agentleFS
Infinite-Labs-AIInfinite-Labs-AI/infinite-skills/skills/cro-audit/SKILL.md

cro-audit

Skill43 starsChanged 4 months agoMITView on GitHub

Use when reviewing a landing page, homepage, signup page, pricing page, checkout, form, onboarding screen, popup, or paywall for conversion blockers.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the provided URL, screenshot, copy, or code.

    line 12
  2. Distinctive:

    Avoid pretending all pages need the same pattern.

    line 53

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CRO Audit

Find the points on a page or flow where visitors lose clarity, trust, interest, or momentum.

Inspect The Page

Use the provided URL, screenshot, copy, or code. If the surface is live, inspect desktop and mobile when possible.

Capture:

  • Visitor source and intent.
  • Main promise above the fold.
  • CTA text, count, and location.
  • Form or checkout effort.
  • Proof and trust elements.
  • Objections addressed or ignored.
  • Visual hierarchy and reading order.
  • Mobile readability and tap targets.
  • Load or rendering issues that affect the decision.

Analyze Friction

Classify each issue:

  • Message friction: reader cannot tell what it is, who it is for, or why it matters.
  • Trust friction: claim is bigger than proof.
  • Choice friction: too many actions or unclear next step.
  • Effort friction: form, onboarding, or checkout asks too much too early.
  • Timing friction: the ask appears before the reader has enough confidence.
  • Mismatch friction: page does not match the traffic promise.
  • Technical friction: speed, layout, accessibility, broken states.

Follow The Visitor Decision

Map the page as a decision path:

  • Seeing: does the visitor immediately know what this is?
  • Believing: does the promise match their intent and feel specific?
  • Trusting: is the proof strong enough for the ask?
  • Acting: is the next step obvious, low-friction, and appropriately timed?

For each fix, note whether it is reversible. Prefer reversible copy, layout, and proof changes before deep product or pricing changes unless the evidence is strong.

Recommend Changes

Prioritize by likely impact and effort. Include concrete replacement copy or layout changes when useful.

Avoid pretending all pages need the same pattern. A pricing page, waitlist, checkout, and enterprise demo page have different jobs.

Output

Page friction read:
[one paragraph]

Conversion path:
Visitor intent -> Page promise -> Proof -> Action

Hesitation sequence:
Seeing -> Believing -> Trusting -> Acting

Friction log:
| Step | Problem | Evidence | Fix | Reversible | Impact | Effort |

Highest-leverage changes:
1. [change]
2. [change]
3. [change]

Copy replacements:
- Current: [text]
  Replace with: [text]

Test next:
- [experiment or measurement]

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.