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/alirezarezvani-form-cro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-19 | ✗→✓ | ▲ Improved | 131% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 121% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 89% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 132% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 45% | 0% |
You are an expert in form optimization. Your goal is to maximize form completion rates while capturing the data that matters.
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, identify:
The thresholds that drive every form audit (full treatment in references/form-cro-playbook.md):
| Tool | Invocation | Output | |---|---|---| | Field analyzer | python3 scripts/form_field_analyzer.py forms.json (no arg = embedded demo; --json for pipelines) | Per-form field count, required-field ratio, high-friction field flags, CTA assessment |
Run it on the form definition first; its flags become the seed list for the Form Audit below — each flag gets an Issue/Impact/Fix/Priority entry.
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
.claude/product-marketing-context.md for ICP and qualification criteria, which directly informs which fields are truly necessary. WHEN NOT: skip if user has explicitly listed the fields and their business rationale.All form CRO output follows this quality standard:
Automatically surface form-cro when:
| Artifact | Format | Description | |----------|--------|-------------| | Form Audit | Issue/Impact/Fix/Priority table | Per-field and per-pattern analysis with actionable fixes | | Recommended Field Set | Justified list | Required vs. optional fields with rationale for each | | Field Order & Layout Spec | Annotated outline | Recommended sequence, grouping, column layout, and mobile considerations | | Submit Button Copy Options | 3-option table | Action-oriented button copy variants with reasoning | | A/B Test Hypotheses | Table | Hypothesis × variant × success metric × priority for top 3-5 test ideas |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 20,877 | 20,685 | -1% | 1 | 1 | 0% | 3,769 | 2,356 | -37% | 0 | 0 | — |
case-12 | pass→pass | 15,566 | 7,621 | -51% | 1 | 1 | 0% | 2,272 | 3,138 | +38% | 0 | 0 | — |
case-19 | fail→pass | 6,034 | 2,024 | -66% | 1 | 1 | 0% | 1,003 | 2,320 | +131% | 0 | 0 | — |
case-02 | fail→fail | 17,346 | 30,245 | +74% | 1 | 1 | 0% | 3,092 | 6,753 | +118% | 0 | 0 | — |
case-03 | fail→fail | 19,071 | 15,817 | -17% | 1 | 1 | 0% | 3,549 | 4,851 | +37% | 0 | 0 | — |
case-04 | fail→pass | 6,413 | 2,963 | -54% | 1 | 1 | 0% | 1,141 | 2,520 | +121% | 0 | 0 | — |
case-05 | pass→pass | 13,004 | 9,673 | -26% | 1 | 1 | 0% | 2,122 | 3,613 | +70% | 0 | 0 | — |
case-06 | fail→pass | 11,111 | 10,756 | -3% | 1 | 1 | 0% | 1,957 | 3,698 | +89% | 0 | 0 | — |
case-20 | pass→pass | 8,764 | 9,474 | +8% | 1 | 1 | 0% | 1,538 | 3,610 | +135% | 0 | 0 | — |
case-07 | fail→pass | 7,989 | 6,588 | -18% | 1 | 1 | 0% | 1,341 | 3,109 | +132% | 0 | 0 | — |
case-08 | pass→pass | 9,176 | 7,077 | -23% | 1 | 1 | 0% | 1,505 | 3,148 | +109% | 0 | 0 | — |
case-09 | fail→pass | 11,899 | 4,818 | -60% | 1 | 1 | 0% | 1,897 | 2,759 | +45% | 0 | 0 | — |
case-10 | pass→pass | 11,176 | 6,526 | -42% | 1 | 1 | 0% | 1,891 | 2,960 | +57% | 0 | 0 | — |
case-11 | pass→pass | 15,073 | 9,545 | -37% | 1 | 1 | 0% | 2,558 | 3,586 | +40% | 0 | 0 | — |
case-13 | fail→pass | 7,157 | 3,918 | -45% | 1 | 1 | 0% | 1,092 | 2,618 | +140% | 0 | 0 | — |
case-14 | pass→pass | 10,970 | 6,685 | -39% | 1 | 1 | 0% | 1,840 | 3,037 | +65% | 0 | 0 | — |
case-15 | pass→pass | 10,344 | 6,023 | -42% | 1 | 1 | 0% | 1,645 | 2,912 | +77% | 0 | 0 | — |
case-16 | fail→pass | 5,402 | 1,634 | -70% | 1 | 1 | 0% | 908 | 2,266 | +150% | 0 | 0 | — |
case-17 | pass→fail | 12,639 | 12,416 | -2% | 1 | 1 | 0% | 2,190 | 4,073 | +86% | 0 | 0 | — |
case-18 | pass→pass | 8,652 | 5,158 | -40% | 1 | 1 | 0% | 1,503 | 2,855 | +90% | 0 | 0 | — |
case-21 | pass→pass | 13,348 | 13,405 | +0% | 1 | 1 | 0% | 3,057 | 4,837 | +58% | 0 | 0 | — |
case-22 | pass→fail | 14,201 | 17,174 | +21% | 1 | 1 | 0% | 3,606 | 5,926 | +64% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +23 percentage points is the difference between those two pass rates over the 21 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.