monetize
Skill1 starsChanged 4 months agoMITView on GitHub
Use when turning a project into a money-making product, or when the user mentions pricing, charging, subscriptions, payments, Stripe, or a landing page. Run it early - pricing shapes scope.
In this repository13 other files it gives its agents.
- add-aiSkill
- add-authSkill
- growSkill
- hardenSkill
- hireSkill
- launchSkill
- maintainSkill
- new-projectSkill
- optimizeSkill
- pitchSkill
- product-specSkill
- ship-itSkill
- validate-ideaSkill
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 18
If the answers are weak, stop here and report that — integrating Stripe into a product nobody pays for is wasted work.
- Distinctive: line 26
Default: Stripe. Standard shape for a SaaS webapp:
- Distinctive: line 32
Test end-to-end in Stripe test mode with test cards before going live.
≈ “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
Monetize
Turn a product into revenue. Run BEFORE building most features — what people pay for defines the MVP.
Step 1 — Foundation (answer honestly before anything else)
Delegate to the biz-strategist agent with the product idea and target user:
- Who exactly is the customer, and what painful problem does this solve?
- What do they use today (including "nothing"), and why switch?
- Competitor scan with real current prices.
If the answers are weak, stop here and report that — integrating Stripe into a product nobody pays for is wasted work.
Step 2 — Model & pricing
From the biz-strategist output, lock in: ONE monetization model, 2-3 price tiers max with concrete numbers, and the "needed to charge the first customer" feature list. Everything not on that list is deferred.
Step 3 — Payment integration (when there's something to sell)
Default: Stripe. Standard shape for a SaaS webapp:
- Stripe Checkout (hosted) for purchase — do not build custom card forms.
- Webhook endpoint (
checkout.session.completed,customer.subscription.updated/deleted) that updates the user's plan in the database; verify webhook signatures; make handlers idempotent. - Stripe Customer Portal for self-serve cancel/upgrade — don't build billing UI.
- Gate features by the plan column in the database (server-side checks, not client-only).
- Test end-to-end in Stripe test mode with test cards before going live. Fetch current Stripe docs via the context7 MCP tools — API versions change.
Implementation goes to backend-builder; keys are env vars, never in code. Anything beyond this standard shape (usage-based billing, invoicing, marketplace splits) goes through /product-spec's feasibility gate before implementation.
Step 4 — Landing page
biz-strategist writes the copy (headline = customer outcome, pain, 3-step how, proof, one CTA); frontend-builder ships it. Include: pricing table matching Step 2, and analytics (choose a simple one, e.g. platform analytics or a lightweight script — no heavyweight suites for v1).
Step 5 — Launch checklist
- Payments verified live with one real transaction, refunded after. Switching to live keys and making the real charge require the user's explicit go-ahead — never run them unprompted (a refunded charge still costs the Stripe fee); until then, test-mode evidence is the bar.
- Legal minimums: terms + privacy pages (templates fine), refund policy stated.
- Money-path actions only here — the first 3 with dates; channel planning and announcements belong to /launch.
- Metric to watch weekly: visitors → signups → paid conversion. One number per stage, tracked from day one.
Report (use exactly these sections)
- Model & prices: chosen model and tiers with concrete numbers.
- MVP-to-charge list: features required to charge customer #1; everything else deferred.
- Integration status: built and tested vs planned (Stripe test-mode evidence when built).
- Launch actions: the first 3 concrete actions with dates.
- Assumptions to validate: market/pricing assumptions not yet backed by real users.
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.

