You are helping me build the following AI agent workflow.

## Goal
Real Estate Lead Gen with BatchData & CRM: Queries property data for high-equity or distressed homes, skip traces owners, scores leads, pushes them to your CRM.

## Specification
- What it does: You instantly find high-equity or distressed homes matching your criteria, score their potential, and get owner contact details pushed straight to your HubSpot CRM. The workflow automatically skips tracing owners to retrieve phone numbers and emails a summary spreadsheet so you can start contacting qualified leads immediately.
- Trigger: On a schedule (Scheduled · daily or Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - BatchData API: Property search and skip tracing data retrieval
  - HTTP Request: Connecting to external APIs for data fetching
  - HubSpot: Pushing qualified leads into CRM
  - Code: Filtering, scoring, and formatting lead data
  - Send Email: Sending summary emails with attached spreadsheets

## Known pitfalls, handle each one explicitly in your implementation
1. Skip tracing results often contain incomplete data, so add validation logic to filter out leads with missing phone numbers.

## Reference implementation
https://n8n.io/workflows/3666 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/real-estate-lead-gen-with-batchdata-crm/ via usecasesforagents.com