Landing page intel

Extract competitor and customer intelligence from any company's landing page HTML.

How to use it

  1. Hit Copy SKILL.md — or use the Claude Code line below to get every file.
  2. Claude: ⋯ → Download .md, then Customize → Skills → Add → Upload skill.
    ChatGPT: make a Project and paste it into Instructions.
    Neither? Paste it at the top of a new chat — it works for that chat.
  3. Describe your job in plain words. The AI follows the skill from there.
Claude Code — installs the whole folder, not just SKILL.md
npx degit gooseworks-ai/goose-skills/skills/competitive-intel/capabilities/landing-page-intel#main ~/.claude/skills/landing-page-intel

For one project only, change the path to .claude/skills/landing-page-intel. This skill also uses report.json, Next.js — copying SKILL.md alone won't be enough. See the folder on GitHub.

Not working?
  • Check which app you pasted it into — the steps above name the right one.
  • Some skills need the paid tier of Claude or ChatGPT.
Step-by-step guide with screenshots · Ask in the forum

Paste into Claude, ChatGPT or Cursor.

Show the full text68 lines
landing-page-intel/SKILL.md68 lines3.0 KBpushed 96d agoRawView on GitHub

Landing Page Intel

Extract GTM-relevant intelligence from any company's landing page by scraping its HTML source.

Quick Start

Only dependency is pip install requests. No API key needed.

# Basic scan of a single URL
python3 skills/landing-page-intel/scripts/scrape_landing_page.py \
  --url "https://example.com"

# Scan multiple pages of the same site
python3 skills/landing-page-intel/scripts/scrape_landing_page.py \
  --url "https://example.com" --pages "/,/pricing,/about"

# Output as summary table instead of JSON
python3 skills/landing-page-intel/scripts/scrape_landing_page.py \
  --url "https://example.com" --output summary

# Save full report to file
python3 skills/landing-page-intel/scripts/scrape_landing_page.py \
  --url "https://example.com" --output json > report.json

What It Extracts

Category Details
Tech Stack Analytics (GA4, Mixpanel, Amplitude, PostHog, Heap), marketing automation (HubSpot, Marketo, Pardot), chat widgets (Intercom, Drift, Crisp, Zendesk), A/B testing (Optimizely, VWO, LaunchDarkly), session recording (Hotjar, FullStory, LogRocket), CDPs (Segment, Clearbit, 6sense)
Ad Pixels Meta Pixel, Google Ads, LinkedIn Insight Tag, TikTok pixel, Twitter pixel
Customer Logos Image URLs from "trusted by" / logo carousel sections, grouped by directory
SEO Metadata Title, meta description, Open Graph tags, Twitter Cards, canonical URL, structured data (JSON-LD), hreflang tags
CTAs & Sales Motion All CTA button text and links — reveals PLG vs sales-led motion
Social Proof Testimonials, customer counts, case study links, badge images
Integrations Links to integration/partner pages, embedded third-party widgets
Hidden Elements Content in display:none, hidden, or HTML comments that may reveal upcoming features
Infrastructure CMS platform (Webflow, WordPress, Next.js, etc.), detected from HTML signatures

CLI Reference

Flag Default Description
--url required Target website URL
--pages / Comma-separated paths to scan (e.g., /,/pricing,/about)
--output json Output format: json or summary
--timeout 15 Request timeout in seconds

GTM Use Cases

  • Competitive intel: See what tools competitors use, how they position, who their customers are
  • Prospect research: Before a sales call, scan a prospect's site to understand their stack and maturity
  • Market mapping: Scan multiple competitors to compare positioning, customer segments, and GTM motions
  • Customer discovery: Extract competitor customer logos as potential prospects for your own product

Cost

Free. No API keys required. Uses only HTTP requests to fetch public HTML.

1---
2name: landing-page-intel
3description: >
4 Extract competitor and customer intelligence from any company's landing page HTML.
5 Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata,
6 CTAs, hidden elements, and more. No API keys required.
7---
8 
9# Landing Page Intel
10 
11Extract GTM-relevant intelligence from any company's landing page by scraping its HTML source.
12 
13## Quick Start
14 
15Only dependency is `pip install requests`. No API key needed.
16 
17```bash
18# Basic scan of a single URL
19python3 skills/landing-page-intel/scripts/scrape_landing_page.py \
20 --url "https://example.com"
21 
22# Scan multiple pages of the same site
23python3 skills/landing-page-intel/scripts/scrape_landing_page.py \
24 --url "https://example.com" --pages "/,/pricing,/about"
25 
26# Output as summary table instead of JSON
27python3 skills/landing-page-intel/scripts/scrape_landing_page.py \
28 --url "https://example.com" --output summary
29 
30# Save full report to file
31python3 skills/landing-page-intel/scripts/scrape_landing_page.py \
32 --url "https://example.com" --output json > report.json
33```
34 
35## What It Extracts
36 
37| Category | Details |
38|----------|---------|
39| **Tech Stack** | Analytics (GA4, Mixpanel, Amplitude, PostHog, Heap), marketing automation (HubSpot, Marketo, Pardot), chat widgets (Intercom, Drift, Crisp, Zendesk), A/B testing (Optimizely, VWO, LaunchDarkly), session recording (Hotjar, FullStory, LogRocket), CDPs (Segment, Clearbit, 6sense) |
40| **Ad Pixels** | Meta Pixel, Google Ads, LinkedIn Insight Tag, TikTok pixel, Twitter pixel |
41| **Customer Logos** | Image URLs from "trusted by" / logo carousel sections, grouped by directory |
42| **SEO Metadata** | Title, meta description, Open Graph tags, Twitter Cards, canonical URL, structured data (JSON-LD), hreflang tags |
43| **CTAs & Sales Motion** | All CTA button text and links — reveals PLG vs sales-led motion |
44| **Social Proof** | Testimonials, customer counts, case study links, badge images |
45| **Integrations** | Links to integration/partner pages, embedded third-party widgets |
46| **Hidden Elements** | Content in `display:none`, `hidden`, or HTML comments that may reveal upcoming features |
47| **Infrastructure** | CMS platform (Webflow, WordPress, Next.js, etc.), detected from HTML signatures |
48 
49## CLI Reference
50 
51| Flag | Default | Description |
52|------|---------|-------------|
53| `--url` | *required* | Target website URL |
54| `--pages` | `/` | Comma-separated paths to scan (e.g., `/,/pricing,/about`) |
55| `--output` | `json` | Output format: `json` or `summary` |
56| `--timeout` | `15` | Request timeout in seconds |
57 
58## GTM Use Cases
59 
60- **Competitive intel**: See what tools competitors use, how they position, who their customers are
61- **Prospect research**: Before a sales call, scan a prospect's site to understand their stack and maturity
62- **Market mapping**: Scan multiple competitors to compare positioning, customer segments, and GTM motions
63- **Customer discovery**: Extract competitor customer logos as potential prospects for your own product
64 
65## Cost
66 
67Free. No API keys required. Uses only HTTP requests to fetch public HTML.
68 

Discussion

Alternatives

Also in Landing page copy