Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).
.claude/skills/get-convex-convex-billing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -13% | 0% |
<!-- GENERATED from convex-agents content/capabilities/billing.json — do not edit by hand. -->
Wire Stripe to Convex using @convex-dev/stripe: a checkout action, an httpAction webhook registered by the component (signature-verified automatically), subscription state stored in the component's tables, and server-side gating via a query.
npm install @convex-dev/stripe.convex/convex.config.ts:ts import { defineApp } from 'convex/server'; import stripe from '@convex-dev/stripe/convex.config.js'; const app = defineApp(); app.use(stripe); export default app;
env micro power): STRIPE_SECRET_KEY (sk_test_… / sk_live_…) and STRIPE_WEBHOOK_SECRET (whsec_…).convex/http.ts to register the webhook route (the component handles signature verification automatically):ts import { httpRouter } from 'convex/server'; import { components } from './_generated/api'; import { registerRoutes } from '@convex-dev/stripe'; const http = httpRouter(); registerRoutes(http, components.stripe, { webhookPath: '/stripe/webhook' }); export default http;
convex/billing.ts with a checkout action and a subscription-gate query:ts import { action, query } from './_generated/server'; import { components } from './_generated/api'; import { StripeSubscriptions } from '@convex-dev/stripe'; import { v } from 'convex/values'; const stripeClient = new StripeSubscriptions(components.stripe, {}); export const createSubscriptionCheckout = action({ args: { priceId: v.string() }, returns: v.object({ sessionId: v.string(), url: v.union(v.string(), v.null()) }), handler: async (ctx, args) => { const identity = await ctx.auth.getUserIdentity(); if (!identity) throw new Error('Not authenticated'); const customer = await stripeClient.getOrCreateCustomer(ctx, { userId: identity.subject, email: identity.email, name: identity.name }); return await stripeClient.createCheckoutSession(ctx, { priceId: args.priceId, customerId: customer.customerId, mode: 'subscription', successUrl: ${process.env.SITE_URL ?? 'http://localhost:3000'}/?success=true, cancelUrl: ${process.env.SITE_URL ?? 'http://localhost:3000'}/?canceled=true, subscriptionMetadata: { userId: identity.subject } }); }, }); export const isSubscribed = query({ args: {}, returns: v.boolean(), handler: async (ctx) => { const identity = await ctx.auth.getUserIdentity(); if (!identity) return false; const subscriptions = await ctx.runQuery(components.stripe.public.listSubscriptionsByUserId, { userId: identity.subject }); return subscriptions.some((sub) => sub.status === 'active' || sub.status === 'trialing'); }, });
npx convex dev --once — it will install the component and push the functions. Verify output shows ✔ Installed component stripe.https://<deployment>.convex.site/stripe/webhook, subscribe to checkout.session.completed, customer.subscription.*, invoice.*, payment_intent.*. Copy the signing secret as STRIPE_WEBHOOK_SECRET.env micro power): STRIPE_SECRET_KEY and STRIPE_WEBHOOK_SECRET.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 32,627 | 23,454 | -28% | 1 | 1 | 0% | 5,834 | 3,496 | -40% | 0 | 0 | — |
case-02 | fail→pass | 21,761 | 14,003 | -36% | 1 | 1 | 0% | 4,477 | 3,462 | -23% | 0 | 0 | — |
case-03 | fail→pass | 20,271 | 10,169 | -50% | 1 | 1 | 0% | 4,127 | 3,315 | -20% | 0 | 0 | — |
case-04 | fail→pass | 7,395 | 3,998 | -46% | 1 | 1 | 0% | 1,319 | 1,545 | +17% | 0 | 0 | — |
case-05 | fail→pass | 10,004 | 4,087 | -59% | 1 | 1 | 0% | 1,873 | 1,630 | -13% | 0 | 0 | — |
case-06 | fail→pass | 13,807 | 3,385 | -75% | 1 | 1 | 0% | 2,685 | 1,688 | -37% | 0 | 0 | — |
case-07 | fail→pass | 16,550 | 8,124 | -51% | 1 | 1 | 0% | 2,554 | 2,696 | +6% | 0 | 0 | — |
case-08 | fail→pass | 16,955 | 10,653 | -37% | 1 | 1 | 0% | 3,571 | 3,503 | -2% | 0 | 0 | — |
case-09 | fail→pass | 18,485 | 8,260 | -55% | 1 | 1 | 0% | 2,558 | 2,700 | +6% | 0 | 0 | — |
case-10 | pass→pass | 13,948 | 7,330 | -47% | 1 | 1 | 0% | 1,841 | 2,001 | +9% | 0 | 0 | — |
case-11 | fail→pass | 4,750 | 2,965 | -38% | 1 | 1 | 0% | 613 | 1,379 | +125% | 0 | 0 | — |
case-12 | fail→pass | 7,854 | 6,824 | -13% | 1 | 1 | 0% | 1,496 | 2,089 | +40% | 0 | 0 | — |
case-13 | pass→pass | 12,237 | 3,872 | -68% | 1 | 1 | 0% | 1,710 | 1,597 | -7% | 0 | 0 | — |
case-14 | fail→pass | 15,600 | 5,873 | -62% | 1 | 1 | 0% | 2,796 | 2,139 | -23% | 0 | 0 | — |
case-15 | pass→pass | 12,200 | 8,518 | -30% | 1 | 1 | 0% | 2,034 | 2,266 | +11% | 0 | 0 | — |
case-16 | pass→pass | 5,258 | 3,256 | -38% | 1 | 1 | 0% | 858 | 1,441 | +68% | 0 | 0 | — |
case-17 | pass→pass | 12,227 | 6,816 | -44% | 1 | 1 | 0% | 2,036 | 2,207 | +8% | 0 | 0 | — |
case-18 | fail→pass | 14,814 | 7,194 | -51% | 1 | 1 | 0% | 2,371 | 1,997 | -16% | 0 | 0 | — |
case-19 | fail→pass | 15,463 | 6,177 | -60% | 1 | 1 | 0% | 2,267 | 1,966 | -13% | 0 | 0 | — |
case-20 | pass→pass | 17,005 | 14,199 | -17% | 1 | 1 | 0% | 3,110 | 3,677 | +18% | 0 | 0 | — |
case-21 | fail→fail | 24,234 | 17,465 | -28% | 1 | 1 | 0% | 3,625 | 4,443 | +23% | 0 | 0 | — |
case-22 | fail→fail | 27,647 | 28,143 | +2% | 1 | 1 | 0% | 4,357 | 5,359 | +23% | 0 | 0 | — |
case-23 | fail→fail | 34,381 | 26,761 | -22% | 1 | 1 | 0% | 5,664 | 5,407 | -5% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +61 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.