model-growth-funnel
Skill14 starsChanged 3 months agoMITView on GitHub
Build a decision-grade growth or revenue funnel backward from a business target. Use for numeric funnel plans, baseline assumptions, conversion targets, capacity checks, unit economics, sensitivity analysis, or deciding whether a growth goal is feasible.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brief-creativeSkill
- brief-product-uiSkill
- conquistadorSkill
- create-brandSkill
- create-paid-campaignSkill
- create-shortformSkill
- debate-agentsSkill
- improve-conversionSkill
- knowledge-reviewSkill
- map-user-flowSkill
- measure-growthSkill
- optimize-searchSkill
- plan-campaignSkill
- polish-vietnameseSkill
- research-channelSkill
- research-positioningSkill
- write-copySkill
- write-longformSkill
- write-outreachSkill
- write-socialSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Keep arithmetic inspectable.
- Distinctive: line 32
Run at least downside, base, and upside cases across the assumptions most likely to change the decision.
- Distinctive: line 45
If the model requires impossible throughput, unjustified conversion, or negative economics, say so and identify the binding constraint.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Model a growth funnel
Turn a business target into explicit math, assumptions, constraints, and the next evidence needed. This is a decision model, not a forecast.
Define the outcome and units
Name the target, time window, currency, customer/account definition, and whether the target means bookings, recurring revenue, recognized revenue, activation, or another outcome. Do not mix people, accounts, opportunities, orders, and revenue in one rate.
Work backward from the outcome through the smallest useful funnel. For each transition, show:
- numerator and denominator;
- current observed value and source, when available;
- planning assumption when evidence is absent;
- owner and date for replacing the assumption;
- operational action required at that volume.
Keep arithmetic inspectable. Show formulas and rounded operational totals.
Test feasibility
Run at least downside, base, and upside cases across the assumptions most likely to change the decision. Do not vary everything at once.
Check:
- audience/market capacity;
- acquisition and sales throughput;
- onboarding, delivery, and support capacity;
- average contract or order value;
- gross margin and marginal service cost;
- retention/churn where the time horizon requires it;
- acquisition cost, payback, and LTV:CAC only when their inputs exist.
If the model requires impossible throughput, unjustified conversion, or negative economics, say so and identify the binding constraint. Do not reverse-engineer optimistic rates merely to hit the goal.
Deliver
Return:
- decision and target definition;
- assumptions table with source/owner;
- base model and formulas;
- downside/base/upside sensitivity;
- capacity and unit-economics constraints;
- the assumptions with highest decision sensitivity;
- smallest evidence plan for replacing them;
- feasible range, revised target, or explicit no-go recommendation.
Separate model outputs from observed results. Keep spending and external system changes behind explicit approval.
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
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.

