In-app paywall and upgrade screen optimization covering feature gate design, usage limit UX, trial expiration flows, upgrade trigger timing, save offer strategy, and ethical monetization patterns.
SkillScore77Maintained
Automatic
◆Product Management pack
Last verified 8/20/2026
What it changes
Passed 17 of 22 test cases with the skill, and 5 of 22 without it.
Without skill23%
With skill77%
Checks it passed that the model alone missed
The response cites a benchmark paywall click-through rate target of 5-15%.
The response caps in-app paywall modal triggers at a maximum of 1 per session.
The response advises against displaying upgrade paywalls during initial onboarding.
and 11 more in the full report
12 fixed5 passed either way5 still failing0 broke
Pass-rate lift
+55 pp
Tokens
+230%
Agent turns
0%
Response time
+4%
Model gemini-3.6-flashMeasured 8/20/2026v117 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
We have a dataset `funnel_data.json` tracking paywall impressions through to payment completion. We need to run the funnel analyzer script to get JSON output. What exact command syntax should be used?
What was checked, without and with the skill
Checked
Without skill
With skill
The response specifies executing `python scripts/upgrade_funnel_analyzer.py funnel_data.json`.
Missed
Passed
The response includes the `--format json` option.
Passed
Passed
case-14 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md506 lines4 filesincludes scripts
Paywall & Upgrade Screen CRO
Production-grade framework for in-product upgrade flows. Covers feature gate design, usage limit UX, trial expiration sequences, upgrade trigger timing, dark pattern avoidance, and ethical monetization. Distinct from public pricing pages (use page-cro for those) -- this focuses on in-product moments where users have already experienced value.
Before designing the paywall, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Upgrade model — freemium-to-paid, trial-to-paid, or tier upgrade (determines the paywall type and trigger architecture)
Free vs paid boundary — what is gated (defines the value gap the paywall communicates)
Aha moment — so triggers fire only after value is experienced (the value-first principle)
Platform — web, iOS, or Android (IAP rules and commissions constrain web vs app flows)
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the deliverable.