
Paid Media Math Model
Calculates ad metrics like CPA, ROAS and break-even with clear assumptions and scenarios.
- Repository
- AgriciDaniel/claude-ads
- Stars
- 10,667
- Licence
- MIT
- Files
- 1 file
What it does
Once installed, the agent handles paid advertising money questions in a structured way. It works out metrics such as cost per acquisition, return on ad spend, break-even targets, lifetime value to acquisition cost ratio and budget forecasts, showing each formula and its inputs. It also asks for missing numbers instead of guessing, flags problems like division by zero, and separates ad-platform revenue from total business revenue and profit.
Great for
- Marketers who need to check whether a campaign pays back before spending more
- Small business owners building a simple budget or break-even forecast
- Analysts who want ad economics laid out with base, downside and upside cases
Skip it if
- Filing taxes or making formal financial reports, since the skill is a modeling aid and does not verify accounting treatment
- Decisions based on numbers you have not checked, because the output is only as reliable as the inputs you supply
Try asking
- “What is my break-even CPA if my product margin is 40 percent and refunds are 5 percent?”
- “Build a ROAS calculator for a $10,000 monthly budget with base, downside and upside cases.”
- “Calculate LTV to CAC for my subscription business using these figures: ...”
- “Forecast next quarter's budget for three campaigns and show the assumptions behind each number.”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
ads-math.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip ads-math.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip ads-math.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Give the agent your margin, currency, time period and whether revenue is platform-reported or business-reported before asking for results.
- Ask for sensitivities to see which input changes the decision the most.
- Check the assumptions the agent lists, since it will not invent missing financial inputs.
What's inside
- SKILL.md
Redistributed unmodified from AgriciDaniel/claude-ads under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.