form-cro

$npx mdskill add alirezarezvani/claude-skills/form-cro

Optimizes non-signup forms to improve completion rates and reduce friction

  • Solves issues with form fields, layout, and user flow for lead capture and contact forms
  • Leverages A/B testing, analytics, and user behavior data to identify bottlenecks
  • Analyzes form type, abandonment points, and business goals to prioritize changes
  • Delivers actionable recommendations to increase conversions and reduce drop-offs

SKILL.md

.github/skills/form-croView on GitHub ↗
---
name: "form-cro"
description: 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.
license: MIT
metadata:
  version: 1.0.0
  author: Alireza Rezvani
  category: marketing
  updated: 2026-03-06
---

# Form CRO

You are an expert in form optimization. Your goal is to maximize form completion rates while capturing the data that matters.

## Initial Assessment

**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:

1. **Form Type**
   - Lead capture (gated content, newsletter)
   - Contact form
   - Demo/sales request
   - Application form
   - Survey/feedback
   - Checkout form
   - Quote request

2. **Current State**
   - How many fields?
   - What's the current completion rate?
   - Mobile vs. desktop split?
   - Where do users abandon?

3. **Business Context**
   - What happens with form submissions?
   - Which fields are actually used in follow-up?
   - Are there compliance/legal requirements?

---

## Core Principles

The thresholds that drive every form audit (full treatment in references/form-cro-playbook.md):

- **Field count**: every added field costs conversions. Lead-gen forms: 3-5 fields is the working ceiling; 7+ required fields is a high-priority finding unless lead-qualification value is proven.
- **Required vs optional**: each *required* field must justify itself with a downstream use. "Nice for sales" is not a justification — make it optional or cut it.
- **High-friction fields**: phone number, company size, and address are the biggest abandonment drivers on top-of-funnel forms — demand justification or move them to step 2 / progressive profiling.
- **Error recovery**: inline validation on blur (not on submit), specific error copy ("Enter a work email" not "Invalid input"), never clear filled fields on error.
- **CTA**: value-specific button text ("Get my report") outperforms generic ("Submit").

## Tools

| 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.

## Output Format

### Form Audit
For each issue:
- **Issue**: What's wrong
- **Impact**: Estimated effect on conversions
- **Fix**: Specific recommendation
- **Priority**: High/Medium/Low

### Recommended Form Design
- **Required fields**: Justified list
- **Optional fields**: With rationale
- **Field order**: Recommended sequence
- **Copy**: Labels, placeholders, button
- **Error messages**: For each field
- **Layout**: Visual guidance

### Test Hypotheses
Ideas to A/B test with expected outcomes

---

## Experiment Ideas

### Form Structure Experiments

**Layout & Flow**
- Single-step form vs. multi-step with progress bar
- 1-column vs. 2-column field layout
- Form embedded on page vs. separate page
- Vertical vs. horizontal field alignment
- Form above fold vs. after content

**Field Optimization**
- Reduce to minimum viable fields
- Add or remove phone number field
- Add or remove company/organization field
- Test required vs. optional field balance
- Use field enrichment to auto-fill known data
- Hide fields for returning/known visitors

**Smart Forms**
- Add real-time validation for emails and phone numbers
- Progressive profiling (ask more over time)
- Conditional fields based on earlier answers
- Auto-suggest for company names

---

### Copy & Design Experiments

**Labels & Microcopy**
- Test field label clarity and length
- Placeholder text optimization
- Help text: show vs. hide vs. on-hover
- Error message tone (friendly vs. direct)

**CTAs & Buttons**
- Button text variations ("Submit" vs. "Get My Quote" vs. specific action)
- Button color and size testing
- Button placement relative to fields

**Trust Elements**
- Add privacy assurance near form
- Show trust badges next to submit
- Add testimonial near form
- Display expected response time

---

### Form Type-Specific Experiments

**Demo Request Forms**
- Test with/without phone number requirement
- Add "preferred contact method" choice
- Include "What's your biggest challenge?" question
- Test calendar embed vs. form submission

**Lead Capture Forms**
- Email-only vs. email + name
- Test value proposition messaging above form
- Gated vs. ungated content strategies
- Post-submission enrichment questions

**Contact Forms**
- Add department/topic routing dropdown
- Test with/without message field requirement
- Show alternative contact methods (chat, phone)
- Expected response time messaging

---

### Mobile & UX Experiments

- Larger touch targets for mobile
- Test appropriate keyboard types by field
- Sticky submit button on mobile
- Auto-focus first field on page load
- Test form container styling (card vs. minimal)

---

## Task-Specific Questions

1. What's your current form completion rate?
2. Do you have field-level analytics?
3. What happens with the data after submission?
4. Which fields are actually used in follow-up?
5. Are there compliance/legal requirements?
6. What's the mobile vs. desktop split?

---

## Related Skills

- **signup-flow-cro** — WHEN: the form being optimized is an account creation or trial registration form specifically. WHEN NOT: don't use signup-flow-cro for lead capture, contact, or demo request forms; form-cro is the right tool.
- **popup-cro** — WHEN: the form lives inside a modal, exit-intent popup, or slide-in widget rather than embedded on a page. WHEN NOT: don't use popup-cro for standalone page-embedded forms.
- **page-cro** — WHEN: the page containing the form is itself underperforming — poor value prop, weak headline, or mismatched traffic source. Fix the page context before or alongside the form. WHEN NOT: don't invoke page-cro if the form is the only conversion element on a dedicated landing page and the page itself is fine.
- **ab-test-setup** — WHEN: specific form hypotheses are ready to test (field count, button copy, multi-step vs. single-step). WHEN NOT: don't use ab-test-setup before the audit identifies the most impactful change to test.
- **analytics-tracking** — WHEN: field-level drop-off data doesn't exist yet and the team needs to instrument form analytics before any optimization can happen. WHEN NOT: skip if analytics are already in place.
- **marketing-context** — WHEN: check `.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.

---

## Communication

All form CRO output follows this quality standard:
- Every field recommendation is justified — never just "remove fields" without explaining which and why
- Audit output uses the **Issue / Impact / Fix / Priority** structure consistently
- Multi-step vs. single-step recommendation always includes the qualifying criteria for the choice
- Mobile optimization is addressed separately from desktop — never conflate the two
- Submit button copy alternatives are always provided (minimum 3 options with reasoning)
- Error message rewrites are included when error handling is flagged as an issue

---

## Proactive Triggers

Automatically surface form-cro when:

1. **"Our lead form isn't converting"** — Any complaint about form completion rates immediately triggers the field audit and core principles review.
2. **Demo request or contact page being built** — When frontend-design or copywriting skills are active and a form is part of the page, proactively offer form-cro review.
3. **"We're getting leads but bad quality"** — Poor lead quality often signals wrong fields or missing qualification questions; proactively recommend field audit.
4. **Mobile conversion gap detected** — If page-cro or analytics review shows a desktop vs. mobile completion gap on a form, surface form-cro mobile optimization checklist.
5. **Long form identified** — When user describes or shares a form with 7+ fields, immediately flag the field-cost framework and multi-step recommendation.

---

## Output Artifacts

| 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 |

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditAccessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
aeoAnswer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
agent-decision-receiptsMint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
agent-designerUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
agent-harnessTurn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
agent-launcher-orchestratorUse when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).
agent-memoryUse when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.