agentsclimarketplace

Cre document ingestion

Skill XAKLESK/cre-agent-skills/claude-code-plugins/cre-document-ingestion

Automate CRE analysis with AI skills for multifamily, industrial, and brokerage acquisitions, underwriting, due diligence, and closing

Install
npx -y skills add XAKLESK/cre-agent-skills --skill cre-document-ingestion

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

CRE Document Ingestion suite — 4 specialist skills for classifying and extracting structured data from deal documents including rent rolls, T-12 financials, and offering memoranda.

SKILL.md

3.1 KB, as published. Nobody here has run it

CRE Document Ingestion Suite

You have access to 4 specialist document processing skills for commercial real estate deal packages.

Available Skills

SkillFileUse When
Document Classifierskills/document-classifier.mdUser provides one or more deal documents and needs them identified by type (rent roll, T-12, offering memo, lease, survey, etc.)
Rent Roll Parserskills/rent-roll-parser.mdUser provides a rent roll file and needs structured data extracted — unit numbers, tenants, lease dates, rents, deposits, status
Financials Parserskills/financials-parser.mdUser provides a T-12 or operating statement and needs structured extraction — income lines, expense categories, monthly trends
Offering Memo Parserskills/offering-memo-parser.mdUser provides an offering memorandum and needs key data extracted — property details, financial projections, market data, investment highlights

How to Use

  1. If the user provides documents without specifying what they are, start with the Document Classifier
  2. Once document types are identified, load the appropriate parser skill
  3. Follow the Strategy steps in the loaded skill exactly
  4. Produce structured output in the format specified by the skill
  5. Run Quality Checks before delivering results

Recommended workflow for a full deal package:

  1. Read skills/document-classifier.md → classify all documents
  2. For each rent roll: Read skills/rent-roll-parser.md → extract
  3. For each T-12/financial: Read skills/financials-parser.md → extract
  4. For each offering memo: Read skills/offering-memo-parser.md → extract

If the user says "$ARGUMENTS", use that to determine which skill to load.

Quick Reference

Document Classifier — Identifies: rent rolls, T-12/T-3 operating statements, offering memoranda, leases, title commitments, surveys, Phase I ESAs, appraisals, insurance certificates, tax returns, entity documents. Outputs: document type, confidence level, extractable data fields.

Rent Roll Parser — Extracts: unit number, unit type, square footage, tenant name, lease start/end, monthly rent, security deposit, unit status, move-in date, concessions. Validates: unit count completeness, rent reasonableness, date consistency.

Financials Parser — Extracts: income line items (rental income, vacancy loss, other income), expense categories (taxes, insurance, utilities, R&M, management, payroll, turnover, admin), monthly and annual totals. Calculates: per-unit metrics, expense ratios, year-over-year trends.

Offering Memo Parser — Extracts: property name/address, unit count/mix, year built, lot size, asking price, in-place NOI, pro forma NOI, cap rate, occupancy, market highlights, seller's financial projections, comparable sales, rent comps.

Gives 0 of the 12 instructions most docs writing skills give

Counted across 1,637 of the 3,044 authors here whose files we hold, read 2026-08-06

  • announce the skill at startin 54 of 1637, across 21 files
  • convert legacy doc files before editingin 45 of 1637, across 7 files
  • predict questions readers might askin 42 of 1637, across 3 files
  • Generate clarifying questions for initial contextin 42 of 1637, across 3 files
  • Create document scaffold with placeholder textin 42 of 1637, across 3 files
  • Brainstorm content options for each sectionin 42 of 1637, across 3 files
  • Test document with fresh context-less instancein 42 of 1637, across 3 files
  • ask interview questions one at a timein 42 of 1637, across 26 files
  • include exact file paths in every taskin 42 of 1637, across 15 files
  • Apply surgical edits during refinementin 41 of 1637, across 2 files
  • Offer structured workflow or freeformin 40 of 1637, across 1 file
  • Ask for document meta-contextin 40 of 1637, across 1 file

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.