Skip to content
SkillModel-led152 tokens in use

ads-math

Calculate CPA, CPL, ROAS, MER, break-even, LTV:CAC and budget forecasts with the formula shown, every input mapped, and downside and upside cases.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-math
/plugin install claude-ads@ai-marketing-hub-claude-ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing ads-math costs

77tokens idle
152tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure11/25
  • Examples0/15
  • Output12/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity84
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

ads-math is a paid-media calculator that works in the open. It identifies the decision, collects units, currency, period, tax and refund treatment, margin and attribution basis, then shows the formula and maps each input to a value you gave or a cited source.

It validates denominators, signs, missing values and incompatible windows, and runs base, downside and upside cases where uncertainty changes the answer.

What You Get

  • A worked calculation with the formula shown and every input traced to its source
  • Base, downside and upside cases when uncertainty affects the decision
  • Machine-readable inputs, formulas, outputs and sensitivities
  • A statement of what the result means for the decision you asked about

Common Use Cases

  • Working out a break-even ROAS or CPA from margin
  • Forecasting a budget under different conversion assumptions
  • Comparing platform-attributed revenue with blended business revenue
  • Checking the economics of an experiment before running it

What Makes It Unique

The skill keeps platform-attributed revenue, blended business revenue, cash flow and contribution margin separate, so a ROAS figure is not read as profit. It refuses to fabricate missing financial inputs, to hide division by zero, or to give a point forecast without stating its assumptions.

Under The Hood

The skill is a short instruction file with no scripts, network calls or file writes of its own. The agent does the arithmetic in the conversation, checks units, currencies and time windows, and returns structured inputs, formulas and outputs. It relies on numbers you supply or cite and asks for missing ones.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers