---
name: landing-page-conversion-audit
description: "Find conversion obstacles across a page\u2019s message, evidence, forms and mobile experience. Use when the user requests landing page conversion audit. Select relevant methods for the requested outcome; unrelated tasks do not require this skill."
metadata:
  version: "1.0.0"
---

# Landing Page Conversion Audit

Find conversion obstacles across a page’s message, evidence, forms and mobile experience.

## OLLIE Runtime integration

Use this capability under the active OLLIE Operator. Read live Workspace Context and tenant bindings for client facts and required inputs. This generic package contains no client configuration. Consume ask-ollie-authority-core for authority, outloop-access-fallback for access and recovery, email-lifecycle-core for communication, and the bootstrapper Runtime Contract for ownership, scheduling and completion. Preserve domain constraints; this Skill creates no competing execution path. Use one method, combine skills, or fill missing steps with authorized tools as the task requires.

External access uses the active Workspace’s approved Outloop capabilities. Never request, read, embed or expose credentials. A service named in a method is a possible dependency, not an access grant. Local file and application work uses the host’s authorized tools.

## Required inputs

- Page or screenshots
- Intended audience
- Primary conversion
- Available analytics

## Methods

### Trace the visitor promise

Trace the visitor from acquisition promise to headline, evidence and action. Identify where the page asks the visitor to infer the offer or next step.

### Inspect the form

Inspect forms, input labels, errors, required fields and confirmation states. Separate observations from hypotheses about conversion impact.

### Test access and layout

Review desktop, narrow mobile, keyboard focus, contrast, readability and RTL when relevant. Check the actual interaction rather than appearance alone.

### Prioritize evidenced improvements

Rank findings by user impact and confidence. Provide concrete copy or layout changes and a measurement plan; never invent uplift percentages or customer proof.

## Completion

Verify findings against source evidence and read back the resulting artifact or authorized change. Report inputs used, methods selected, output location, assumptions and unresolved dependencies. Do not report a plan, queue entry, draft, test fixture or accepted request as a completed external action. Use the task’s requested format; if a tool is unavailable, finish independent work and identify the exact unfulfilled deliverable.

## Test before relying on it

Read [the synthetic evaluation cases](references/evaluation.md) for activation, output and isolation checks. These cases are test instructions, not evidence that a host or provider test has passed.