Run a full Section 508 + WCAG 2.2 Level AA accessibility audit on a federal / .gov / public-sector website or ICT product. Triggers: "Section 508", "508 audit", "WCAG", "VPAT", "ACR".
日本語の概要は準備中です。原文の説明を表示しています。
Extract a structured abstract from a commercial lease PDF — tenant/landlord identification, premises description + RSF/USF, lease term + commencement/expiration, renewal options (count, notice windows, fair-market rent reset), base rent schedule + escalations (fixed %, CPI-linked.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
You convert a lease PDF (and amendments) into a structured abstract. Manual lease abstraction takes 4-12 hours per document depending on complexity; AI-assisted reduces that to 20-40 minutes of human review on top of a generated draft. The standardization matters as much as the speed — every abstracted lease should fit the same schema so a portfolio can be queried.
Recovery:
PDF preprocessing:
pytesseract or AWS Textract (better for table extraction).Persist lease.text.json with section anchors so the abstract can cite source page+section per extracted field.
VALIDATION: Page count > 0, no all-white pages, text extraction confidence per section ≥ 80%.
Extract into this schema (camelCase JSON):
{
"parties": {"tenant": "...", "landlord": "...", "guarantor": "...", "broker": "..."},
"premises": {"address": "...", "suite": "...", "rsf": 12500, "usf": 11700, "load_factor": 0.068},
"term": {
"commencement_date": "2024-04-01",
"expiration_date": "2034-03-31",
"term_months": 120,
"rent_commencement_date": "2024-06-01",
"free_rent_months": 2
},
"rent_schedule": [
{"period": "Year 1", "start": "2024-04-01", "end": "2025-03-31", "monthly_rent_psf": 4.50, "monthly_rent_total": 56250.00, "annual_rent_total": 675000},
...
],
"escalations": {"type": "fixed_pct", "pct": 0.03, "annual_review_date": "anniversary"},
"options": [
{"type": "renewal", "count": 2, "term_months": 60, "notice_window_months": 12, "rent_basis": "FMR", "rent_floor_pct": null}
],
"additional_rent": {
"expense_structure": "modified_gross",
"base_year": 2024,
"expense_stop_psf": null,
"tenant_share_pct": 0.085,
"cap": {"type": "cumulative_5pct_year_over_year", "applies_to": "controllable_only"},
"gross_up_provision": true,
"audit_rights": {"window_months": 12, "self_help": false}
},
"ti_allowance": {"amount_psf": 75.00, "total": 937500, "unused_treatment": "rent_credit"},
"security_deposit": {"type": "letter_of_credit", "amount": 250000, "burn_down": [{"month": 36, "to": 125000}, {"month": 60, "to": 0}]},
"use_restriction": "general office and ancillary uses; no medical, retail, or industrial",
"co_tenancy": null,
"exclusivity": null,
"assignment_sublet": {"consent_standard": "not_unreasonably_withheld", "permitted_transfers": ["affiliates", "merger_consolidation"]},
"termination_rights": {"tenant_kick_out_year": 7, "notice_months": 12, "termination_fee": "9 months base rent + unamortized TI/commissions"},
"expansion_rights": {"type": "ROFO", "size_sf": null, "notice": "60 days"},
"holdover": {"rate_pct_of_holdover": 1.50, "consent_required": false},
"insurance": {"tenant_liability_minimum": 3000000, "additional_insureds": ["landlord", "property_manager"]},
"default": {"monetary_cure_days": 5, "non_monetary_cure_days": 30, "late_fee_pct": 0.05, "interest_rate": "prime + 4%"},
"estoppel_sndaa": {"estoppel_required": true, "snda_attached": true},
"amendments_incorporated": ["Amendment 1 (2024-09-15)", "Amendment 2 (2025-03-01)"]
}
Every field has a source sub-field with {page, section, confidence}.
VALIDATION: Schema fields present (null OK if absent in lease — don't fabricate). Rent schedule sum reconciles to total committed rent over term.
Some lease clauses are inherently ambiguous; flag for human review:
Flag each as {field, ambiguity, suggested_interpretation, reviewer_action}.
VALIDATION: At least 1 flag per lease (if zero, the abstraction is too confident and worth a second pass).
Emit a calendar file (critical_dates.ics + critical_dates.csv) with reminders:
VALIDATION: Calendar imports into Google/Outlook/iCal without errors.
Final deliverable directory:
lease-{tenant-slug}-{address-slug}/
├── README.md # what each file is and where it goes
├── abstract.json # full schema (Phase 2)
├── abstract.csv # flat row for portfolio rollup
├── abstract.md # human-readable summary
├── critical_dates.ics
├── critical_dates.csv
├── flags.md # ambiguities (Phase 3)
├── source_lease.pdf # original (link, not copy)
└── audit_trail.json # extraction confidence per field
The Markdown summary is a one-pager: parties, premises, term, rent, escalations, options, key flags. Designed for handoff to a broker / attorney / portfolio manager.
VALIDATION: All files render. CSV imports into Excel without column drift.
Score 1–5:
Common gap: forgetting to incorporate amendments. The "original" lease's rent schedule is often superseded by an amendment.
Append to ~/.claude/skills/lease-abstraction/LEARNINGS.md:
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Run a full Section 508 + WCAG 2.2 Level AA accessibility audit on a federal / .gov / public-sector website or ICT product. Triggers: "Section 508", "508 audit", "WCAG", "VPAT", "ACR".
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes actuarial modeling systems for loss reserving accuracy, premium pricing methodology, mortality/morbidity tables, stochastic modeling, and capital adequacy per SOA and Solvency II standards..
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes advertising yield across programmatic and direct-sold inventory including CPM/CPC/CPA performance, header bidding efficiency, fill rate optimization, inventory monetization strategies, and compliance with IAB standards and OpenRTB protocols..
日本語の概要は準備中です。原文の説明を表示しています。
Create and manage Architecture Decision Records using the Michael Nygard format. Triggers: you need to document architecture decisions, record technical choices, explain why a technology was chosen.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes affordable housing management software for unit allocation algorithms, waitlist management, income verification workflows, Fair Housing compliance, LIHTC and Section 8 program tracking, inspection scheduling, and tenant reporting..
日本語の概要は準備中です。原文の説明を表示しています。
Rewrites existing landing pages, blog posts, and documentation so AI search engines (Google AI Overviews, ChatGPT, Perplexity, Claude, Gemini) cite them. Triggers: an existing page underperforms in AI answers despite ranking well in classic SERPs.
日本語の概要は準備中です。原文の説明を表示しています。