balsm-health/website / .claude/skills/seo-flow
seo-flow
VerifiedFLOW framework integration: evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO prompts.
references/prompts/win/conversion-audit-prompt.md
View on GitHub<!-- Source: github.com/AgriciDaniel/flow | License: CC BY 4.0 | Synced: 2026-04-26 -->
---
title: "Conversion Audit Prompt"
description: "Conversion Audit Prompt"
updated: 2026-04-25
tags:
- prompts
- win
---
# Conversion Audit Prompt
## Use This When
Use this when a page, campaign, or funnel gets traffic but produces weak leads, low conversion rate, unclear attribution, or poor sales follow-up quality.
## AI Compatibility
Claude, GPT, Gemini, and other long-context models. Works best with current customer language and conversion evidence.
## Inputs
- Page or funnel copy.
- Traffic sources.
- Conversion goal.
- Analytics or conversion data.
- Call, chat, or form transcript samples.
- Known objections.
- Ad copy or campaign promise.
- Sales feedback, if available.
## Prompt
```text
Audit this conversion path for lead quality, friction, and measurement gaps.
Use the supplied page, campaign, and first-party conversation data. Identify:
1. Where visitor expectations may not match the page or offer.
2. Common objections and hesitation points.
3. Missing decision-making information.
4. Language mismatches between customers and the page.
5. CTA friction.
6. Tracking gaps across form, phone, chat, and offline outcomes.
7. Whether reporting connects to qualified leads or sales, not only traffic.
Return an executive summary, top blockers, lead-quality risks, messaging fixes, page/content fixes, tracking fixes, first-party data to collect next, and a ranked test backlog. Do not recommend more spend until content, offer clarity, and measurement gaps are assessed.
```
## Output
- A structured Win-stage working document.
- Prioritized recommendations.
- Evidence and measurement gaps.
- Claims or assumptions that require verification.
## Example
Input: paid search landing page with many calls but few booked appointments. Output: an audit of pricing clarity, qualification, phone attribution, repeated objections, CTA mismatch, and test priorities.
## See Also
- [Prompt Library](../README.md)
- BOFU and Conversion Content
- Dual-Surface Scorecard
## Source Note
Derived from PPC Trends 2026, CallRail/SEJ Better Leads More Sales 2025, and SEJ State of SEO 2026.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |