Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plan user flows and screen states for a Figma design before any designing starts. Use when asked to plan a user flow, map out screens for a feature, define screen states, plan a Figma file structure, or work out what needs to be designed before opening Figma. Produces a complete flow map with all screens, states, entry/exit points, and a suggested Figma page structure.
.claude/skills/mohitagw15856-figma-user-flow-planner/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 40% | 0% |
Plans what needs to be designed before a pixel is touched — mapping all screens, states, entry points, and edge cases so designers do not discover missing states mid-build.
Feature, user, goal, entry points, success exit, failure exits.
| # | Screen name | Type | Triggered by | Notes | |---|---|---|---|---| | 1 | Screen] | New/Modal/Drawer/Toast | What triggers] | Considerations] |
Screen types to cover: entry, happy path, loading, success, error (network/validation/permission), empty, first-time/onboarding, edge cases.
Screen name]
| State | Trigger | Visual change | Action available | |---|---|---|---| | Default | Page load | Description] | What user can do] | | Loading | User taps action | Skeleton/spinner | None | | Error | API failure | Error message | Retry/Go back | | Empty | No data | Empty state | CTA] |
Decision: Name]
Feature name/
- Cover
- Flow Map
- Happy Path
- Error States
- Empty States
- Edge Cases
- HandoffExplicit out-of-scope items — prevents scope creep]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 23,154 | 14,471 | -38% | 1 | 1 | 0% | 4,537 | 3,467 | -24% | 0 | 0 | — |
case-02 | fail→fail | 20,212 | 15,570 | -23% | 1 | 1 | 0% | 3,771 | 3,658 | -3% | 0 | 0 | — |
case-03 | fail→pass | 34,708 | 19,832 | -43% | 1 | 1 | 0% | 6,221 | 4,673 | -25% | 0 | 0 | — |
case-04 | fail→pass | 23,150 | 17,482 | -24% | 1 | 1 | 0% | 4,061 | 3,896 | -4% | 0 | 0 | — |
case-05 | fail→pass | 20,579 | 18,387 | -11% | 1 | 1 | 0% | 3,760 | 3,974 | +6% | 0 | 0 | — |
case-06 | fail→pass | 19,262 | 11,466 | -40% | 1 | 1 | 0% | 3,189 | 3,359 | +5% | 0 | 0 | — |
case-07 | fail→pass | 14,265 | 15,923 | +12% | 1 | 1 | 0% | 2,566 | 3,588 | +40% | 0 | 0 | — |
case-08 | fail→fail | 18,771 | 15,605 | -17% | 1 | 1 | 0% | 3,090 | 3,422 | +11% | 0 | 0 | — |
case-09 | fail→fail | 21,319 | 18,223 | -15% | 1 | 1 | 0% | 3,501 | 3,834 | +10% | 0 | 0 | — |
case-10 | fail→fail | 20,480 | 19,777 | -3% | 1 | 1 | 0% | 3,474 | 4,038 | +16% | 0 | 0 | — |
case-11 | fail→pass | 15,727 | 20,149 | +28% | 1 | 1 | 0% | 2,773 | 3,931 | +42% | 0 | 0 | — |
case-12 | fail→fail | 22,214 | 19,492 | -12% | 1 | 1 | 0% | 3,817 | 4,049 | +6% | 0 | 0 | — |
case-13 | fail→pass | 25,562 | 20,809 | -19% | 1 | 1 | 0% | 4,528 | 4,196 | -7% | 0 | 0 | — |
case-14 | fail→fail | 17,296 | 21,306 | +23% | 1 | 1 | 0% | 2,991 | 4,285 | +43% | 0 | 0 | — |
case-15 | fail→fail | 17,756 | 14,361 | -19% | 1 | 1 | 0% | 3,260 | 3,570 | +10% | 0 | 0 | — |
case-16 | fail→fail | 15,912 | 14,389 | -10% | 1 | 1 | 0% | 2,814 | 3,264 | +16% | 0 | 0 | — |
case-17 | fail→pass | 18,497 | 14,216 | -23% | 1 | 1 | 0% | 3,064 | 3,164 | +3% | 0 | 0 | — |
case-18 | fail→pass | 20,423 | 16,783 | -18% | 1 | 1 | 0% | 3,587 | 3,741 | +4% | 0 | 0 | — |
case-19 | fail→pass | 17,256 | 14,452 | -16% | 1 | 1 | 0% | 2,857 | 3,358 | +18% | 0 | 0 | — |
case-20 | pass→pass | 17,913 | 16,998 | -5% | 1 | 1 | 0% | 3,741 | 3,831 | +2% | 0 | 0 | — |
case-21 | pass→pass | 17,413 | 15,501 | -11% | 1 | 1 | 0% | 3,151 | 3,621 | +15% | 0 | 0 | — |
case-22 | pass→pass | 17,691 | 19,342 | +9% | 1 | 1 | 0% | 3,090 | 4,159 | +35% | 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 +45 percentage points is the difference between those two pass rates over the 22 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.