Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to optimize any form that is NOT signup/registration — including lead capture forms, contact forms, demo request forms, application forms, survey forms, or checkout forms. Also use when the user mentions "form optimization," "lead form conversions," "form friction," "form fields," "form completion rate," or "contact form." For signup/registration forms, see signup-flow-cro. For popups containing forms, see popup-cro.
.claude/skills/davila7-form-cro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 156% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 125% | 0% |
| case-17 | ✓→✓ | ＝ Same ✓ | 127% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 123% | 0% |
You are an expert in form optimization. Your goal is to maximize form completion rates while capturing the data that matters.
Before providing recommendations, identify:
Each field reduces completion rate. Rule of thumb:
For each field, ask:
Good:
Email
[name@company.com]Bad:
[Enter your email address] ← Disappears on focusGood: "Please enter a valid email address (e.g., name@company.com)" Bad: "Invalid input"
Weak: "Submit" | "Send" Strong: "Action] + What they get]"
Examples:
For each issue:
Ideas to A/B test with expected outcomes
Layout & Flow
Field Optimization
Smart Forms
Labels & Microcopy
CTAs & Buttons
Trust Elements
Demo Request Forms
Lead Capture Forms
Contact Forms
If you need more context:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | pass→pass | 13,563 | 14,654 | +8% | 1 | 1 | 0% | 2,132 | 4,849 | +127% | 0 | 0 | — |
case-01 | fail→pass | 24,550 | 23,957 | -2% | 1 | 1 | 0% | 4,180 | 6,498 | +55% | 0 | 0 | — |
case-02 | pass→pass | 13,152 | 15,044 | +14% | 1 | 1 | 0% | 2,170 | 4,843 | +123% | 0 | 0 | — |
case-03 | pass→pass | 12,917 | 11,457 | -11% | 1 | 1 | 0% | 2,358 | 4,170 | +77% | 0 | 0 | — |
case-04 | pass→pass | 14,332 | 16,230 | +13% | 1 | 1 | 0% | 2,381 | 5,124 | +115% | 0 | 0 | — |
case-05 | pass→pass | 10,902 | 10,124 | -7% | 1 | 1 | 0% | 1,891 | 4,024 | +113% | 0 | 0 | — |
case-06 | fail→pass | 10,943 | 12,858 | +17% | 1 | 1 | 0% | 1,776 | 4,553 | +156% | 0 | 0 | — |
case-07 | pass→pass | 11,647 | 11,327 | -3% | 1 | 1 | 0% | 1,857 | 4,296 | +131% | 0 | 0 | — |
case-08 | pass→pass | 12,267 | 10,330 | -16% | 1 | 1 | 0% | 1,931 | 4,281 | +122% | 0 | 0 | — |
case-09 | pass→pass | 9,950 | 15,081 | +52% | 1 | 1 | 0% | 1,764 | 4,806 | +172% | 0 | 0 | — |
case-10 | pass→pass | 11,220 | 11,433 | +2% | 1 | 1 | 0% | 2,006 | 4,471 | +123% | 0 | 0 | — |
case-11 | pass→pass | 11,692 | 11,615 | -1% | 1 | 1 | 0% | 2,022 | 4,335 | +114% | 0 | 0 | — |
case-12 | fail→fail | 10,533 | 10,203 | -3% | 1 | 1 | 0% | 1,826 | 4,214 | +131% | 0 | 0 | — |
case-13 | pass→pass | 9,953 | 10,369 | +4% | 1 | 1 | 0% | 1,663 | 4,228 | +154% | 0 | 0 | — |
case-14 | pass→pass | 9,977 | 9,029 | -10% | 1 | 1 | 0% | 1,837 | 4,191 | +128% | 0 | 0 | — |
case-15 | pass→pass | 8,993 | 9,842 | +9% | 1 | 1 | 0% | 1,519 | 4,079 | +169% | 0 | 0 | — |
case-16 | pass→pass | 11,113 | 12,575 | +13% | 1 | 1 | 0% | 1,875 | 4,512 | +141% | 0 | 0 | — |
case-18 | pass→pass | 12,596 | 10,813 | -14% | 1 | 1 | 0% | 2,163 | 4,134 | +91% | 0 | 0 | — |
case-19 | fail→pass | 12,892 | 14,031 | +9% | 1 | 1 | 0% | 2,119 | 4,759 | +125% | 0 | 0 | — |
case-20 | pass→pass | 12,656 | 13,572 | +7% | 1 | 1 | 0% | 2,000 | 4,650 | +133% | 0 | 0 | — |
case-21 | pass→pass | 16,405 | 14,724 | -10% | 1 | 1 | 0% | 2,821 | 5,131 | +82% | 0 | 0 | — |
case-22 | pass→pass | 17,904 | 17,037 | -5% | 1 | 1 | 0% | 3,309 | 5,761 | +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 +14 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.