Internal · Marketing & Growth

One skill that audits every page
like a senior consultant.

A multidisciplinary web-excellence consultant that runs inside Claude Code — reviewing performance, accessibility, SEO, AI-discoverability, UX, design, Webflow and conversion in a single, repeatable pass.

Built for Marketing & Growth Anchored on real Landbot audits

Press to begin · O for overview · keyboard-navigable & reduced-motion aware.

The problem

Web reviews are fragmented, inconsistent,
and they don't repeat.

Fragmented

Performance, SEO and accessibility each live in a different tool — so nobody sees how a fix in one quietly breaks another.

Inconsistent

Every reviewer checks different things in a different order — so you can't compare two pages, or track the same page over time.

Slow & leaky

Manual reviews don't scale and never run the same way twice — quietly missing the issues that cost rankings and conversions.

Growth needs pages that are fast, findable — by Google and AI — and that convert. This skill checks every discipline together, every time — so nothing slips through.

What it is

A skill that reviews your web pages like a senior web consultant would.

It runs inside Claude Code. Point it at a page and it runs 10 expert checks on it, then combines them into one review — sorting out any places where the checks disagree.

You get one to-do list, sorted by what matters most — not nine separate opinions, and never one thing fixed at the quiet expense of another.

The idea in one line

It doesn't do the checks itself. It picks the right expert checks, gives them all the same evidence, weighs the trade-offs, and turns everything into one prioritized report.

Runs the checks Combines them One report
The coverage · nine disciplines

Every page, checked across nine disciplines at once.

Core Web Vitals sit inside Performance — 10 specialist skills feed these 9 disciplines.

How it runs · the workflow

One pass: gather the evidence once, run all nine checks, then combine them.

1
Discover
see which checks are installed
2
Classify
what you gave it, what you want
3
Capture
load the page, record everything
Once
4
Run checks
all 9, in the same format
5
Combine
sort out conflicts, then rank
6
Deliver
a short summary first
Step 4 · at the same time All 9 checks read the same evidence

Gathering the evidence once (step 3) is what lets all nine checks run cheaply — and keeps every finding tied to the same facts.

The workflow · step by step

What happens at each step.

01

Discover the checks

It sees which of the 10 expert checks are installed and matches each to a topic. If one is missing, it flags where the review will be lighter.

A map of which checks will run
02

Understand the request

It works out what you gave it — a link, a whole site, a design file, a screenshot, a report, or code — and what you want: a review, a plan, or actual fixes.

The right checks for the job
03

Gather the evidence — once

It loads the page one time and records everything: the finished page, the raw HTML before scripts, all network requests, the console, desktop + mobile screenshots, real-user speed, and the findable/blocked check.

One shared set of facts
04

Run the checks

All nine topics review that same evidence at once. Each writes its findings the same way: an ID, how serious it is, the effort to fix, the proof, and the fix.

Findings in one format
05

Combine & rank

It merges everything, sorts out cases where two checks disagree, scores each finding by impact, effort and risk, and groups them into four priority tiers.

One ranked to-do list
06

Hand it back

You get a short summary first. The full report, the checklist, and a PDF or HTML version are there whenever you ask for them.

Report · checklist · PDF / HTML
How it fits together

It doesn't just list problems — it settles the conflicts between them.

Fixing one thing often hurts another. Instead of quietly picking a side, it shows the trade-off and tells you what to do.

10 expert checks
speedCore Web VitalsaccessibilitySEOAI-crawldesignUXWebflowconversionquality
Web Excellence
same evidence for all of them
One report, sorted by priority

Three trade-offs it sorts out for you

SEO wants more text near the top vs Speed wants a lighter page
Lead with a short, keyword-rich headline and load the rest afterward — then check the page doesn't jump.
Speed wants faster-loading fonts vs Layout can jump when a font swaps in
Preload the font and reserve its space, then re-measure the jump.
Marketing wants its tracking tags vs Speed wants fewer scripts
Remove them one at a time with marketing, checking each tag still fires.
How it gathers evidence

It uses the same tools a senior engineer would.

Everything is captured once, up front — so every finding is backed by proof, not a guess.

Chrome DevTools

Loads the page and records the network requests, console errors, a performance trace, and desktop + mobile screenshots.

Lighthouse

Scores the page on Performance, Accessibility, Best Practices and SEO.

PageSpeed Insights

Real-user speed from Google (CrUX): LCP, INP and CLS from people who actually visited.

Command line (curl)

Grabs the raw HTML before scripts run, plus robots.txt and sitemap.xml — the “can it be found / is it blocked” check.

Page scripts

Pull out headings, image alt text, colour contrast and structured data straight from the page.

The result

One shared set of facts — reused by all nine checks, so nothing is reviewed twice or guessed at.

Two ways to use it

Check a page, or improve one.

Same skill — you decide whether it just reviews the page, or actually makes changes to it.

Way 1 · Review only

Check a page

Point it at a page and it reviews everything, then hands you the report and a to-do list sorted by priority. Nothing on the page changes.

Use it to

Find out how good a page is, and exactly what to fix first.

Way 2 · Make changes

Fix or build a page

Ask it to actually make the changes. On a live page it works carefully — one change at a time, checking nothing breaks:

1 Measure the page now 2 Make one change 3 Check nothing broke 4 Measure again 5 Write down the result

Then it moves to the next change — so you always know each fix helped and didn't break anything.

What you get ① · the standard report

A standard report — the same 16 sections, every time.

Web Excellence Audit — Landbot.io Homepage landbot-homepage-audit-2026-06-18

Fixed structure

  1. 01 Executive Summary
  2. 02 Business Impact
  3. 03 Performance
  4. 04 AI Crawlability
  5. 05 SEO
  6. 06 AEO
  7. 07 Accessibility
  8. 08 UX
  9. 09 Design
  10. 10 Webflow
  11. 11 Conversion
  12. 12 Risk & Confidence
  13. 13 Prioritized Roadmap
  14. 14 Implementation Plan
  15. 15 Action Checklist
  16. 16 Evidence Appendix

Executive summary + scorecards

MetricField p75TargetStatus
LCP2,592 ms< 2,500Needs work
INP76 ms< 200Good
CLS0.04< 0.1Good

Per-discipline finding — one schema

W1 Duplicate, divergent hero sections HighEffort M–L
Evidence: two hero sections ship; desktop display:none on mobile, already drifted. → one root cause behind four findings.

SEO metadata & schema snapshot

robots.txt — URL allowed?allowed · AI crawlers not blocked
In sitemap.xml?listed
Structured dataOrganization only · stale logo
Open the full HTML report & checklist
What you get ② · the action checklist

Grouped by discipline — Now / Change / Why, one checkbox each.

Real items from the Landbot homepage audit. Click an item to check it off.

Action Checklist — Landbot.io Homepage 0 / 3 complete
Performance 1 item
Accessibility 1 item
SEO 1 item
Open the full HTML checklist
How it prioritizes

Scored on five dimensions, plotted by impact × effort.

Impact → Effort →
Quick Wins
High impact · low effort. Do first — safe momentum.
High-Impact
High impact · high effort. Plan & sequence deliberately.
Fill-ins
Low impact · low effort. Batch when convenient.
Reconsider
Low impact · high effort. Usually defer or drop.

Every finding scored on

User impact
effect on real users' experience
H / M / L
Business impact
revenue, leads, brand, strategy
H / M / L
Technical impact
perf, SEO, a11y, maintainability
H / M / L
Effort
time, coordination, unknowns
S / M / L
Risk
regression likelihood if changed
H / M / L

Bucketed into four roadmap tiers

Quick Wins
now
Medium
next
High-Impact
plan
Long-Term
strategic

Within each tier: order by impact first, then risk, then effort.

Real example ① · landbot.io homepage

Fundamentally healthy — B+ with a clear path to A.

