Communitygithub.com

cro-audit

Shows an agent how to art-direct and build "cro audit" so the concrete output is a landing page, homepage, or portfolio. The procedure moves through CRO audit, Inputs, Steps. Use it when a new assignment calls for this craft.

O que é cro-audit?

cro-audit is a Claude Code agent skill that shows an agent how to art-direct and build "cro audit" so the concrete output is a landing page, homepage, or portfolio. The procedure moves through CRO audit, Inputs, Steps. Use it when a new assignment calls for this craft.

Funciona com~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/mavrin-xv/landing-factory/tree/HEAD/skills/cro-audit

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

CRO audit

Find what stops a visitor from acting, in the order worth fixing. The score is a structured review, not a prediction; its value is the fix order.

Inputs

  • The page (URL or file) and its screenshots at 390 and 1440 (landing-qa's shot.py).
  • The page job and the traffic source. Table: references/page-jobs.md.
  • The ad or post the visitor clicked.
  • Any real numbers the owner has (conversion rate, bounce, scroll depth), with their source.

Steps

  1. Set the page job. Write it in a copy of templates/cro-scores.json. A page is judged against its job; a waitlist with no price is fine, a cold sale with no price is not.
  2. Run first-screen-check first. Its result feeds headline, above_fold, cta and message_match.
  3. Score the 12 dimensions 0 to 10 with the anchors in references/rubric.md. Write a note for every score under 8: the block, what is wrong.
  4. Total it. python3 scripts/cro_score.py cro-scores.json. It applies the weights, the first-screen hard gate (under 60% of the first five dimensions is BLOCK), the grade, and the ordered fix list.
  5. Write the fixes in three groups: quick wins, high impact, test ideas. Each names the dimension, the block, the exact change and, for copy, two alternative lines.
  6. Hand back to the build loop (landing-factory) or to the owner as a TEARDOWN report.

Gates

  • The page job is set before any score.
  • Every score under 8 has a note naming the block.
  • Verdict not BLOCK and grade C or better before paid traffic.
  • No outside conversion statistic in the report without its source next to it.

Output

CRO audit: site/index.html (page job: cold subscription, paid social traffic)
  dimension      score  weight  points  note
  headline           8      18    14.4
  cta                8      15    12.0
  ...
  trust              6       5     3.0  no real product photo yet (placeholder), no named roasters in About
  first-screen gate: 53.8 of 67 (80%, needs 60%)
  total 78.3 of 100, grade B, verdict B
fix list (fix order stage, then points lost):
  1. [2 headline] headline: 3.6 points lost.
  ...

Full run: examples/northwind-roasters/out/cro_score.txt from examples/northwind-roasters/cro-scores.json.

Failure modes

TrapWhat it looks likeInstead
Generic ideala waitlist marked down for "no pricing"score against the page job
Polish firstbutton colors debated while the headline is a sloganthe fix order: job, headline, sections, proof, friction, polish
Borrowed statistics"red buttons convert 21% better"only numbers with a source, ideally the owner's own
Score as forecast"grade B means 4% conversion"the score orders fixes; tests measure conversion
Vague fixes"improve trust"the block, the exact change, two alternative lines
Good FAQ hides a bad herototal 70, first screen weakthe hard gate blocks it
One reviewer's tastea 3 where a colleague gives an 8two reviewers on the big five; talk when they differ by more than 2

Individual skills in this repo

This repo contains 4 individual skills — each has its own dedicated page.

landing-copy

Design skill. Writes and checks the words of a one-offer landing page. It turns the offer into a hero with the outcome and the cost, a mechanism, segments, proof and an honest offer block in skeptic order, then lints the copy for dashes, hype, fake urgency, income promises and numbers missing from the facts file, and scores it on a 7-dimension gate. Use when writing or rewriting landing page copy, when the user says "write the copy", "the hero is weak", "nobody understands what we sell", "check this copy", or

landing-design

Design skill. Designs and builds the HTML and CSS of a landing page that does not look generated. It commits to one written design read, sets tokens with one accent and an off-black ink, builds mobile first at 390, gives every section a visual, sizes grids to the content, and lints the result for the tells of a template page. Use when building or restyling a landing page, when the user says "make it look less AI", "it looks like a template", "design the sections", "fix the mobile layout", or after the copy fo

landing-factory

Design skill. Builds a converting landing page from a reference URL and a brief, in rounds. It reverses the reference, writes the page architecture, applies a design canon and a copy canon, builds mobile first, and runs the gates (copy lint, design lint, wiring, screenshots, first screen, copy score, CRO score) before every round is shown. Use when the user asks to "make a landing page like this one", "build a sales page", "clone this site for my product", "redo our landing", "fix the landing after feedback",

landing-qa

Shows an agent how to art-direct and build "landing qa" so the concrete output is a landing page, homepage, or portfolio. The procedure moves through Landing QA, Inputs, Steps. Use it when a new assignment calls for this craft.

Habilidades Relacionadas