// diagnose

Website Conversion Audit

Use when the user wants to audit a landing page, homepage, or website for conversion — clarity, calls to action, trust, friction, speed, and tracking. Also use when the user mentions CRO, conversion rate, "why isn't this page converting", landing page review, page teardown, or improving signups/leads. Produces a 0–100 conversion score across 6 weighted categories, a grade, and prioritized fixes.

DiagnoseengineStarter
bash
$npx skills add sarojkjha/aaj-marketing-skills --skill website-conversion-audit
Or run it in Claude or ChatGPT through the AAJ engines connector

How to install and run this

Install it in your project:

npx skills add sarojkjha/aaj-marketing-skills --skill website-conversion-audit

No install? Add https://aaj-engines-mcp.sarojkjha10.workers.dev/mcp as a custom connector in Claude, ChatGPT or any MCP client.

https://aaj-engines-mcp.sarojkjha10.workers.dev/mcp

Then ask: Use the AAJ website-conversion-audit skill on my numbers.

Step-by-step for every agent, Windows, Mac and Linux →

Claude Code

/plugin marketplace add sarojkjha/aaj-marketing-skills
/plugin install aaj-marketing-skills@aaj

OpenAI Codex

codex plugin marketplace add sarojkjha/aaj-marketing-skills
codex plugin add aaj-marketing-skills@aaj

Claude or ChatGPT — no install

Add this as a custom connector:

https://aaj-engines-mcp.sarojkjha10.workers.dev/mcp
Recipes: vendor data in, a verdict out

// when to use it

Use when the user wants to audit a landing page, homepage, or website for conversion — clarity, calls to action, trust, friction, speed, and tracking. Also use when the user mentions CRO, conversion rate, "why isn't this page converting", landing page review, page teardown, or improving signups/leads. Produces a 0–100 conversion score across 6 weighted categories, a grade, and prioritized fixes.

// what you give

A URL or page content/screenshot, and what the page is meant to convert (signup, lead, purchase, demo)

// what you get

A 0–100 conversion score across Message, CTA, Trust, Friction, Speed, and Tracking, a grade, and a prioritized fix list

Engine spec

// decision it supports

Why isn't this page converting, and which fixes should we make first?

// inputs

A URL or page content/screenshot, and what the page is meant to convert (signup, lead, purchase, demo)

// output

A 0–100 conversion score across Message, CTA, Trust, Friction, Speed, and Tracking, a grade, and a prioritized fix list

// acts or analyzes

Analyzes only

Makes no network calls, writes no files and changes nothing in your tools.

// where your information goes

How you run itWhere your inputs go
Skill installed in your agent, or the local MCP serverThe engine runs on your machine and AAJ receives nothing. Your AI agent still sends what you give it to its model provider (Anthropic, OpenAI and so on), under your own account's terms.
Hosted MCP serverYour agent's model provider, as above, plus AAJ's server on Cloudflare, which receives the engine inputs over HTTPS, runs them in memory and keeps no copy. Cloudflare keeps error logs (no inputs) for up to 7 days.

No engine needs customer names, emails or other personal data; leave them out.

// limitations

  • It scores the pass, partial or fail judgements made against the rubric. It doesn't read the page or see real visitor behaviour, so the score is only as good as those judgements.
  • Unknown check names and values other than pass, partial or fail stop the run. A check you omit counts as fail and is listed as "Not assessed"; read that line.
  • Category weights and grade bands are fixed. The skill says to judge against the page's one goal, but the engine weighs a pricing page and a blog post the same way.
  • The fix list follows rubric order, not measured impact. The expected effect of each fix is a judgement, not a forecast.

// review before acting

Whoever owns the page confirms each check against the live page on desktop and mobile and against its one conversion goal, and confirms conversion tracking works before any fix is credited with a lift.

