Enrich HubSpot companies with technographic data from BuiltWith using an agent skill

mkdir -p .claude/skills/tech-enrich/scripts

---
name: tech-enrich
description: Looks up what technologies HubSpot companies use via BuiltWith. Categorizes technologies into CRM, marketing, and analytics stacks and writes them to custom HubSpot company properties.
disable-model-invocation: true
allowed-tools: Bash(python *)
---
 
Enrich HubSpot companies with technographic data:
 
1. Run: `python $SKILL_DIR/scripts/tech_enrich.py`
2. Review the per-company tech stack results
3. Confirm tech data was written to HubSpot

#!/usr/bin/env python3
"""
Technographic Enrichment: HubSpot → BuiltWith → HubSpot
Looks up tech stacks for companies and writes categorized results to HubSpot.
"""
import os
import sys
import time
from datetime import datetime
 
try:
    import requests
except ImportError:
    os.system("pip install requests -q")
    import requests
 
HUBSPOT_TOKEN = os.environ.get("HUBSPOT_TOKEN")
BUILTWITH_API_KEY = os.environ.get("BUILTWITH_API_KEY")
 
if not all([HUBSPOT_TOKEN, BUILTWITH_API_KEY]):
    print("ERROR: Set HUBSPOT_TOKEN and BUILTWITH_API_KEY environment variables")
    sys.exit(1)
 
HS_HEADERS = {"Authorization": f"Bearer {HUBSPOT_TOKEN}", "Content-Type": "application/json"}
 
CATEGORY_MAP = {
    "crm": ["crm"],
    "marketing": ["marketing-automation", "email", "marketing"],
    "analytics": ["analytics", "web-analytics"],
}
 
# --- Fetch companies ---
print("Searching for companies without tech stack data...")
companies = []
after = 0
while True:
    resp = requests.post(
        "https://api.hubapi.com/crm/v3/objects/companies/search",
        headers=HS_HEADERS,
        json={
            "filterGroups": [{"filters": [{
                "propertyName": "tech_stack_crm",
                "operator": "NOT_HAS_PROPERTY"
            }]}],
            "properties": ["domain", "name"],
            "limit": 100,
            "after": after
        }
    )
    resp.raise_for_status()
    data = resp.json()
    companies.extend(data["results"])
    if data.get("paging", {}).get("next"):
        after = data["paging"]["next"]["after"]
    else:
        break
 
print(f"Found {len(companies)} companies to enrich\n")
 
# --- Process each company ---
enriched = 0
skipped = 0
 
for company in companies:
    domain = company["properties"].get("domain")
    name = company["properties"].get("name", "Unknown")
 
    if not domain:
        print(f"  {name} — no domain, skipping")
        skipped += 1
        continue
 
    # Call BuiltWith
    bw_resp = requests.get(
        "https://api.builtwith.com/v21/api.json",
        params={"KEY": BUILTWITH_API_KEY, "LOOKUP": domain}
    )
    bw_resp.raise_for_status()
    bw_data = bw_resp.json()
 
    # Parse technologies
    results = bw_data.get("Results", [])
    techs = []
    if results:
        paths = results[0].get("Result", {}).get("Paths", [])
        if paths:
            techs = paths[0].get("Technologies", [])
 
    if not techs:
        print(f"  {name} ({domain}) — no technologies found")
        skipped += 1
        time.sleep(2)
        continue
 
    # Categorize
    categorized = {cat: [] for cat in CATEGORY_MAP}
    for tech in techs:
        tag = (tech.get("Tag") or "").lower()
        cats = [c.lower() for c in (tech.get("Categories") or [])]
        for category, keywords in CATEGORY_MAP.items():
            if any(kw in tag for kw in keywords) or any(kw in c for kw in keywords for c in cats):
                categorized[category].append(tech["Name"])
                break
 
    # Update HubSpot
    properties = {
        "tech_stack_crm": ", ".join(categorized["crm"]) or "None detected",
        "tech_stack_marketing": ", ".join(categorized["marketing"]) or "None detected",
        "tech_stack_analytics": ", ".join(categorized["analytics"]) or "None detected",
        "tech_stack_all": ", ".join(t["Name"] for t in techs),
        "tech_enrichment_date": datetime.now().strftime("%Y-%m-%d"),
    }
 
    requests.patch(
        f"https://api.hubapi.com/crm/v3/objects/companies/{company['id']}",
        headers=HS_HEADERS,
        json={"properties": properties}
    ).raise_for_status()
 
    enriched += 1
    print(f"  {name} ({domain}) — {len(techs)} technologies")
    print(f"    CRM: {properties['tech_stack_crm']}")
    print(f"    Marketing: {properties['tech_stack_marketing']}")
    print(f"    Analytics: {properties['tech_stack_analytics']}")
 
    time.sleep(2)  # BuiltWith rate limit
 
print(f"\nDone. Enriched: {enriched}, Skipped: {skipped}")

# Via Claude Code
/tech-enrich
 
# Or directly
python .claude/skills/tech-enrich/scripts/tech_enrich.py

# .github/workflows/tech-enrichment.yml
name: Technographic Enrichment
on:
  schedule:
    - cron: '0 3 * * 0'  # Weekly Sunday 3 AM UTC
  workflow_dispatch: {}
jobs:
  enrich:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: '3.12'
      - run: pip install requests
      - run: python .claude/skills/tech-enrich/scripts/tech_enrich.py
        env:
          HUBSPOT_TOKEN: ${{ secrets.HUBSPOT_TOKEN }}
          BUILTWITH_API_KEY: ${{ secrets.BUILTWITH_API_KEY }}