subscription-readiness
Skill2 starsChanged 25 days agoApache-2.0View on GitHub
Use when billing recurs: subscriptions, trials that convert, auto-renewing plans, or metered billing. It checks that renewal, trial conversion, price changes, and cancellation are disclosed, actually work in the billing system, and agree across page, checkout, terms, and emails. Do not use it on products without recurring billing, to invent cancellation or refund terms, or to state renewal-law requirements from memory.
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Not for one-time purchases (payments-readiness), and not for wording requirements (consumer-protection-readiness escalates those).
- Distinctive: line 43
Test-mode flow completed: OBSERVED in test mode.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
subscription-readiness
Recurring billing is where good products lose trust: a free trial that quietly charges, a plan you can sign up for in two clicks and cancel only by emailing someone. This skill checks the mechanics and the honesty of recurrence.
Activate when
- Plans renew, trials convert, seats/usage are billed periodically, or "cancel anytime" appears in copy.
- Not for one-time purchases (
payments-readiness), and not for wording requirements (consumer-protection-readinessescalates those).
Working alone
This skill is self-contained. Its companions (declared in its metadata) are skills whose method it may need to do its own promised work. Use of a companion can be conditional: declaring one does not mean running it. When a companion's lane applies, use the skill if it is installed; if not, follow its short entry in references/companion-methods.md and say in your report which lanes ran inline at reduced depth. Never skip an applicable lane silently. Skills mentioned here only for escalation, referral, documentation, or optional deeper follow-up are not dependencies: report the hand-off and finish honestly.
Companions: design-system-reconnaissance.
Inspect
- Model: plan names, price, currency, interval, trial length and what triggers first charge, proration on upgrade/downgrade, seats/metered usage, grandfathered prices, discounts that expire.
- Disclosure at the point of purchase: amount and interval, renewal date or trigger, trial-to-paid conversion, and how to cancel are stated next to the buy button and in the confirmation and receipt, not only in the terms. The wording agrees with the actual billing configuration (a "14-day trial" in copy vs. a 7-day trial configured in the provider is a bug).
- Cancellation: a working path that is at least as easy as signup, reachable while logged in without contacting support (billing portal or in-app button); cancellation takes effect at period end or immediately as stated; confirmation shown and emailed; access after cancel behaves as promised; what happens to data (
data-rights). - Failed payments and dunning: what the user sees; grace period; emails (transactional); access handling; recovery path.
- Changes and reminders: price change communication process; renewal reminders if promised; trial-ending reminders if promised; the promised emails actually exist and send (
email-compliancefor transactional vs marketing). - Refund policy consistency: the same policy across FAQ, checkout, Terms, and support text; refunds mechanically possible (provider settings and admin capability). Use the applicable subscription sections of the Terms template and returns/refunds template only as drafting references. State verified billing behavior separately from owner-approved renewal/refund commitments. Cancelling future renewal does not itself refund an existing charge; never add physical-return steps to SaaS access.
- Webhook/state sync: subscription status in the app follows the provider (canceled, past_due, paused); an "active" flag not updated on cancel is a launch bug (
payments-readiness). - Exercise in test mode on local/staging (never live): subscribe with a trial, verify conversion configuration, cancel via the UI, simulate failed renewal (provider test clocks/cards), and confirm state and emails. Fast-forward using the provider's test-clock tools where available.
Evidence that counts
Label each claim OBSERVED, SOURCE-INDICATED, DECLARED, INFERRED, UNKNOWN, or REVIEW REQUIRED. UNKNOWN is never a pass and never a failure.
- Test-mode flow completed: OBSERVED in test mode. Live billing, tax collection, and provider dashboard policies are DECLARED/UNKNOWN.
- Copy vs configuration mismatch requires reading both (the price/interval in the provider config or code, and the rendered copy).
- Legal specifics: never from memory. When a rule, deadline, threshold, or required wording matters, read the current text or guidance at an official source while you run (start from references/official-sources.md), cite the source and access date, and treat applicability to this business as REVIEW REQUIRED. If you cannot look it up, the answer is UNKNOWN.
May change
Design first. Before creating or changing anything visible, inspect the project's existing design system (design-system-reconnaissance) and build from its tokens and components, by the component ladder: reuse, compose, extend, and only then create a matching component. Never impose a ReadyVibe look on the user's site.
Make displayed renewal/trial/price statements match the real configuration; surface cancellation and renewal info near the buy button and in confirmation emails/receipts using owner-provided wording; fix a broken cancel route or portal link; sync subscription state from webhooks; add renewal/trial reminders only if the owner wants them. If the relevant policy needs implementation, inspect and reuse the existing design system, update the established route and links, preserve mobile/accessibility behavior, and verify the actual cancellation action agrees with the text. Do not create plans/prices in the provider, invent refund or cancellation windows, or hide the cancel path. Keep unresolved markers and decisions private; never publish them.
Must not claim
"Cancel anytime", "no hidden fees", "compliant with auto-renewal laws", or any legal requirement about renewals, cooling-off, or notices.
Verify
Repeat the test-mode subscribe → trial → cancel → failed-renewal cases; confirm copy, checkout, terms, emails, and provider config agree on price, interval, trial, renewal, and cancellation; confirm access state after cancel.
Escalate
Any recurring billing to consumers, trials, regional pricing, or auto-renewal wording: REVIEW REQUIRED where the wording or the applicable rule is unclear or differs by market; look the rule up at an official source, cite it, and name what remains unresolved. Keep the recommendation proportional: name the specific unresolved fact or risk that warrants it (minors, sensitive data, a regulated domain, cross-border sale, unclear markets, contested wording), and do not tell an ordinary low-risk site to hire a lawyer. Flows you cannot exercise in test mode: UNVERIFIED.
No change is valid when
There is no recurring billing (say so; recheck when plans are added), or disclosure, cancellation, and state sync are all verified consistent.
In this repository54 other files it gives its agents.
- wcag-readinessSkill
- admin-audit-logSkill
- admin-authorizationSkill
- admin-dashboardSkill
- payments-readinessSkill
- ai-features-readinessSkill
- analytics-privacySkill
- consent-managementSkill
- consumer-protection-readinessSkill
- cookie-and-storage-auditSkill
- data-flow-mappingSkill
- data-rightsSkill
- email-complianceSkill
- jurisdiction-applicabilitySkill
- legal-identity-noticesSkill
- minors-readinessSkill
- policy-consistencySkill
- privacy-policySkill
- privacy-readinessSkill
- regulated-domain-triggersSkill
- terms-of-serviceSkill
- third-party-privacySkill
- user-content-safetySkill
- compliance-allSkill
- compliance-diffSkill
- design-system-reconnaissanceSkill
- discoverability-allSkill
- launch-allSkill
- launch-verificationSkill
- production-allSkill
- quality-allSkill
- site-reconnaissanceSkill
- trust-allSkill
- search-console-readinessSkill
- seo-readinessSkill
- social-sharingSkill
- structured-dataSkill
- multilingual-readinessSkill
- rtl-readinessSkill
- content-trustSkill
- error-pagesSkill
- failure-resilienceSkill
- faq-readinessSkill
- forms-readinessSkill
- launch-identitySkill
- legal-navigationSkill
- link-integritySkill
- mobile-readinessSkill
- performance-readinessSkill
- public-supportSkill
- dependency-securitySkill
- deployment-cleanupSkill
- security-headersSkill
- web-securitySkill
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.