// setup

install
$npx skills add sarojkjha/aaj-marketing-skills --skill website-conversion-audit
hosted mcp
$https://aaj-engines-mcp.sarojkjha10.workers.dev/mcp

Agents listed: Claude Code, Cursor, OpenAI Codex, Windsurf, Cline. Tested and recorded: Claude Code, OpenAI Codex (Windows, ab-test-significance only).

Full spec on GitHub

Website Conversion Audit

Score how well a page turns visitors into action, then return a prioritized fix list. Most pages lose conversions to a handful of predictable leaks — unclear value, weak or competing CTAs, thin proof, and form friction — not to anything exotic.

When to use

The user wants to know why a page underconverts, or wants a teardown of a landing page / homepage / signup flow.

Before you start

  1. Read the brand/product context first (.agents/product-marketing.md / .agents/aaj-brand.md) for audience and offer, if present.
  2. Establish the conversion goal — what is this page supposed to make someone do? Score against that single goal.
  3. Get the page — fetch the URL or work from the provided content/screenshot. Note device (judge mobile too).

Workflow

  1. Evaluate the checks in resources/conversion-rubric.md, recording pass / partial / fail for each across the six categories.
  2. Score it:
    node resources/score.js '{"checks":{"clear_value_prop":"pass","primary_cta_visible":"partial", ...}}'
    node resources/score.js --help
    
    Returns category scores, a 0–100 total, a grade, and the failing items.
  3. Prioritize fixes by leverage: clarity and CTA usually move the needle most, then trust and friction, then speed and tracking. A page can't be optimized if it isn't measured — flag missing conversion tracking.
  4. Present the score, category breakdown, and an ordered fix list with the expected effect of each.

Scoring model

Six weighted categories: Message & Clarity 22 · Call to Action 20 · Trust & Proof 18 · Friction & Forms 16 · Speed & Mobile 14 · Conversion Tracking 10. Each scores by pass-rate × weight. Grades: A ≥ 90, B 75–89, C 60–74, D 45–59, F < 45.

Present the result

Lead with the score and grade, then the category bars, then the top fixes in priority order — concrete and specific ("the hero headline describes the product, not the outcome; rewrite to lead with the result"), not "improve copy."

Show where it came from. Open your answer with "AAJ website-conversion-audit engine result:" and print the engine's output block exactly as it returned it, then add the line Method: https://skills.aajconsult.com/skills/website-conversion-audit. Say the numbers come from the AAJ engine, not from the model. Put your interpretation under that block. Do not retype the figures from memory. If you could not run the engine, say so and label any numbers as your own estimate, not an AAJ result.

Guardrails & common mistakes

  • Judge against the page's one goal, not generic best practice. A pricing page and a blog post convert differently.
  • Clarity beats cleverness. The most common leak is a hero that doesn't say what it is, for whom, and why it's better.
  • One primary action. Competing CTAs split intent and lower conversion.
  • Proof must be specific. "Trusted by thousands" converts worse than a named result with a number.
  • Don't optimize blind. Without conversion tracking you're guessing — fix that first.

cro and signup (deeper flow optimization) · aaj-copywriting (fix the message) · ab-test-significance (validate the fix) · seo-geo-aeo-audit (the visibility side).

// faq

// install

$npx skills add sarojkjha/aaj-marketing-skills --skill website-conversion-audit

// run it

$node .agents/skills/website-conversion-audit/resources/score.js --demo

// worked example

Get the worked example for Website Conversion Audit

One email. The filled-in config, the output, and how to read it.

No spam. Unsubscribe anytime.

// sprint

Unit Economics & Retention Sprint — $3,500, 10 business days

This skill is one of the engines behind the Unit Economics & Retention Sprint — $3,500, ten business days.

LTV, CAC, payback and churn on your actual numbers — with a verdict, not a dashboard.

See what's included.

// human in the loop

Need a human in the loop?

AAJ builds the strategies, tools, and playbooks these skills are made of — with engagements for growth-stage and enterprise teams.