landingpage-cro

landingpage-cro is a skill for Claude Code from Gekkos-tech/agency-os. It costs 163 tokens per session (1,903 once invoked), scanned A, original, MIT.

A planning and review skill for structuring landing pages—web pages designed to persuade visitors to take an action—and improving their conversion rate.

In plain words
What is it for?
Use it to create a section-by-section landing-page plan, check that ads and headlines make the same promise, or audit an existing page.
Why use it?
It finds missing or misplaced sections, unclear promises, and other obstacles that may stop visitors from acting after they arrive.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ad-creative plugin — 8 skills, 2 commands shipped together

Good fit Use it to create a section-by-section landing-page plan, check that ads and headlines make the same promise, or audit an existing page.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gekkos-tech/agency-os/landingpage-cro
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Gekkos-tech/agency-os --skill landingpage-cro
Clone the repo
git clone --depth 1 https://github.com/Gekkos-tech/agency-os

Made for: Claude Code.

Or install ad-creative, the plugin that ships this one along with the rest of its 8 skills, 2 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for landingpage-cro

README.md
[![agentmods](https://agentmods.dev/badge/skills/gekkos-tech/agency-os/landingpage-cro/github.svg)](https://agentmods.dev/skills/gekkos-tech/agency-os/landingpage-cro)
Your own site
<a href="https://agentmods.dev/skills/gekkos-tech/agency-os/landingpage-cro"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/landingpage-cro/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for landingpage-cro

Your own site · 80×15
<a href="https://agentmods.dev/skills/gekkos-tech/agency-os/landingpage-cro"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/landingpage-cro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,903 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00163 $0.01903
Opus 5 $0.00081 $0.00951
Sonnet 5 $0.00033 $0.00381
Haiku 4.5 $0.00016 $0.00190

Measured 12d ago against content hash 5bb122c94f57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

landingpage-cro scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/ad-creative/skills/landingpage-cro/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Landing Page CRO — Conversion-Focused Page Structure

Design the argument of a landing page: which sections, in which order, doing which persuasive job. Output is a structural blueprint plus audit findings — not visual design, not finished copy.

© GEKKOS Tech. Licensed under MIT.

Two modes

  • Build mode (user is creating a page): run the message-match check, then produce the section sequence with per-section jobs and must-contain elements, then the measurement plan.
  • Audit mode (user asks "why isn't it converting"): fetch/read the page, check message match first, then walk the section sequence for missing/misordered jobs, then run the friction checklist. Report findings ordered by expected conversion impact, not by page order.

Message-match rule (check this first, always)

The single highest-leverage CRO factor. Two equations must hold:

  1. Ad promise == hero promise. Whatever the ad (or email, or post) promised is the first thing the hero must confirm — same offer, same benefit, same wording family, same visual world. A visitor who clicked "30% off onboarding" and lands on a generic homepage-style hero bounces before reading anything else.
  2. Keyword == H1 intent. For search traffic, the H1 must answer the query's intent (not necessarily echo the keyword verbatim, but resolve it). Someone searching "payroll software comparison" must land on a comparison, not a signup pitch.

If traffic comes from multiple distinct promises, recommend separate landing page variants per promise — one page per message, not one page for all messages.

The conversion narrative — section sequence

Default sequence for a cold-to-warm conversion page. Each section has ONE job; a section doing two jobs is doing neither. Layout patterns per section are in references/section-patterns.md.

# Section Job Must contain
1 Hero promise Confirm the click was right, state the core value in 5 seconds H1 = main benefit (message-matched), supporting subline (how/for whom), primary CTA, hero visual showing product/outcome, above the fold on mobile
2 Credibility strip Answer "can I trust these people?" before any selling Client/press logos OR review score OR key number ("12,000 customers"); compact, no headline needed
3 Problem / solution Create recognition ("that's my problem"), then map product to it Problem stated in the visitor's words, 2–4 pain points, solution framed as the mechanism (HOW it fixes it, not just "it fixes it")
4 Offer detail Make the offer concrete and evaluable What exactly they get (features as benefits), pricing or pricing-path, scope/timeline, visual of the actual product/service
5 Social proof Let others make the claims the brand can't 2–3 testimonials with full name + photo/company (specific results > praise), case numbers, ratings with source
6 Objection handling / FAQ Remove the last "yes, but…" 4–7 real objections (price, effort, switching, "will it work for MY case", contract terms) answered honestly; sourced from sales/support if available
7 Risk reversal Make saying yes safer than saying no Guarantee, free trial, free cancellation, "no credit card required", data portability — whichever is true
8 Final CTA Convert the reader who scrolled everything Repeat primary CTA + one-line benefit recap; optionally a lower-commitment secondary path (newsletter, demo) for not-ready visitors

Read the full file on GitHub · 90 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 90 lines · 163 tokens per session scan A 5bb122c94f57

Subscribe to this mod's changes

landingpage-cro is a skill published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 163 tokens to every session and 1,903 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

design-mobile-apps

Use when the user wants to design a mobile app or UI screens, when they mention their Sleek (sleek.design) projects, or when implementing Sleek designs in code (HTML, React Native, SwiftUI).

aiskillstore/marketplace · 49 tokens

diagram-design

Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, treemap, bar, line, Gantt and scatter charts, high-level…

aiskillstore/marketplace · 188 tokens

dengguang-zhaoming-bikeng-zhinan

A Chinese-language knowledge guide about home lighting, including ceiling lights, light strips, color temperature, color rendering, and room zoning.

aiskillstore/marketplace · 99 tokens

appllama-app-design-skill

Build native-feeling, benchmark-quality mobile app screens (Expo / React Native). Use when designing or implementing any mobile UI — screens, flows, onboarding, paywalls, tab bars, sheets, settings, empty states — or when polishing motion, navigation, typography, dark mode, or perceived performance. Enforces Apple HIG…

aiskillstore/marketplace · 184 tokens

archify

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…

aiskillstore/marketplace · 130 tokens

landing-page-design

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section…

aiskillstore/marketplace · 102 tokens