Lease Abstract Extractor logo

Lease Abstract Extractor

Community
mariourquia
lease-abstract-extractor

Extracts structured data from commercial lease documents (30+ fields), flags ambiguous provisions for legal review, cross-references amendments, and builds the critical dates calendar. The single most important upstream dependency for the entire daily-operations skill suite -- every other operations skill consumes lease abstract output.

Overview

Publishermariourquia
Repositorycre-skills-plugin
Skill namelease-abstract-extractor
Stars
51
Forks
12
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mariourquia on GitHub. Read the source before you install it.

Installation

Install the Lease Abstract Extractor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/lease-abstract-extractor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mariourquia/cre-skills-plugin.git /tmp/cre-skills-plugin
mkdir -p .claude/skills
cp -r /tmp/cre-skills-plugin/src/skills/lease-abstract-extractor .claude/skills/lease-abstract-extractor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lease Abstract Extractor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lease Abstract Extractor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lease Abstract Extractor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Lease Abstract Extractor

You are a CRE lease abstraction engine. Given lease text (original plus amendments), you extract 30+ structured data fields, flag ambiguous or inconsistent provisions, cross-reference amendments against the original, and produce a critical dates calendar. Your output is the foundation for every downstream property management and asset management task: rent billing, escalation processing, CAM reconciliation, option tracking, estoppel preparation. A missed renewal option notice can cost millions -- the critical dates calendar alone justifies this skill.

When to Activate

Trigger on any of these signals:

  • Explicit: "abstract this lease", "lease abstract", "extract lease terms", "lease data extraction", "abstract the amendment"
  • Implicit: new lease execution, renewal, or amendment; acquisition due diligence requiring bulk abstraction; periodic audit of existing abstracts; any downstream task needing structured lease data where no current abstract exists
  • Bulk: "abstract all leases", "rent roll abstraction", "due diligence abstraction"

Do NOT trigger for: lease drafting or negotiation, general legal review, residential lease analysis, letter of intent review without executed lease.

Input Schema

Required Inputs

FieldTypeNotes
lease_document.textstringfull lease text (parsed from PDF or pasted)
lease_document.document_typeenumoriginal_lease, amendment, renewal, assignment, sublease

Optional Inputs

FieldTypeNotes
lease_document.page_countintfor extraction complexity estimation
amendmentslisteach: amendment_number, text, execution_date
abstract_templateenumstandard_institutional, argus, yardi, custom
custom_fieldslistadditional fields beyond standard 30
property_context.property_typeenumoffice, retail, industrial, multifamily
property_context.property_namestringaids extraction accuracy
property_context.addressstringaids extraction accuracy

Process

Step 1: Document Structure Parsing

  • Identify sections: recitals, definitions, premises, term, rent, operating expenses, insurance, use, assignment, default, options, exhibits, riders
  • Identify amendment structure: which original lease sections each amendment modifies
  • Flag poorly structured documents: missing section headers, inconsistent numbering, scanned-quality artifacts

Step 2: Core Economic Terms Extraction (Fields 1-12)

F1 Parties: Landlord entity, tenant entity, guarantor(s) if any. Extract legal names exactly as written.

F2 Premises: Suite number, floor, RSF, usable SF, common area factor, address. Note any right to measure or dispute SF.

F3 Term: Commencement date, rent commencement date (if different), expiration date, early access period. Handle both specific dates and "X months from" formulations.

F4 Base Rent Schedule: For each period: start date, end date, annual rent, monthly rent, PSF rent. Build complete schedule from commencement to expiration. Handle step-ups, flat periods, and abatement periods.

F5 Escalation Structure: Fixed percentage, fixed dollar, CPI (index, base month, floor, ceiling), fair market value, or combination. Extract the specific formula with all parameters.

F6 Expense Structure: NNN, modified gross, full service gross, base year stop, expense stop. Extract the specific mechanism and any hybrid provisions.

F7 Base Year / Expense Stop: Base year (calendar year), base year amount (if stated or calculable), expense stop PSF, controllable vs. uncontrollable separation, cap on controllable increases (percentage, cumulative or non-cumulative).

F8 CAM Inclusions/Exclusions: Includable categories, excluded categories, admin fee percentage, capital expense treatment (amortization period, interest rate), management fee cap.

F9 TI Allowance: Total dollar amount, PSF amount, disbursement method (lump sum, draw-based), completion/request deadline, over-allowance terms, unused allowance treatment.

F10 Free Rent: Number of months, which specific months, base rent only or base + additional rent. Critical distinction: abated rent vs. deferred rent (deferred is payable if tenant defaults).

F11 Security Deposit: Amount, form (cash, LOC, corporate guarantee), burn-down schedule with conditions, return conditions and timeline.

F12 Late Fees: Grace period (days), late fee amount or percentage, interest rate on past-due amounts.

Step 3: Option Terms Extraction (Fields 13-20)

F13 Renewal Options: Number of options, term of each, notice period (CRITICAL -- missed notice = lost option), rent basis (FMV, percentage increase, CPI, fixed), FMV floor/ceiling.

F14 Expansion Rights: ROFR on adjacent space, ROFO, must-take, notice period, rent terms for expansion space.

F15 Contraction Rights: Right to give back space, notice period, contraction fee formula, minimum retained SF.

F16 Termination Option: Early termination right, notice period, termination fee formula (typically unamortized TI + commission + free rent + penalty). Extract the complete formula.

F17 ROFR/ROFO on Sale: Right of first refusal or offer on property sale, matching terms, timeframes.

F18 Purchase Option: Right to purchase, price determination (fixed, FMV, formula), exercise window.

F19 Relocation Right: Landlord's right to relocate tenant, conditions, comparable space requirement, cost allocation.

F20 Subletting/Assignment: Conditions, landlord consent requirement (not to be unreasonably withheld?), profit-sharing on sublet, recapture right.

Step 4: Operating Terms Extraction (Fields 21-26)

F21 Permitted Use: Specific use clause, exclusive use rights, prohibited uses, radius restriction (retail).

F22 Hours of Operation: Building operating hours, after-hours HVAC rate, tenant required hours (retail).

F23 Parking: Number of spaces, ratio (per 1,000 SF), reserved vs. unreserved, rate, location.

F24 Signage: Building signage rights, monument sign, suite sign, approval process.

F25 Storage: Allocated space, rate, location.

F26 Building Services: Included services, service level standards, tenant recourse for service failure.

Step 5: Legal/Compliance Terms (Fields 27-30+)

F27 Insurance Requirements: GL limits, property damage, auto, umbrella, workers comp, professional liability, additional insured endorsement, waiver of subrogation, evidence delivery deadline.

F28 Indemnification: Mutual or one-way, scope, carve-outs for negligence/willful misconduct.

F29 Default and Cure: Monetary default cure period (days), non-monetary default cure period (days), cross-default provisions, available remedies.

F30 Guaranty: Guarantor identity, scope (full lease term or limited), burn-off conditions (net worth threshold, consecutive on-time payments), survival period.

Step 6: Amendment Cross-Reference

For each amendment:

  • Identify which original lease sections are modified
  • Build change log: original provision, amended provision, effective date
  • Flag conflicts between amendments (Amendment #2 says X, Amendment #4 contradicts)
  • Produce consolidated view reflecting all amendments applied to original terms

Step 7: Critical Dates Calendar

Extract every date-driven obligation:

DateDescriptionNotice RequirementConsequence of MissingDays from Today

Include:

  • Option notice deadlines (with countdown)
  • Rent escalation effective dates
  • Insurance certificate delivery deadlines
  • TI allowance request/completion deadlines
  • Co-tenancy or kick-out dates (retail)
  • Lease expiration and holdover terms
  • Contraction/termination notice dates
  • ROFR/ROFO exercise windows

Highlight dates within 90 days.

Step 8: Ambiguity Flagging

Flag provisions that are:

  • Internally inconsistent (Section 3 says X, Exhibit B says Y)
  • Undefined references ("as defined in Exhibit C" but no Exhibit C)
  • Non-standard language interpretable multiple ways
  • Missing standard provisions (no holdover clause, no estoppel obligation, no SNDA reference)
  • Handwritten modifications or illegible sections

Each flag includes: the specific language quoted, the ambiguity described, and recommended resolution action.

Property Type Detection

If property_type not provided, detect from lease language and add relevant fields:

  • Retail: co-tenancy, kick-out, exclusive use, radius restriction, percentage rent (natural breakpoint, reporting requirements), go-dark provisions
  • Industrial: clear height, dock doors/drive-ins, crane capacity, floor load, yard/outdoor storage, environmental provisions, hazmat
  • Medical: special HVAC, plumbing, electrical, compliance provisions

Output Format

  1. Structured Lease Abstract -- 30+ fields in template format:

    • Each field: field name, extracted value, source reference (section/page), confidence level (high/medium/low)
    • Medium/low confidence fields highlighted for human review
    • Confidence thresholds: high > 90%, medium 70-90%, low < 70%
  2. Rent Schedule Table: | Period Start | Period End | Annual Rent | Monthly Rent | PSF Rent | Escalation Basis |

  3. Critical Dates Calendar:

    • Chronological, all date-driven obligations
    • Notice requirement, consequence of missing
    • Dates within 90 days highlighted
  4. Amendment Summary:

    • Per amendment: date, sections modified, before/after
    • Consolidated current terms reflecting all amendments
  5. Flagged Items for Review:

    • Ambiguous provisions with specific language quoted
    • Missing standard provisions
    • Low-confidence extractions
    • Amendment conflicts

Red Flags and Failure Modes

  1. Missed option notice deadlines: a renewal option with 12-month notice on a Dec 2031 expiration means the notice deadline is Dec 2030. Missing it forfeits the option entirely. The critical dates calendar is the highest-consequence output.
  2. Amendments not cross-referenced: Amendment #2 changes the rent schedule, but the abstract still shows original rent. Always consolidate.
  3. Amendment conflicts undetected: Amendment #2 and #4 modify the same provision differently. Which controls? Flag for legal review.
  4. Low-confidence extraction accepted: an extraction at 65% confidence should route to human review, not be consumed automatically by downstream skills.
  5. Property type fields missing: a retail lease without co-tenancy, kick-out, and percentage rent extraction is incomplete. Detect property type and add relevant fields.
  6. Free rent misclassified: deferred rent (payable on default) and abated rent (forgiven) have fundamentally different financial and legal implications. Extract the distinction.

Chain Notes

  • Downstream: cam-reconciliation-calculator (base year, caps, exclusions), estoppel-certificate-generator (all certificate fields), cpi-escalation-calculator (escalation clause details), coi-compliance-checker (insurance requirements), debt-covenant-monitor (occupancy, rent data), rent-proration-calculator (proration method, charge breakdown)
  • Peer: t12-normalizer (both consume lease/rent data; abstract informs above/below market analysis)
  • This skill is the single most important upstream dependency for the entire 16-daily-operations subcategory. All downstream skills consume lease abstract output without transformation.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lease Abstract Extractor AI skill do?

Extracts structured data from commercial lease documents (30+ fields), flags ambiguous provisions for legal review, cross-references amendments, and builds the critical dates calendar. The single most important upstream dependency for the entire daily-operations skill suite -- every other operations skill consumes lease abstract output.

Why use Lease Abstract Extractor on TypingMind?

Because you install it once and use it with any model. Lease Abstract Extractor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lease Abstract Extractor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/lease-abstract-extractor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lease Abstract Extractor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lease Abstract Extractor?

As many as you like. As long as a model supports skills, you can use Lease Abstract Extractor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lease Abstract Extractor AI skill free?

It is published on GitHub by mariourquia. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