Agent skill · Audited from source

Landing Page Creator

skill · Affitor/affiliate-skillsMIT licenceAudited 15 Oct 2026 · source 2515ce9634da

★ 713pushed 2 days agoversion 1.0
✓SAFEGrade B · 89/100 · 15 Oct 2026 · 2515ce9
713repo stars · whole Affitor/affiliate-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 2515ce9634da and found no filesystem, network or shell access and no hard-coded secrets. What it does: Build high-converting affiliate landing pages as single self-contained HTML files. Triggers on: "create a landing page for", "build a landing page", "product landing page", "affiliate landing page", "comparison page…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Landing Page Creator (Affitor/affiliate-skills)”. Retrieved 15 Oct 2026. https://modelsatlas.com/skills/affitor/landing-page-creator

Trust audit

Audit 0.4.1 · source read 15 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 2515ce9634da · 15 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherAffitor GitHub organizationOwner of the repository this skill is read from
  • Source folderAffitor/affiliate-skills/skills/landing/landing-page-creatorThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict2515ce9634daA new audit runs when the source changes
  • Repository statusNot archivedLast push 2 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Build high-converting affiliate landing pages as single self-contained HTML files. Triggers on: "create a landing page for", "build a landing page", "product landing page", "affiliate landing page", "comparison page…

---
name: landing-page-creator
description: >
  Build high-converting affiliate landing pages as single self-contained HTML files.
  Triggers on: "create a landing page for", "build a landing page", "product landing page",
  "affiliate landing page", "comparison page for", "vs page", "single product page",
  "conversion page", "sales page for affiliate", "landing page HTML", "build me a page for",
  "create a page to promote [product]", "I need a landing page", "make a page for [product]".
license: MIT
version: "1.0.0"
tags: ["affiliate-marketing", "landing-pages", "conversion", "offers", "html", "tailwind"]
compatibility: "Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent"
metadata:
  author: affitor
  version: "1.0"
  stage: S4-Landing
---

# Landing Page Creator

Build dedicated affiliate landing pages that convert. Output is a single self-contained HTML file with inline CSS — no build step, no dependencies, mobile-responsive, deployable anywhere. Supports two page types: single product spotlight and multi-product comparison.

## Stage

S4: Landing — Higher conversion than blog links because the entire page is designed around one goal: convert a visitor into a click. Landing pages are the bridge between traffic sources (social, email, ads) and the affiliate product.

## When to Use

- User wants a dedicated page to promote an affiliate product
- User wants a comparison/vs page for 2-3 competing products
- User has a product from S1 (affiliate-program-search) and needs a conversion page
- User says anything like "landing page", "sales page", "product page", "comparison page", "vs page"
- User wants to promote an affiliate product beyond blog content
- User needs a deployable HTML page for an affiliate campaign

## Input Schema

```yaml
product:                    # REQUIRED — the affiliate product to feature
  name: string              # Product name (e.g., "HeyGen")
  description: string       # What it does
  reward_value: string      # Commission (e.g., "30% recurring")
  url: string               # Affiliate link URL
  reward_type: string       # "recurring" | "one-time" | "tiered"
  cookie_days: number       # Cookie duration
  tags: string[]            # e.g., ["ai", "video", "saas"]

page_type: string           # OPTIONAL — "single" | "comparison"
                            # Default: "single"

compare_with: object[]      # OPTIONAL — products for comparison page
  - name: string            # Competitor name
    description: string     # Brief description
    url: string             # URL (non-affiliate OK)
    pricing: string         # Starting price

angle: string               # OPTIONAL — marketing angle / hook
                            # e.g., "fastest", "cheapest", "best for beginners"
                            # Default: auto-generated from product strengths

color_scheme: string        # OPTIONAL — "blue" | "green" | "purple" | "orange" | "dark" | hex code
                            # Default: "blue" (#2563eb)
```

**Chaining from S1**: If `affiliate-program-search` was run earlier in the conversation, automatically pick up `recommended_program` from its output as the `product` input. The field mapping:
- `recommended_program.name` → `product.name`
- `recommended_program.description` → `product.description`
- `recommended_program.reward_value` → `product.reward_value`
- `recommended_program.url` → `product.url`
- `recommended_program.reward_type` → `product.reward_type`
- `recommended_program.cookie_days` → `product.cookie_days`
- `recommended_program.tags` → `product.tags`

**Chaining from S3**: If `affiliate-blog-builder` was run, use `products_featured` for the comparison page's `compare_with` list.

If the user says "now make a landing page for it" after running S1 — use the recommended program. No need to ask again.

