Finance & models
AuraScore 81/100

Commercial Credit Debt Service Coverage Modeling Specification

Develop a financial modeling specification for multi-scenario commercial credit risk and debt service stress testing.

Apply this prompt when engineering credit risk assessment models for institutional or commercial lending. It creates a standardized financial model design specification with dynamic covenant calculations and sensitivity grids.

Template

Role: Senior Commercial Credit Risk Officer and Financial Modeling Lead specializing in structured corporate debt underwriting.

Context

  • Target borrower sector: {{target_borrower_sector}}
  • Credit facility hierarchy: {{credit_facility_hierarchy}}
  • Macroeconomic stress vectors: {{macro_stress_vectors}}
  • Financial covenant thresholds: {{covenant_threshold_matrix}}
  • Primary cash flow drivers: {{cash_flow_driver_logic}}
  • Collateral valuation and haircut schedules: {{collateral_haircut_rules}}

Task

Generate a comprehensive financial model design specification for a multi-scenario commercial credit underwriting workbook that models Debt Service Coverage Ratios (DSCR), dynamic leverage profiles, and collateral adequacy under baseline and stressed conditions.

Method

  1. Define the fundamental chart of accounts and dynamic Three-Statement financial statement integration tailored to {{target_borrower_sector}}.
  2. Detail the exact algebraic formulas for EBITDA adjustments, Free Cash Flow conversion, and Available Cash Flow for Debt Service (CFADS) based on {{cash_flow_driver_logic}}.
  3. Establish the debt waterfall calculation engine mapping amortization, interest payments, cash sweeps, and payment priority across {{credit_facility_hierarchy}}.
  4. Design the covenant monitoring module calculating rolling 12-month DSCR, Fixed Charge Coverage (FCCR), and Senior Debt-to-EBITDA against {{covenant_threshold_matrix}}.
  5. Construct the stress-testing matrix incorporating multi-variable shocks from {{macro_stress_vectors}} across revenue, input margin compression, and benchmark interest rate hikes.
  6. Formulate the borrowing base and collateral liquidation valuation logic applying markdown percentages from {{collateral_haircut_rules}}.
  7. Detail the model validation framework, including circularity breakers, dynamic error checks, and auditable assumption change logs.

Constraints

  • MUST define explicit formulas for every financial metric using standard financial modeling naming syntax (e.g., Excel/VBA/Python naming conventions).
  • MUST NOT permit unhedged floating interest rate assumptions without explicit baseline forward curve modeling.
  • Include both point-in-time snapshot formulas and trailing-twelve-month (TTM) dynamic roll logic.
  • Assumptions must account for seasonality and working capital swings typical in commercial lending.

Output format

Provide the specification structured under these mandatory sections:

  1. Model Architecture & Structural Overview
  2. Cash Flow Driver Mechanics & Adjusted EBITDA Definitions
  3. Debt Amortization Waterfall & Seniority Schedule
  4. Dynamic Covenant Compliance Engine
  5. Multi-Vector Sensitivity & Macro Stress Testing Matrix
  6. Collateral Assessment Engine & Model Auditing Controls Total length should be between 1,200 and 1,800 words.

Self-review

  1. Verify that all facility tiers in the hierarchy are sequenced accurately within the debt waterfall.
  2. Ensure the stress test methodology simulates simultaneous margin compression and interest rate escalation.
  3. Confirm that all covenant calculations explicitly handle potential negative denominator or zero-cash edge cases.
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering10/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness5/5 · Strong

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

business-strategy
business-finance
financial-services
credit-risk
financial-modeling
commercial-lending