Systems Lab

Agent skill

multi-product-detection

AI prompt to detect multi-product company structure from public sources (Petra Hajal)

activeSelf-containedInstructions only707 words

From jurjen-gtm-engineer/gtmskills · 55 skill entries · 0 · pushed 2026-10-04

What it does when it runs

AI prompt to detect multi-product company structure from public sources (Petra Hajal)

Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about multi-product-detection

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/jurjen-gtm-engineer/gtmskills.git /tmp/gtmskills
git -C /tmp/gtmskills sparse-checkout set "skills/multi-product-detection"
mkdir -p ~/.claude/skills/multi-product-detection
cp -R "/tmp/gtmskills/skills/multi-product-detection/." ~/.claude/skills/multi-product-detection/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from jurjen-gtm-engineer/gtmskills/blob/77dc0b3112dbf6cf906dfc3d526b6f7031bf964c/skills/multi-product-detection/SKILL.md, which is licensed MIT (repository). 707 words, 14 headings.

Multi-Product Detection

You are using Petra Hajal's methodology for detecting multi-product company structure, a signal that can't be bought from standard data providers but predicts fit for certain solutions.

Why This Matters

Build data you can't buy. (Idea credited to Petra Hajal.)

Multi-product structure is a strong predictor for:

  • Platform/integration complexity
  • Cross-sell and upsell dynamics
  • Need for unified analytics/reporting
  • Product management tools
  • Customer success complexity

Standard databases don't capture this. You have to detect it.

Input

User provides:

  • Company website URL
  • Or: Company name for research
  • Context on why multi-product matters for their use case

Process

  1. Analyze Public Sources

    Sources to Check:

    • Product/solutions pages
    • Pricing page structure
    • Navigation and site architecture
    • Blog/content for product announcements
    • Job postings (product team structure)
  2. Detection Prompt

    Claygent/AI Prompt:

    Analyze {{Company Website}} to determine if this company has multiple products or a single product.
    
    Check for these multi-product indicators:
    
    PRODUCT PAGES:
    - Are there multiple distinct product pages?
    - Does the navigation show "Products" with dropdown?
    - Are products branded separately?
    
    PRICING STRUCTURE:
    - Separate pricing pages per product?
    - "Suite" or "Platform" pricing?
    - Bundle discounts mentioned?
    - "Add-on" products?
    
    NAMING/BRANDING:
    - Separate product names (e.g., "Company X" vs "Company Suite" vs "Company Analytics")?
    - Sub-brands or product lines?
    - "Platform" language suggesting multiple modules?
    
    ACQUISITION HISTORY:
    - Recent acquisitions integrated as products?
    - "Formerly [Company]" anywhere?
    
    Return:
    - Product Structure: Single / Multi-Product / Suite/Platform
    - Products Identified: [List if multiple]
    - Key Evidence: [Top 3 signals observed]
    - Confidence: High / Medium / Low
    
    If insufficient data, return: "Unable to determine - [what's missing]"
    
  3. Output Format

    ## Multi-Product Analysis: [Company]
    
    ### Product Structure: [Single/Multi-Product/Suite]
    
    ### Products Identified
    
    | Product | Description | Standalone? |
    |---------|-------------|-------------|
    | [Product 1] | [Brief description] | [Yes/No] |
    | [Product 2] | [Brief description] | [Yes/No] |
    
    ### Evidence
    
    | Signal | Finding | Source |
    |--------|---------|--------|
    | Product pages | [Finding] | [URL] |
    | Pricing structure | [Finding] | [URL] |
    | Naming/branding | [Finding] | [Source] |
    
    ### Confidence Level: [High/Medium/Low]
    
    [Explanation of confidence]
    
    ### Implications
    
    If selling [X], multi-product structure suggests:
    - [Implication 1]
    - [Implication 2]
    

Example

Input: "Check if HubSpot has multiple products"

Output:

## Multi-Product Analysis: HubSpot

### Product Structure: Multi-Product (Suite)

### Products Identified

| Product | Description | Standalone? |
|---------|-------------|-------------|
| Marketing Hub | Marketing automation | Yes |
| Sales Hub | CRM and sales tools | Yes |
| Service Hub | Customer service | Yes |
| CMS Hub | Website/content | Yes |
| Operations Hub | Data sync and automation | Yes |
| Commerce Hub | Payments and commerce | Yes |

### Evidence

| Signal | Finding | Source |
|--------|---------|--------|
| Product pages | Six distinct "Hub" products with separate pages | hubspot.com/products |
| Pricing structure | Each Hub priced separately, bundle discounts available | hubspot.com/pricing |
| Naming/branding | Consistent "[X] Hub" naming convention | Navigation |

### Confidence Level: High

Clear multi-product structure with distinct products and pricing.

### Implications

If selling integration/data tools, multi-product structure suggests:
- Data silos between Hubs
- Need for unified reporting across products
- Complex customer journey across products

Multi-Product Indicators Cheat Sheet

Multi-Product Signals:

  • "Products" dropdown in navigation
  • Separate pricing pages
  • Distinct product names
  • "Add [Product]" or "Upgrade" CTAs
  • Product-specific job postings

Suite/Platform Signals:

  • "Platform" or "Suite" branding
  • Bundle pricing prominent
  • "All-in-one" messaging
  • Unified dashboard mentioned
  • Cross-product features highlighted

Single Product Signals:

  • No "Products" section
  • One pricing page with tiers
  • Features, not products
  • Single product name throughout

Related Skills

  • /data-point-research - Framework for custom signals
  • /product-complexity-detection - Related signal
  • /plg-company-detection - Related signal
  • /pricing-strategy - Pricing page analysis

Credits

"Build data you can't buy" is Petra Hajal's line and approach. The prompts and wording here are ours.


Examples are illustrative. Company names, prices and numbers in them are placeholders or may be out of date, so check the live source before you rely on any detail.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what multi-product-detection does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.