## Workflow

### Step 1: Gather Product Info

If `product` data is available from S1 chaining or user input, use it directly. Otherwise:

1. Use `web_search` to research the product: `"[product name] features pricing review"`
2. Gather: name, description, key features (3-6), pricing, target audience, top competitors
3. If `page_type = comparison` and `compare_with` is empty:
   - Search: `"best alternatives to [product.name]" OR "[product.name] vs"`
   - Find 1-2 competitors with pricing, features, and positioning

### Step 2: Plan Page Structure

Read `references/conversion-principles.md` for AIDA framework, CTA placement, and design rules.

Choose `page_type` if not specified:
- If user mentions "vs", "compare", "comparison", or provides `compare_with` → `comparison`
- Otherwise → `single`

Plan the page sections based on type:

**Single product:**
1. FTC disclosure (above fold)
2. Hero: headline + subtitle + primary CTA + trust signal
3. Trust bar: rating, user count, press mention
4. Features: 3-column grid (3-6 features as benefits)
5. Pricing: price + CTA
6. Testimonial: one strong quote
7. Who is this for: audience list
8. FAQ: 4-6 questions addressing objections
9. Final CTA: headline + CTA button
10. Footer: Affitor branding

**Comparison:**
1. FTC disclosure (above fold)
2. Hero: "[A] vs [B]" headline + subtitle
3. Comparison table: feature rows with winner highlights
4. Individual product sections: description + pros/cons + CTA each
5. Winner callout: clear recommendation with reasoning
6. FAQ: 4-6 comparison-specific questions
7. Dual CTA: buttons for top 2 products
8. Footer: Affitor branding

Map the user's `color_scheme` to CSS custom properties:
- `blue` → `--color-primary: #2563eb`
- `green` → `--color-primary: #059669`
- `purple` → `--color-primary: #7c3aed`
- `orange` → `--color-primary: #ea580c`
- `dark` → `--color-primary: #3b82f6; --color-bg: #0f172a; --color-surface: #1e293b; --color-text: #f1f5f9`
- Hex code → use directly as `--color-primary`

### Step 3: Write Full HTML

Read the matching template from `templates/`:
- `templates/single-product.html` for `page_type = single`
- `templates/comparison

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 2515ce9

Download folder ↗
git clone https://github.com/Affitor/affiliate-skills
git -C affiliate-skills checkout 2515ce9634da

The author documents no install command, so this uses the repository directly. Our verdict covers commit 2515ce9634da only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
Gemini CLIMentioned in its text, not testedSkills for Gemini CLI · About Gemini CLI
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
WindsurfMentioned in its text, not testedSkills for Windsurf · About Windsurf
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 2515ce9634da

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/affitor/landing-page-creator/badge.svg)](https://modelsatlas.com/skills/affitor/landing-page-creator/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Ab Test Generator✓SAFE

Affitor/affiliate-skills

Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my landing page…

★ 713Grade B
Affiliate Blog Builder✓SAFE

Affitor/affiliate-skills

Write SEO-optimized affiliate blog articles, product reviews, comparison posts, listicles, and how-to guides. Triggers on: "write a blog post about", "review of [product]", "best [category] article", "comparison blog",…

★ 713Grade B
Affiliate Program Search✓SAFE

Affitor/affiliate-skills

Research and evaluate affiliate programs to find the best ones to promote. Use this skill when the user asks anything about finding affiliate programs, comparing commission rates, evaluating affiliate opportunities,…

★ 713Grade B
Bio Link Deployer✓SAFE

Affitor/affiliate-skills

Create a Linktree-style bio link hub page as a single self-contained HTML file. Triggers on: "create a bio link page", "make a linktree", "link in bio page", "bio link", "link hub", "create my link page", "all my links…

★ 713Grade B
Bonus Stack Builder✓SAFE

Affitor/affiliate-skills

Design exclusive bonus packages that make YOUR affiliate link the obvious choice. Triggers on: "create bonuses for", "bonus stack", "what bonuses should I offer", "bonus ideas for", "exclusive bonuses", "differentiate…

★ 713Grade B
Category Designer✓SAFE

Affitor/affiliate-skills

Define a new category where your product wins by default. Reframe the buying decision. Triggers on: "create a category", "category design", "define my category", "category of one", "reframe the market", "position as…

★ 713Grade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/affitor/landing-page-creator/badge.svg)](https://modelsatlas.com/skills/affitor/landing-page-creator/)

Questions about Landing Page Creator

What does the Landing Page Creator skill do?
50 AI agent skills for affiliate marketing. Research trending content, write data-backed posts, generate infographics, build landing pages, deploy — full flywheel with social intelligence. Works with Claude Code, Pi, ChatGPT, Gemini, Cursor, Windsurf, any AI.
Is Landing Page Creator safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Landing Page Creator access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Landing Page Creator work with?
Its documentation mentions claude-code, cursor, gemini-cli, openclaw and windsurf. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (2515ce9634da), read on 2026-10-15. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.