LCP · field p75
0.00s
Needs improvement
INP · field p75
0ms
Good
CLS · field p75
0.00
Good
The standout finding

One dual-hero Webflow anti-pattern → one root cause, four findings.

Desktop and mobile ship two different hero sections — different headline, value prop and CTA — with the desktop <h1> hidden via display:none on mobile. That single decision hurts four disciplines at once:

Performance
Ships a duplicate hero — inflates the 442 KB payload.
Accessibility
Mobile AT users get no H1 — it's display:none.
SEO
Divergent headings fragment the page's signal.
Conversion
A different promise by device; demo missing on mobile.
Real example ② · landbot.io/pricing

The dramatic one — and the biggest win for the least work.

CLS · lab + field p75
0.00
Worst possible — real users

A perfect 1.00 Cumulative Layout Shift means the page visibly jumps under the reader on every visit — and it's in the field data, not just the lab.

HTML payload0 KB
DOM nodes0
Dimensionless images0
JSON-LD schema0
The fixLighthouse: SEO 100 · A11y 92 · BP 73

Set explicit width & height on those 1,158 images.

One quick win moves the worst metric on the entire site — reserved space stops the layout collapsing as images load.

Track progress over time

Run it again after fixes — and watch it improve.

Because every report has the same shape, you can put two runs side by side and see exactly what moved.

What we measureJun 18 · first runAug 1 · after quick winsChange
Overall gradeB+A− Up
LCP · load speed (real users)2.59 s2.31 s −0.28 s
CLS · layout jump (real users)0.040.03 still good
Muted-text contrast3.36 : 1 · fails4.6 : 1 · passes fixed
Console errors10 cleared
Structured dataOrganization only+ SoftwareApplication added
Open “High” issues41 −3

The second column is an example re-run after shipping the Quick Wins — same audit, same page, a later date. Each new run just adds a column.

Why it matters for Growth

Four reasons this matters for Growth.

Faster pages → better rankings, more sign-ups

Google uses page speed as a ranking signal, and slow pages lose sales. On phones — where most people visit and pages are slowest — speed decides whether someone waits or leaves.

The pricing page's CLS 1.00 and the homepage's 2.59 s load are exactly what quietly holds back paid and organic results.

AI search → a new way to get found

ChatGPT, Perplexity, Claude and Google's AI answers now reply to buyers directly, quoting pages they can easily read and trust. These checks make sure your pages can be read, your info is machine-readable, and AI isn't blocked from your site.

A new way to get discovered that most competitors haven't set up yet.

Consistency → faster, cheaper reviews

The same checks in the same order every time means results don't depend on who ran them. You can compare pages and track one over time, the easy wins are obvious, and the team stops re-hashing the same debates.

Reviews become a routine, not a big one-off effort.

One shared language with dev & design

Every problem gets an ID, a severity and an effort tag — so marketing, engineering and design all describe it the same way. Less back-and-forth, fewer “is this really a bug?” threads, faster hand-offs.

The report becomes the one place everyone checks.

The cost of waiting adds up

Every quarter a fixable CLS 1.00, a blocked AI crawler, or a missing review score stays live is discovery and sales you don't get back — on your most important pages. Running the check is cheap and repeatable; leaving it isn't.

How to use it · next steps

Point it at a page this week.

Just say the word — in Claude Code

“Audit https://landbot.io/pricing”
“Why is my LCP bad on this page?”
“Review this hero for conversion”
“Generate the report & checklist”

Even a small question runs the full check — so nothing gets missed.

Where outputs land
Markdown report + checklist in audits/ · PDF + HTML on request.
How often to run it
Key templates quarterly — and before every launch.
Your first audit
Pick one high-traffic page. Run it. Ship the quick wins.
In one glance

Nine disciplines. One evidence capture.
One ranked, repeatable report.

Run your first audit

In Claude Code: “audit <url>” → review the exec summary → “generate the report” → ship the Quick Wins first.

The one-liner

A senior web consultant that reviews every page across every discipline — fast, consistent, and evidence-backed.

Thanks — questions welcome. Press O to jump to any slide.