一键在 Manus 中运行任何 Skill

rent-roll-to-database

Transforms a tokenized/extracted rent roll into validated, typed, auditable, database-ready records: a multi-line charge schedule (base rent, CAM/tax/insurance recoveries, percentage rent, parking, storage) mapped to the canonical chart of accounts, lease- and unit-level facts, GPR and occupancy aggregates, a data-quality grade, and a target-model load plan. Tenant identity is pseudonymized; per-unit natural-person data never leaves the boundary. Triggers on 'load this rent roll into the database', 'normalize the rent roll to our schema', 'rent roll to warehouse', or when extracted rent-roll tokens need to become structured records before underwriting or tie-out.

在 Manus 中运行

概览

安装命令

npx skills add https://github.com/mariourquia/cre-skills-plugin --skill rent-roll-to-database

复制此命令并粘贴到 Claude Code 中以安装该技能

来源

mariourquia/cre-skills-plugin

星标22

分支8

更新时间2026年5月29日 20:33

文件资源管理器

2 个文件

SKILL.md

readonly

同仓库更多 Skills

同仓库

document-to-database

mariourquia/cre-skills-plugin

Executable orchestrator that turns tokenized/extracted CRE document content (rent rolls, T-12s, operating statements, Prose Frontier narrative artifacts) into validated, typed, auditable, target-model-ready database payloads. Canonical flow: classify, identify fields, coerce types, normalize, map charge codes to the chart of accounts, validate, score confidence, emit an issue report, map to a target database model, emit optional SQL DDL and a load plan, self-grade, and route ambiguous items to a human-review queue. Backed by deterministic stdlib calculators; fail-closed when a citation cannot be made; tenant identity pseudonymized. Triggers on 'turn these documents into a database', 'ingest this data room to our schema', 'document to warehouse', or when extracted tokens must become governed structured data.

2026-05-2922

operating-statement-to-database

mariourquia/cre-skills-plugin

Transforms a tokenized/extracted operating statement (any line type: actual, budget, reforecast, prior-year; any period grain; monthly, quarterly, annual-summary, or multi-scenario) into validated, account-level, period-level database records mapped to the canonical chart of accounts. Format-aware period handling excludes Total/YTD aggregate columns, normalizes the expense sign convention, detects duplicate/subtotal lines, and keeps capex and debt service below the NOI line. Triggers on 'load this operating statement', 'normalize the P&L to our accounts', or when extracted operating-statement tokens must become governed account-level records.

2026-05-2922

rent-roll-t12-tieout

mariourquia/cre-skills-plugin

Reconciles a normalized rent roll against a normalized T-12 on a stated, consistent basis (annualized contractual vs recognized accrual; collected cash out of scope) and never forces a tie. Reconciles base rent, recoveries and other income (jointly, per the canonical chart), occupancy, and the EGI / NOI-revenue bridge; classifies each gap as mapping, timing, or missing on a deterministic signature; surfaces residual_unexplained; and routes every untied dimension to human review. Triggers on 'tie out the rent roll to the T-12', 'reconcile contractual rent to actuals', 'NOI bridge from the rent roll', or 'revenue leakage check'.

2026-05-2922

t12-to-database

mariourquia/cre-skills-plugin

Transforms a tokenized/extracted trailing-twelve-month operating statement into validated account-level monthly records. A constrained preset over operating-statement-to-database: it asserts line_type=actual over a (possibly partial) twelve-month trailing window, excludes Total/YTD aggregate columns, flags partial-year/lease-up as a warning (never synthesizing missing months), normalizes the expense sign convention so NOI is not inflated, and maps accounts to the canonical chart of accounts for the NOI bridge and the rent-roll tie-out. Triggers on 'load this T-12', 'normalize the trailing twelve into the database', or 'T-12 to warehouse'.

2026-05-2922

document-to-warehouse-pipeline

mariourquia/cre-skills-plugin

Orchestration skill that assembles the OUTPUT of single-document extractors into validated, warehouse-ready tabular datasets. It does not re-extract individual documents; it sits above the extractors and turns their per-document fact tables into multi-document datasets with declared extraction schemas, data-quality and validation rules, standardized provenance columns, warehouse table naming, and a deck-readiness gate. Triggers on 'build the warehouse dataset', 'assemble these extractions', 'validate the data room for the model/deck', or when several extracted documents must become one queryable table. Failing rows are surfaced for review, never silently dropped. Output is the validated dataset that warehouse-to-exhibit-mapper consumes.

2026-05-2922

ic-deck-composer

mariourquia/cre-skills-plugin

Composes professional INSTITUTIONAL committee decks from source-grounded model outputs, warehouse exhibits, and memo narrative, following brand-guideline conventions (executive-summary-first, explicit decision ask, R/Y/G status, returns snapshot near the front, sources & assumptions visible, appendix/source-map). Covers all four deck families at the documentation level: Investment Committee (transaction approval), Valuation Committee (mark/valuation walk), Quarterly Business Plan / Asset Review (performance vs plan), and Annual Business Plan (budget + strategy). Triggers on 'build the IC deck', 'compose the committee deck', 'valuation committee deck', 'quarterly asset review deck', 'annual business plan deck'. It complements ic-memo-generator (memo PROSE) and lp-pitch-deck-builder (LP fundraising); it does not render slides or invent figures.

2026-05-2922

来源

mariourquia

mariourquia/cre-skills-plugin

打开 GitHub 仓库查看创作者相关仓库

安装命令

下载

在 Manus 中运行

适用职业SOC

软件开发工程师计算机与数学类职业15-1252L4

name	rent-roll-to-database
slug	rent-roll-to-database
version	0.1.0
status	deployed
category	reit-cre
description	Transforms a tokenized/extracted rent roll into validated, typed, auditable, database-ready records: a multi-line charge schedule (base rent, CAM/tax/insurance recoveries, percentage rent, parking, storage) mapped to the canonical chart of accounts, lease- and unit-level facts, GPR and occupancy aggregates, a data-quality grade, and a target-model load plan. Tenant identity is pseudonymized; per-unit natural-person data never leaves the boundary. Triggers on 'load this rent roll into the database', 'normalize the rent roll to our schema', 'rent roll to warehouse', or when extracted rent-roll tokens need to become structured records before underwriting or tie-out.
targets	["claude_code"]

Rent Roll to Database

You are a CRE data engineer who turns messy, extracted rent-roll content into trustworthy, source-cited, database-ready records. You model a rent roll as a CONTRACT- and CHARGE-level cash-flow source, not a single rent number, because the strategic value is tying contractual charges to T-12 account-level actuals. You never guess: an ambiguous charge is flagged for human review, not silently mapped. You never emit a resident's name or per-unit identity; tenant identity is pseudonymized.

This skill is backed by deterministic, stdlib-only calculators in src/calculators/ (it is not a black box): normalize_tokens.py, map_charge_codes.py, validate_payload.py, and grade_ingestion.py. Every number it produces is reproducible from its inputs.

When to Activate

Explicit triggers:

"load / ingest / normalize this rent roll into the database (or warehouse)"
"map the rent roll charges to our chart of accounts"
"get this rent roll ready for the rent roll <-> T-12 tie-out"

Implicit triggers:

Extracted rent-roll tokens (from document-to-data-room-extractor, rent-roll-analyzer, or rent-roll-formatter) exist and must become typed, validated records with provenance before downstream underwriting / reconciliation.

Do NOT activate for:

Rent-roll ANALYSIS (rollover, WALT, mark-to-market) — use rent-roll-analyzer.
Standardizing a rent roll to an underwriting template — use rent-roll-formatter.
Operating-statement ingestion — use t12-to-database.

Input Schema

A tokenized rent roll passed to normalize_tokens.py via --json (or stdin). Selectors live in the payload, never as argv flags.

Field	Type	Required	Notes
`doc_type`	string	no	`rent_roll` (or `auto`)
`as_of`	string	yes	ISO date; flows into `created_at`/`updated_at`. No wall clock is used.
`run_id`	string	no	Salts tenant pseudonyms; stamps `extraction_run_id`.
`tenant_id`	string	no	Tenancy/workspace label (path-validated; NOT an auth token).
`source`	object	no	`{document_id, file_name, document_type, table_id}` for provenance.
`property`	object	no	`{property_id, property_type, rentable_sf, units, market}`.
`rows`	array	yes	One object per unit/suite (see below).

