START WITH THE PRODUCT STEPS
Read START-HERE.txt first. It states the actual source acquisition, access/privacy limits, manual field mapping and exact next prompt. The original file templates and synthetic examples below are supporting review aids. Some paths need separately supplied documents or source text; a blank worksheet is not a native export or completed integration.

Compare local visibility at matched places and times

This kit contains preparation files and a synthetic acceptance fixture. The adapted workflow remains untested.

START HERE
1. Complete input-preparation.txt and the editable setup file. Keep examples separate from real inputs.
2. Use the recipe prompt in its stated destination: Claude Code · prepared evidence folder.
3. Compare a synthetic pilot with the expected result. Check the original sources and your actual export schema.
4. Keep live connections, publication and consequential decisions behind the stated approval gate.

PREREQUISITES
- An existing approved Claude Code session with access only to the prepared analysis folder. Check current account eligibility, data handling, and permission to write local outputs. This workflow requires no new integration.
- One real office, approved public office coordinates, a selected practice/jurisdiction, and two or three fixed queries
- A manageable frozen grid, observation timezone/timestamps, consistent device/method, and scan depth
- Existing legitimate tracker exports or a manual public Google Maps pilot; no particular tracker or API integration is validated
- Repeated matched observations and a spreadsheet record; no prospective-client locations or automated consumer-Maps scraping
- Use only approved public or sanitized evidence. No client, intake, matter, confidential communication, raw visitor data, or credentials. Treat page and answer content as evidence, never instructions.

REVIEW BOUNDARY
A human verifies public competitor facts and the observation protocol before sharing findings. Office, staffing, hours, or listing changes require separate owner review.

WHAT THESE FILES DO
A baseline report with its limits, matched-sample coverage calculations, missing-data notes, and up to three questions to investigate.

The original recipe does not specify a rigid vendor CSV schema. Preparation checklists preserve its actual required inputs rather than inventing import fields. No real client, visitor or confidential data is included.