Document Classifier
Sort an unlabeled pile of deal documents, extract the key data, and flag what is missing.
★ 105 on GitHub0 downloads on LenderSkills
Install it in one line — paste a single command into Claude, ChatGPT or Cursor and it writes the skill into your project.
Free, and about thirty seconds: a work email and a six-digit code.
Downloading shares your name, firm, role, and email with Avi Hacker, J.D.. That introduction is what keeps every skill here free.
What this skill does
Makes sense of an incoming document dump before anyone starts underwriting it.
What it does
- Identifies what type each document is
- Extracts the key data points from each
- Organizes them into a usable structure
- Surfaces missing documents and conflicts between them
When to use it
Use this skill at the start of a new deal when you have a collection of documents (rent rolls, financials, offering memos, PSAs, inspection reports, lease materials, etc. ) and need to understand what you have, what each document contains, and what is still missing.
What to have ready
- One or more deal documents in any of these formats: PDF, Excel/CSV, Word, images (JPG/PNG)
- The documents can include any combination of: rent roll, T-12 financial statement, offering memorandum, pro forma, PSA/purchase contract, survey/site plan…
- If you know what document types you have, describe them — if not, describe what you received and this skill will classify them
- Optionally, tell the skill what property address or deal name these documents relate to
How to use it
- 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.
- 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. - 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.
"Use the Document Classifier skill — I've got one or more deal documents in any of these formats."
What you get back
A structured report covering deal name, processed at, documents provided, extracted data, completeness, conflicts, and missing documents. You get it as readable analysis plus the underlying data, so it can feed straight into a memo or another skill.
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.
Source & credit
Imported from the open-source cre-agent-skills library by Avi Hacker, J.D. (github.com/ahacker-1/cre-agent-skills), Apache-2.0 license. The author's content is unmodified apart from a legal disclaimer appended at the end of the package. Full credit to the author.
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.
Inside this skill
The actual file you get. Members can read it in full before saving it.
Document Classifier
Identify, classify, and organize incoming CRE deal documents - determining what type each document is, extracting key data points from each, and surfacing any missing or conflicting information.
When to Use This Skill
Use this skill at the start of a new deal when you have a collection of documents (rent rolls, financials, offering memos, PSAs, inspection reports, lease materials, etc.) and need to understand what you have, what each document contains, and what is still missing. It is the first step before performing underwriting, due diligence, or financial modeling across multifamily, industrial, and other CRE workflows - getting your documents organized and validated.
What You'll Need to Provide
- One or more deal documents in any of these formats: PDF, Excel/CSV, Word, images (JPG/PNG)
- The documents can include any combination of: rent roll, T-12 financial statement, offering memorandum, pro forma, PSA/purchase contract, survey/site plan, inspection/PCA report, environmental report, title commitment, or lease abstracts
- If you know what document types you have, describe them — if not, describe what you received and this skill will classify them
- Optionally, tell the skill what property address or deal name these documents relate to
Mission
Scan incoming documents, identify document types, extract relevant CRE deal data, validate completeness, and generate a structured summary of what data has been captured and what gaps remain - ready for use in underwriting and due diligence.
Strategy
Step 1: Inventory All Documents
List every document provided. For each document, record:
- Filename or description
- File type (PDF, Excel, Word, image)
- Approximate length or size
Step 2: Classify Each Document
For each document, determine its type using filename patterns and content indicators:
Reading the full skill counts as a download. The contributor receives your name, company, and email.
Ratings & reviews
No written reviews yet. If you run this on a live file, say how it went. The next lender reading this page is deciding whether to trust it.
Examination record
Run it in Claude
- Copy the install command above
- Paste it into Claude, ChatGPT or Cursor
- It writes the skill in, fills in your firm’s details, and test-runs it with you
Prefer the file? The prompt above is for a package you already downloaded.
Details
More from Avi Hacker, J.D.
Imported from their public repository with attribution. Their other skills, and where to find the original, are on their contributor page.