Skip to content

ahacker-1/cre-agent-skills / claude-code-plugins/cre-document-ingestion

cre-document-ingestion

Verified

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.

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.


Attribution

Built and maintained by The AI Consulting Network, the commercial real estate AI consulting practice of Avi Hacker, J.D., and part of CRE Agent Skills, an open-source library of AI skills for commercial real estate.

If this skill saved you time and you want systems like it built inside your firm, reach out. We would love to work with you.

Copyright 2026 Avi Hacker, J.D. / The AI Consulting Network. Licensed under the Apache License 2.0. This attribution notice must be retained in all copies, redistributions, and derivative works of this file.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall