Marketing Attribution☆

Brokers, ads, referrals, events and your website all touch a deal before it funds, and every tool claims the credit. This skill sorts out which channels actually drive funded loans — choosing an attribution model, reconciling conflicting reports, and adding a simple "how did you hear about us?" question that often beats the software.

What it does

• Explains first-touch, last-touch and multi-touch models in plain terms
• Reconciles conflicting numbers from ad platforms, analytics and your CRM
• Sets up self-reported attribution on your application or intake form
• Shows how to connect a funded loan back to the campaign that started it
• Writes a one-page attribution readout with confidence levels

When to use it

• Deciding where to put next year's marketing budget
• Ad platforms report more leads than your pipeline shows
• Long deal cycles make it unclear what started a relationship
• Justifying a broker-relations or event budget

What to have ready

• Your marketing channels and roughly what each costs
• Reports from the tools you use — ads, analytics, CRM
• How a lead becomes a funded loan in your shop, and how long it takes
• Funded-loan counts or volume by month, if available

How to use it

1. Download it with the button above. You'll sign in with a work email — that's how the creator knows who is using their skill.
2. Copy the install prompt from the "Run it in Claude" box, and paste it into Claude along with the file. Claude installs the skill, fills in your firm's details where the file has [BRACKETED] placeholders, and runs a quick test with you.
3. Then just ask in plain English. Claude picks the skill up on its own when a request matches it. Anything it still needs, it asks you for — it won't invent a number.

"Our ads show [NUMBER] leads last quarter but our CRM shows [NUMBER] funded loans from all sources — help us figure out which channels are actually producing [LOAN PROGRAM] deals."

What you get back

An attribution readout: what each source says, which to trust, where the gaps are, and a recommendation for where to spend.

Good to know

• Output quality tracks input quality. A missing figure is flagged as missing — it is never estimated to fill a gap.
• Every draft is a starting point for your own review, not a finished decision.
• Runs anywhere Claude does: the Claude app, Claude Desktop, or Claude Code.
• Keep borrower personal and financial data out of ad and analytics tools, and check with counsel before using the visitor de-anonymization tools the author mentions — they raise privacy-law questions. Deal cycles in private lending are short compared with the author's B2B examples; adjust lookback windows to your own cycle.

Source & credit

Imported from Corey Haines's open-source marketingskills library (MIT). Author: Corey Haines — https://github.com/coreyhaines31/marketingskills. LenderSkills folded the author's reference files into the single installable file, replaced sample email addresses with neutral placeholders so the package passes automated screening, and appended a legal disclaimer; the author's content is otherwise unmodified. Full credit to the author. Corey Haines did not submit this listing and does not endorse it — the original is free at the link above.

Legal disclaimer

This skill drafts; it does not decide. Its output is not legal, tax, accounting, appraisal, or investment advice, and using it creates no attorney-client, fiduciary, or advisory relationship. Nothing it produces is a commitment to lend or an offer to sell a security. Verify every number, date, citation, and conclusion against the source documents, and have a qualified professional licensed in the relevant jurisdiction review the work before you rely on it or send it to a borrower, investor, counterparty, or regulator. Laws, rates, and market data change. The final work product is yours.