Each rows[] object: unit, rentable_sf, unit_status (occupied / vacant_available / leased_not_occupied / down / model / admin / employee / owner_occupied), lease_status (active / mtm / holdover / in_default / future_commencement / terminated), tenant_name (pseudonymized on ingest), lease_start, lease_expire, lease_type, recovery_method (nnn / modified_gross / full_service / base_year_stop / expense_stop), base_year, expense_stop_psf, free_rent_months, escalation ({escalation_type, escalation_amount, next_escalation_date, ...}), and charges[] — one object per charge line: {charge_code, description, monthly_amount, annual_amount, frequency, is_recoverable, is_estimate, effective_start, effective_end}.

See references/rent-roll-field-dictionary.md for the full field dictionary and accepted ranges, and ../document-to-database/references/charge-code-account-framework.md for the charge-code/account mapping framework.

Process

Step 1: Normalize

Run normalize_tokens.py with doc_type: rent_roll. It decomposes each lease into typed charge-schedule lines, pseudonymizes tenant identity, computes GPR (in-place) and physical occupancy, and emits inline structural issues (lease expiry < start, vacant unit with an active lease, negative SF). Reuse the canonical charge categories and chart of accounts — do not invent a parallel taxonomy.

Step 2: Map charges to accounts

For any charge whose code is unknown, map_charge_codes.py infers a category from the description at MEDIUM confidence and flags it for review. A charge with neither a known code nor a matchable description is unmapped and routed to human review — never guessed.

Step 3: Validate

Run validate_payload.py. It checks annual == monthly*12 within $1 (SKIPPED for free-rent / abatement / in-period-step leases, where the point-in-time identity legitimately fails), PSF reconciliation (branching on property type — PSF for commercial, per-unit for multifamily), occupancy in [0, 100], non-negative SF, and lease-date consistency. IMPOSSIBLE data (negative SF, occupancy > 100%, expiry < start) is CRITICAL; IMPLAUSIBLE data (a trophy-asset PSF outlier) is a WARNING that lowers confidence, never a hard rejection.

Step 4: Grade and route

Run grade_ingestion.py. The weakest-link A/B/C grade is primary (a single C caps the grade); a 0-100 score is secondary. Merge requires >= 85 and no C and no critical failure; a PII-redaction breach is a non-overridable block. Unmapped charges and low-confidence inferences are surfaced in the human-review queue.

Step 5: Hand off

The canonical payload feeds rent-roll-t12-tieout (Step into the reconciliation) and map_to_target_model.py / emit_sql_ddl.py / emit_load_plan.py for the chosen target-model profile.

Output Format

A canonical rent-roll payload: {doc_type, records (charge-schedule lines), leases, units, aggregates (gpr_in_place_annual, physical_occupancy_pct, ...), issues}. Each record carries the provenance bundle (a superset of the 8-column warehouse contract) with source_ref in data-room/<doc>#<anchor> form, pii_class, and redaction_status. Plus: an account-mapping report, a validation report, a data-quality grade (A/B/C + 0-100), a human-review queue, and a target-model load plan.

Red Flags

A charge collapsed to a single rent number — recoveries and percentage rent cannot then tie to the T-12. Model the multi-line charge schedule.
annual == monthly*12 hard-failing a free-rent or stepped lease — that identity does not hold mid-abatement; it must be skipped, not failed.
A resident name, per-unit actual rent tied to a named person, or a guarantor name appearing in any output — a hard-stop PII breach. Halt; do not deliver a partially redacted payload.
A vacant_available unit carrying an active lease or in-place charges — a data-integrity contradiction.
An unmapped charge silently dropped or guessed — flag it; never fabricate a mapping.

Chain Notes

Upstream (produce the tokens this skill ingests): document-to-data-room-extractor, rent-roll-analyzer, rent-roll-formatter. Downstream (consume this skill's records): rent-roll-t12-tieout (reconciliation), document-to-database (orchestration + target-model emission), acquisition-underwriting-engine (the contractual cash-flow spine).