agentleFS
ZachArticulateVZachArticulateV/designer-pro-and-seo/skills/design-cro/SKILL.md

design-cro

Skill10 starsChanged 27 days agoMITView on GitHub

Run a heuristic conversion-rate-optimization review of a landing or funnel page — CTA hierarchy, above-fold weight, form friction, trust-signal placement, copy clarity, and decision fatigue — scoring each finding by impact over effort. Uses Playwright for in-browser thumb-zone and interaction checks when connected; otherwise reviews the fetched HTML and flags those as manual checks. Trigger when the user says "cro", "conversion review", "why isn't this converting", "landing page review", "funnel review", "improve conversions", or "checkout friction review".

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Optional in-browser pass: If Playwright is available, check thumb-zone reachability and real interaction.

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

design-cro

Family: design Status: Stable

Purpose

A dedicated CRO skill. Runs a heuristic review of a landing page or funnel against established conversion principles and produces a prioritized list of conversion-killing issues with specific fixes. Works on a URL or local HTML with no external tools; Playwright optionally adds in-browser checks (thumb zones, real interaction).

Reviews against: CTA hierarchy (one primary), above-fold weight, form friction, trust signals near the decision, copy clarity (benefit-led, 3-second headline), decision fatigue, and mobile reality.

Triggers

  • "cro" / "conversion review" / "improve conversions"
  • "why isn't this converting"
  • "landing page review" / "funnel review"
  • "checkout friction review"

Inputs

  • Target URL or local build path
  • Conversion goal (lead form / signup / purchase / call)
  • Target audience and page type (landing | pricing | checkout | signup | contact)

Steps

  1. Run the CRO audit on the URL (SSRF-guarded fetch) or local HTML:
    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/design/cro_audit.py" --file landing.html --goal lead --human   # or --url <URL>
    K1–K13 (references/design-cro/cro-heuristics.md): CTA presence and hierarchy in the first screen, generic CTA labels, form length and needlessly required fields, trust signals and their distance from the decision, contact path and tap-to-call, headline clarity, first-screen value copy, autoplay media, long pages with one CTA. Each finding cites its data/ux-rules.csv conversion rule and carries Impact + Effort.
  2. Judge what the script can't — visual weight and contrast of the primary CTA, whether the offer itself is compelling, message match with the ad / search intent.
  3. Optional in-browser pass. If Playwright is available, check thumb-zone reachability and real interaction; otherwise note that as a manual check.
  4. Score each finding by Impact (high/med/low) and Fix Effort (high/med/low).
  5. Render the findings ordered by Impact ÷ Effort, each with a specific fix. For copy fixes, hand to copywriting.

Outputs

  • CRO report: prioritized fix list, each tagged Impact + Effort, ordered by leverage
  • Specific, actionable recommendation per finding

Dependencies

  • scripts/design/cro_audit.py (required) — the K1–K13 heuristic engine
  • data/ux-rules.csv (required) — the conversion rule set each finding cites
  • references/design-cro/cro-heuristics.md (required) — catalog, leverage ranking, limits
  • Playwright (optional — adds in-browser thumb-zone/interaction checks; free path: manual thumb-zone inspection of the fetched HTML, noted in the report)
  • copywriting (optional — drafts copy fixes; free path: inline copy recommendation per finding)

Notes

CRO heuristics produce hypotheses to test, ranked by likely impact — not a substitute for A/B testing. Pair with seo-drift to confirm changes caused no SEO regression.

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.