Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
ads-math - Skill - OpenSmartRoute
Skillv1.0.0
ads-math
Calculate and model paid-media CPA, CPL, CPC, CPM, ROAS, MER, break-even targets, contribution margin, LTV:CAC, impression-share opportunity, budgets, forecasts, and experiment economics.
Imported from agricidaniel/claude-ads (skills/ads-math/SKILL.md) via skills.sh. Install upstream with npx skills add agricidaniel/claude-ads --skill ads-math. Copyright stays with the author.
Paid Media Financial Model
Identify the decision and collect units, currency, period, tax/refund treatment,
margin, attribution basis, and uncertainty.
Show the formula and map every input to an operator value or cited artifact.
Validate denominators, sign, missing values, incompatible windows, and unit
conversions.
Calculate base, downside, and upside cases where uncertainty affects the decision.
Keep platform-attributed revenue, blended business revenue, cash flow, and
contribution margin distinct.
Return machine-readable inputs, formulas, outputs, sensitivities, and decision
implications.
Never fabricate missing financial inputs, hide division-by-zero, or present a point
forecast without its assumptions.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install ads-math and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.