What does this skill do, and when should you use it?
This skill improves landing pages that receive influencer-driven traffic, covering message match, page structure, social proof, CTAs, promo codes, and mobile conversion. It uses user-supplied page, campaign, creator, conversion, audience, and offer details to produce an audit and prioritized optimization plan. Outputs include a message-match score, conversion recommendations, and an A/B testing roadmap. It does not measure post-launch campaign results; that work belongs to performance-analyzer.
Reads the landing-page URL and current state, traffic source, creator message, promo code, audience, baseline conversion rate, and goal; compares creator content with the page across message, value proposition, offer, product, and tone, producing an X/10 Message Match Score and named fixes; recommends a hero-to-CTA page structure with social-proof placement; plans CTA, promo-code auto-application, friction reduction, and mobile improvements; designs impact/effort-ranked A/B tests with hypotheses, variants, sample size, duration, and success metrics; assesses whether a dedicated creator page is warranted; and defines targets for load time, bounce rate, conversion rate, add-to-cart, AOV, UTM parameters, and attribution events. It saves plans under memory/influencer/landing-optimizer/YYYY-MM-DD-<topic>.md and promotes durable facts to memory/hot-cache.md.
- A brand is building a creator-specific page and needs the page copy to match the creator’s video.
- A promo-code campaign has weak conversion and needs its code display, auto-application, and CTA flow reviewed.
- A creator emphasizes one product benefit while the landing page leads with another, creating message discontinuity.
- A campaign sends substantial mobile traffic and needs faster, less friction-heavy conversion paths.
- A marketing team needs a staged landing-page A/B testing plan for an influencer campaign.
How do you install this skill?
- Do not treat the 2–3% benchmark, component lifts, or 2.5% outcome in the example as validated forecasts; use real experiments and power calculations.
- Obtain explicit confirmation before writing to memory or hot-cache, minimize stored promo, audience, and creator data, and define revision and rollback handling.
- For Chinese-speaking users, localize the English templates and metric definitions, and add platform, regional, privacy, and advertising-compliance checks.
- Local filesystem
In Claude Code, add and install the repository with /plugin marketplace add aaron-he-zhu/aaron-marketing-skills followed by /plugin install aaron-marketing@aaron. On Agent Skills-compatible hosts, use npx skills add aaron-he-zhu/aaron-marketing-skills; alternatively, run git clone https://github.com/aaron-he-zhu/aaron-marketing-skills. The repository is Apache-2.0 licensed. The source does not document a dedicated single-skill installation command.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/influencer/report/landing-optimizer" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Use a prompt such as: Optimize our landing page for traffic from [influencer campaign]. You can also provide the landing-page URL, campaign, creator handle, promo code, baseline conversion rate, and goal, for example: Our influencer landing page has a 1.2% conversion rate. How can we improve it?
What are this skill's strengths and limitations?
- Focused on message match and conversion for influencer traffic.
- Covers structure, social proof, CTAs, promo codes, mobile UX, and A/B testing.
- Runs at Tier 1 using user-provided data without requiring live integrations.
- Defines completion criteria, save locations, and the next measurement skill.
- By default, it does not retrieve live analytics, CMS content, or social-platform data; users must supply the relevant inputs.
- It does not measure actual post-launch performance.
- The source provides no platform-specific test report, standalone test suite, or real A/B experiment results.
- Although the roadmap includes sample size and duration, the source does not say that a specific statistical tool calculates them.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Influencer Landing Page Optimizer this page | 54 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Landing Page CRO Analysis Skill | 49 · Use with care | ★ 2.8k | 7mo ago | MIT |
| Email Experiment Designer | 56 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Ad Landing Experience Checker | 55 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Ad Creative Builder | 60 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
Compared with performance-analyzer in the same repository, this skill optimizes the landing page and plans tests, while performance-analyzer evaluates post-optimization conversion, AOV, and attribution. For paid advertising, it owns the post-click page side and pairs with ad-creative-builder, which owns the ad side.
How did FollowSkills review this skill?
The skill limits inputs to user-provided data and describes Tier 1 operation without mandatory live integrations; shared security material also documents protected memory writes and read-only or explicitly escalated connectors. However, it instructs the agent to write a durable report and promote facts to hot-cache without per-run confirmation, data minimization, sensitive marketing-data handling, or rollback guidance. Points are deducted for incomplete consent, data-flow, and recovery controls.
The steps, contract, completion criteria, and templates are largely consistent, and the skill does not require live integrations. However, sample size, test duration, and impact estimates remain placeholders; the worked example gives unsupported benchmark and lift claims; and there is no clear failure feedback for invalid inputs, inaccessible pages, or failed persistence. The score stays within the static-review ceiling.
Triggers, audience, input scope, outputs, and the boundary against post-launch measurement are reasonably clear, and the skill can operate without connectors. However, the templates are predominantly English, Chinese-language adaptation is limited, platform and compliance boundaries are under-specified, geo-relevance is marked low, and false-trigger or non-fit conditions are incomplete. Points are deducted accordingly.
Front matter supplies name, slug, version, compatibility, license, and argument hint. Quick Start, fixed steps, templates, examples, cross-references, and next-skill guidance provide good structure. Full marks are not justified because maintenance ownership, changelog/update path, and troubleshooting are not explicit in the skill; many placeholders remain; and the repository security policy's supported-version statement conflicts with the skill's 18.0.0 metadata.
The skill can produce a message-match audit, page-structure recommendations, CTA/promo-code plan, and A/B roadmap, with reusable templates and HTML snippets. However, the example presents a 1.2% to 2.5% conversion outcome and component lifts without evidence, while sample size and duration are uncomputed. Outputs therefore require substantial business and data validation, so the static score remains below the execution-based ceiling.
The skill includes structured templates, explicit completion criteria, and measurable tracking fields, while the repository contains general CI and validator tests. Those tests do not cover this skill's key paths, and the benchmark, expected-lift, and recommendation claims lack third-party sources or committed reproduction evidence. Static source review supports only limited verifiability.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →