Systems Lab

Agent skill

product-complexity-detection

AI prompt to detect product complexity from public sources (Petra Hajal)

activeSelf-containedInstructions only653 words

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

What it does when it runs

AI prompt to detect product complexity 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 product-complexity-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/product-complexity-detection"
mkdir -p ~/.claude/skills/product-complexity-detection
cp -R "/tmp/gtmskills/skills/product-complexity-detection/." ~/.claude/skills/product-complexity-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/product-complexity-detection/SKILL.md, which is licensed MIT (repository). 653 words, 13 headings.

Product Complexity Detection

You are using Petra Hajal's methodology for detecting product complexity, 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.)

Product complexity is a strong predictor for:

  • Need for customer success/support tools
  • Onboarding and training solutions
  • Documentation platforms
  • Implementation services

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 complexity matters for their use case

Process

  1. Analyze Public Sources

    Sources to Check:

    • Product documentation (help center, docs site)
    • User reviews (G2, Capterra, TrustRadius)
    • Job postings (implementation, support, CS roles)
    • Pricing page (tiers, enterprise features)
    • Customer case studies (implementation mentions)
  2. Detection Prompt

    Claygent/AI Prompt:

    Analyze {{Company Website}} and related public sources to assess product complexity.
    
    Check for these complexity indicators:
    
    DOCUMENTATION:
    - Does the product have extensive documentation? (Help center, docs site)
    - Are there video tutorials or training materials?
    - Is there a certification program?
    
    USER FEEDBACK:
    - Do G2/Capterra reviews mention "learning curve" or "implementation time"?
    - Are there complaints about complexity or praise for depth?
    
    SUPPORT STRUCTURE:
    - Are there implementation specialists or onboarding roles in job postings?
    - Is there a professional services offering?
    - Multiple support tiers (basic, premium, enterprise)?
    
    PRODUCT SIGNALS:
    - Multiple pricing tiers with feature gating?
    - API/integrations section prominent?
    - Enterprise or "Contact Sales" tier?
    
    Return:
    - Complexity Score: Low / Medium / High
    - Key Evidence: [Top 3 signals observed]
    - Confidence: High / Medium / Low
    
    If insufficient data, return: "Unable to determine - [what's missing]"
    
  3. Output Format

    ## Product Complexity Analysis: [Company]
    
    ### Complexity Score: [Low/Medium/High]
    
    ### Evidence
    
    | Signal | Finding | Source |
    |--------|---------|--------|
    | Documentation depth | [Finding] | [URL/Source] |
    | User review themes | [Finding] | [G2/Capterra] |
    | Support structure | [Finding] | [Careers/Website] |
    | Product indicators | [Finding] | [Pricing/Features] |
    
    ### Confidence Level: [High/Medium/Low]
    
    [Explanation of confidence]
    
    ### Implications
    
    If selling [X], this complexity level suggests:
    - [Implication 1]
    - [Implication 2]
    

Example

Input: "Check product complexity for Salesforce"

Output:

## Product Complexity Analysis: Salesforce

### Complexity Score: High

### Evidence

| Signal | Finding | Source |
|--------|---------|--------|
| Documentation depth | Extensive Trailhead learning platform with certifications | trailhead.salesforce.com |
| User review themes | "Steep learning curve" is a recurring theme in reviews | G2 reviews |
| Support structure | Multiple CS, Implementation, and Admin roles posted | LinkedIn |
| Product indicators | 4 product clouds, each with 3+ pricing tiers | salesforce.com/pricing |

### Confidence Level: High

Multiple strong signals across all categories. Salesforce is definitionally complex.

### Implications

If selling customer success tools, this complexity suggests:
- High need for onboarding/training solutions
- Likely existing budget for implementation support
- Pain around time-to-value for new users

Complexity Indicators Cheat Sheet

High Complexity:

  • Certification programs
  • Professional services team
  • Implementation timeline mentioned
  • "Learning curve" in reviews
  • Enterprise sales motion

Medium Complexity:

  • Help center exists
  • Onboarding emails/sequences
  • Some training content
  • Mixed review feedback
  • Self-serve + sales-assist

Low Complexity:

  • Minimal documentation
  • No training needed
  • "Easy to use" in reviews
  • Pure self-serve
  • Single pricing tier

Related Skills

  • /data-point-research - Framework for custom signals
  • /plg-company-detection - Related complexity signal
  • /multi-product-detection - Related complexity signal
  • /saas-identification - Basic classification

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 product-complexity-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.