Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jezweb/onboarding-ux
Audit and generate in-app user guidance — onboarding flows, empty states, tooltips, feature tours, contextual help, defaults, and inline hints. Browses the app to find where new users would get stuck, then produces the actual content and code to fix it. Pairs with ux-audit: audit finds problems, this skill builds the solutions. Triggers: 'onboarding', 'help content', 'empty states', 'user guidance', 'first run experience', 'feature tour', 'app is confusing', 'new user experience', 'make the app
Passed 13 of 19 test cases with the skill, and 7 of 19 without it.
and 5 more in the full report
7 fixed8 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/3/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
Where should the gap analysis report generated during an onboarding audit be saved, and what rating system is used to evaluate the initial 30-second user orientation?
| Checked | Without skill | With skill |
|---|---|---|
| Saves the audit report to .jez/artifacts/onboarding/audit.md. | Missed | Passed |
| Evaluates first impressions using a 1-5 rating score. | Passed | Passed |
The instructions your model reads when the skill loads.
Audit a web app for onboarding gaps, then generate the in-app guidance to fix them. The goal: a new user should never stare at a blank screen wondering what to do.
You've built the features. They work. But when a new user logs in for the first time, they see:
This skill finds those gaps and produces the content and code to fill them.
Same as ux-audit — detect Chrome MCP, Playwright MCP, or playwright-cli. See ux-audit's browser-tools.md reference if needed.
Same as ux-audit — prefer deployed/live URL over localhost. Check wrangler.jsonc, CLAUDE.md, or running dev server.
Browse the app as a brand new user. On every page, evaluate:
Navigate to every list/table/collection page. For each:
| Check | Good | Bad |
|---|---|---|
| What does a zero-data page show? | "No clients yet. Add your first client to get started." + CTA button | Empty table with column headers, or blank white space |
| Is there a clear action? | Button: "Add your first [thing]" | Nothing — user has to find the action in the nav or a menu |
| Does it explain the feature? | "Clients are the people and businesses you work with. Add one to start tracking your relationships." | Just an empty container |
| Is the empty state designed? | Illustration or icon, helpful copy, prominent CTA | Identical to the populated state minus the data |
Log in as a new user (or clear state to simulate). Evaluate:
test cases passed, vs 7 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.