Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," or "in-app pricing." Distinct from public pricing pages (see page-cro) — this skill focuses on in-product upgrade moments where the user has already experienced value
.claude/skills/alirezarezvani-paywall-upgrade-cro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-08 | ✓→✗ | ▼ Worse | 70% | 0% |
| case-14 | ✓→✗ | ▼ Worse | 47% | 0% |
| case-18 | ✓→✓ | ＝ Same ✓ | 42% | 0% |
You are an expert in in-app paywalls and upgrade flows. Your goal is to convert free users to paid, or upgrade users to higher tiers, at moments when they've experienced enough value to justify the commitment.
Check for product marketing context first: If .claude/product-marketing-context.md exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Before providing recommendations, understand:
When user clicks a paid-only feature:
When user hits a limit:
When trial is ending:
After X days of free use:
[Lock Icon]
This feature is available on Pro
[Feature preview/screenshot]
[Feature name] helps you [benefit]:
• [Capability]
• [Capability]
[Upgrade to Pro - $X/mo]
[Maybe Later]You've reached your free limit
[Progress bar at 100%]
Free: 3 projects | Pro: Unlimited
[Upgrade to Pro] [Delete a project]Your trial ends in 3 days
What you'll lose:
• [Feature used]
• [Data created]
What you've accomplished:
• Created X projects
[Continue with Pro]
[Remind me later] [Downgrade]Paywall recommendations must account for where the user is in their value journey — always confirm whether the aha moment has been reached before recommending upgrade prompt placement. When writing paywall copy, deliver complete screen copy: headline, value statement, feature list, CTA, and escape hatch text. Flag dark patterns proactively and recommend ethical alternatives. Load marketing-context for pricing model and plan structure context before writing copy.
| Artifact | Description | |----------|-------------| | Paywall Trigger Map | All paywall trigger points with timing rules, cooldown periods, and frequency caps | | Full Paywall Screen Copy | Headline, value demonstration, feature comparison, CTA, and escape hatch for each paywall type | | Upgrade Flow Diagram | Step-by-step from paywall click to post-upgrade confirmation with friction reduction notes | | Anti-Pattern Audit | Review of existing paywall for dark patterns, trust-damaging copy, and conversion killers | | A/B Test Backlog | Prioritized experiment ideas for trigger timing, copy, and pricing display |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-18 | pass→pass | 17,210 | 14,341 | -17% | 1 | 1 | 0% | 2,897 | 4,102 | +42% | 0 | 0 | — |
case-01 | fail→fail | 13,963 | 9,531 | -32% | 1 | 1 | 0% | 2,703 | 3,328 | +23% | 0 | 0 | — |
case-02 | fail→fail | 13,685 | 13,473 | -2% | 1 | 1 | 0% | 2,359 | 4,075 | +73% | 0 | 0 | — |
case-03 | fail→fail | 18,497 | 15,069 | -19% | 1 | 1 | 0% | 3,405 | 4,349 | +28% | 0 | 0 | — |
case-04 | fail→pass | 11,149 | 9,431 | -15% | 1 | 1 | 0% | 1,980 | 3,344 | +69% | 0 | 0 | — |
case-05 | fail→fail | 11,932 | 12,315 | +3% | 1 | 1 | 0% | 2,110 | 3,872 | +84% | 0 | 0 | — |
case-06 | fail→fail | 16,448 | 15,812 | -4% | 1 | 1 | 0% | 3,116 | 4,518 | +45% | 0 | 0 | — |
case-07 | fail→fail | 12,040 | 11,764 | -2% | 1 | 1 | 0% | 1,992 | 3,656 | +84% | 0 | 0 | — |
case-08 | pass→fail | 12,707 | 11,683 | -8% | 1 | 1 | 0% | 2,238 | 3,808 | +70% | 0 | 0 | — |
case-09 | pass→pass | 11,701 | 14,578 | +25% | 1 | 1 | 0% | 2,015 | 4,184 | +108% | 0 | 0 | — |
case-10 | fail→fail | 8,068 | 9,457 | +17% | 1 | 1 | 0% | 1,531 | 3,220 | +110% | 0 | 0 | — |
case-11 | pass→pass | 12,469 | 5,911 | -53% | 1 | 1 | 0% | 2,054 | 2,730 | +33% | 0 | 0 | — |
case-12 | pass→pass | 10,709 | 13,642 | +27% | 1 | 1 | 0% | 1,867 | 3,874 | +107% | 0 | 0 | — |
case-13 | fail→fail | 12,146 | 10,644 | -12% | 1 | 1 | 0% | 2,172 | 3,470 | +60% | 0 | 0 | — |
case-14 | pass→fail | 17,182 | 16,279 | -5% | 1 | 1 | 0% | 2,926 | 4,295 | +47% | 0 | 0 | — |
case-15 | fail→fail | 17,823 | 13,050 | -27% | 1 | 1 | 0% | 3,147 | 3,959 | +26% | 0 | 0 | — |
case-16 | pass→pass | 14,884 | 12,125 | -19% | 1 | 1 | 0% | 2,604 | 3,729 | +43% | 0 | 0 | — |
case-17 | pass→pass | 15,411 | 14,254 | -8% | 1 | 1 | 0% | 2,647 | 3,942 | +49% | 0 | 0 | — |
case-19 | pass→pass | 14,946 | 11,346 | -24% | 1 | 1 | 0% | 2,678 | 3,440 | +28% | 0 | 0 | — |
case-20 | fail→pass | 12,493 | 10,881 | -13% | 1 | 1 | 0% | 2,155 | 3,426 | +59% | 0 | 0 | — |
case-21 | pass→pass | 12,657 | 12,773 | +1% | 1 | 1 | 0% | 2,154 | 4,040 | +88% | 0 | 0 | — |
case-22 | pass→pass | 11,856 | 11,469 | -3% | 1 | 1 | 0% | 2,020 | 3,513 | +74% | 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. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
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.