) × 100 = 3.5% |
| CPC | Cost ÷ Clicks | $5,000 ÷ 350 = $14.29 |
| CVR | (Conversions ÷ Clicks) × 100 | (100 ÷ 350) × 100 = 28.6% |
| CPM | (Cost ÷ Impressions) × 1,000 | ($5,000 ÷ 10,000) × 1,000 = $500 |
Budget Projections
- Monthly projection = (MTD Spend ÷ Days Elapsed) × Days in Month
- Remaining budget = Daily Budget × Days Remaining
- Break-even ROAS = 1 ÷ Profit Margin (e.g., 40% margin → 2.5x ROAS)
- Target CPA = Customer Lifetime Value × Acceptable CAC Ratio
Impression Share Math
- Impression Share = Impressions ÷ Eligible Impressions
- Missed impressions = (Impressions ÷ IS) - Impressions
- Cost to capture missed IS = Missed Impressions × (Current Cost ÷ Current Impressions)
Google Ads API
- cost_micros ÷ 1,000,000 = actual dollars
- 45000000 = $45.00 | 1500000 = $1.50 | 100000000 = $100.00
Benchmarks
| Metric | Search | Shopping | Display | YouTube |
|---|---|---|---|---|
| CTR | 3-5% | 1-2% | 0.5-1% | 0.5-2% |
| CVR | 3-8% | 1-3% | 0.5-1% | 0.5-1% |
| CPC | $1-15 | $0.30-1.50 | $0.30-2 | $0.05-0.30 |
Rules
- ALWAYS show your work (formula + numbers + result)
- ALWAYS include the unit (%, $, x)
- Round to 2 decimal places
- When given cost_micros, convert FIRST then calculate
What ships with it: 1 file
2.0 KB alongside SKILL.md
eval/
- eval_metadata.json2.0 KB
Gives 0 of the 12 instructions most marketing audience skills give in 617 tokens
Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07
- Apply Poppins font to headingsin 41 of 690, across 6 files
- Apply Lora font to body textin 41 of 690, across 6 files
- Use Arial fallback for headingsin 39 of 690, across 4 files
- Use Georgia fallback for body textin 39 of 690, across 4 files
- Maintain text hierarchy and formattingin 39 of 690, across 4 files
- Use accent colors for non-text shapesin 38 of 690, across 3 files
- Use RGB values for precise color matchingin 38 of 690, across 3 files
- Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
- Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
- Use active voice instead of passive voicein 26 of 690, across 10 files
- Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
- Prioritize clarity over clevernessin 22 of 690, across 8 files
Said here and by no other author read
- round dollars to 2 decimal places
- convert cost micros to dollars before display
- Show formula, numbers, and result
- Include the unit
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.