Install
$ agentstack add skill-fjilvi-afk-growthlens-landing-ux-review ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Landing Page UX Review
> A structured, conversion-oriented critique of a single landing page — what to > fix first to lift conversion.
What it does
Reviews one landing page against a conversion-UX rubric and returns a scored, section-by-section critique with a prioritized fix list. It focuses on the decisions that move conversion — clarity, hierarchy, trust, and friction — not on subjective aesthetics.
When to use this skill
- "Why isn't this landing page converting? "
- "Review the UX / do a CRO review of this page."
- "Improve this page" (with a URL or screenshot).
- Pre-launch check on a new landing or sales page.
Inputs needed
- Required: the page URL, or screenshots (desktop and ideally mobile).
- Helpful: the page's single goal (the one action), the traffic source, and
the target audience — UX is only "good" relative to a goal and a visitor.
- If the goal isn't obvious, ask: "What's the one action this page should drive?"
Method
Score each area 1–5 and note the highest-leverage issue. Use the LIFT-style levers (value proposition, clarity, relevance, urgency, anxiety, distraction).
- Above the fold — within 5 seconds: is it clear what this is, who it's for,
and what to do? Is the primary CTA visible without scrolling?
- Value proposition & clarity — headline strength, benefit vs feature
framing, jargon, reading ease.
- Visual hierarchy — does the eye flow to the headline → proof → CTA? Are
there competing focal points?
- Relevance / message-match — does the page match the promise of the ad,
email, or search query that sent the visitor?
- Call to action — wording (action + value), prominence, repetition,
contrast, and whether there's one primary action or many competing ones.
- Trust & proof — testimonials, logos, numbers, guarantees, security — and
whether they appear near the decision point.
- Friction & anxiety — form length, required fields, unclear pricing,
missing answers to obvious objections, risk reducers.
- Distraction — nav, links, and elements that pull away from the goal.
- Mobile & performance — layout on mobile, tap targets, apparent load speed,
anything that breaks the fold on small screens.
Output format
# Landing UX Review —
## TL;DR
- Overall __/5. The one change that will move conversion most.
## Page goal & visitor
- Primary action: · Traffic source: · Audience:
## Scorecard
| Area | Score /5 | Key issue |
|------|----------|-----------|
| Above the fold | | |
| Value prop & clarity | | |
| Visual hierarchy | | |
| Message-match | | |
| Call to action | | |
| Trust & proof | | |
| Friction & anxiety | | |
| Distraction | | |
| Mobile & performance | | |
## Prioritized fixes
| # | Fix | Area | Why it matters | Impact | Effort |
|---|-----|------|----------------|--------|--------|
## Quick wins (ship today)
- 3 changes that are fast and high-confidence.
Quality bar
- Tie every critique to a conversion lever and the page's stated goal.
- Reference specific page elements ("the second-fold CTA reads 'Submit'"), not
vague impressions.
- Don't invent traffic, bounce, or conversion numbers.
- Separate high-confidence issues from "test this" hypotheses.
Common mistakes to avoid
- Aesthetic opinions ("I'd use a different blue") over conversion impact.
- A flat list of issues with no prioritization.
- Reviewing without knowing the page's one goal.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: fjilvvi
- Source: fjilvvi/growthlens
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.