Financial Modeling Pack

We built the Financial Modeling Pack so you don't have to wrestle with subjective assumptions, broken Excel macros, and the constant fear that your WACC inputs are drifting. Financial modeling isn't just about plugging numbers into a spreadsheet; it's a governance problem. When you treat valuation as a black box, you invite downstream incidents. We designed this skill to bring the rigor of an audit-ready workflow to your local machine, using Python, strict schemas, and reproducible scripts.

The Subjectivity Trap in Engineering Valuations

Most financial models fail because they treat valuation as a one-off calculation rather than a structured pipeline. Engineers often copy-paste WACC formulas from old decks, skip stress-testing terminal values, or ignore the balance sheet identity checks that catch reconciliation errors early. The SEC emphasizes that valuation governance requires strict adherence to industry guidelines and regulations ^[1]. Without a formalized workflow, you're relying on tribal knowledge and fragile cell references.

When you skip validation, you risk material misstatements. SEC correspondence highlights that significant assumptions—like projected earnings, WACC estimates, and tax rate inputs—are frequent points of scrutiny during reviews ^[5]. If your model doesn't explicitly enforce constraints on these variables, you're leaving the door open for errors that only surface when you present to investors or auditors.

What Broken Models Cost Beyond the Spreadsheet

The cost of a flawed valuation model isn't just rework; it's lost credibility and delayed decisions. A single error in the terminal value calculation can skew enterprise value by millions, especially in low-growth environments where the terminal value dominates the DCF. The preparation of economic valuations is a complex process that involves subjective judgment and is not susceptible to partial analysis ^[4]. When you ignore this complexity, you expose your team to rework loops that kill velocity.

Consider the downstream impact: if your Free Cash Flow (FCF) projections don't reconcile with working capital and capex schedules, your investor memos will be wrong. You'll spend days debugging discrepancies instead of shipping. In regulated environments, this can trigger formal inquiries. The SEC's guidance on sound practices underscores that valuation governance impacts reporting integrity ^[1]. A broken model doesn't just waste engineering hours; it erodes stakeholder trust and delays capital allocation decisions.

A Worked Example: The Terminal Value Trap

Imagine a team preparing an indicative valuation for a tech acquisition. They applied the Income Approach, specifically the Discounted Cash Flow method ^[3]. Their model projected five years of revenue and capex, but they used a perpetuity growth model for the terminal value without cross-checking against an exit multiple. The result was a valuation that looked robust on the surface but collapsed under stress testing.

The SEC's Hebron Tech valuation report illustrates how indicative valuations rely on the DCF method, requiring careful application of parameters ^[3]. In our hypothetical scenario, the team missed a critical nuance: the terminal value is a surrogate for the present value of all future cash flows beyond the forecast period ^[8]. By failing to validate the growth rate against the cost of capital and market conditions, they introduced a bias that inflated the enterprise value. A rigorous workflow would have flagged this during the validation phase, using tools that check for growth rate sanity and balance sheet identity.

The After-State: Validated, Reproducible, Audit-Ready

Once you install this skill, your workflow shifts from fragile spreadsheets to a programmable, validated pipeline. Here's what changes:

• Inputs are locked down: templates/dcf_input_schema.json enforces strict types and ranges for cash flow projections, WACC parameters, and growth rates. No more typos in the risk-free rate or equity risk premium.
• Validation runs automatically: scripts/validate_model.py checks balance sheet identity, FCF reconciliation, and growth rate sanity using numpy.gradient. It exits non-zero on failure, so you never ship a broken model.
• Valuation is reproducible: scripts/dcf_engine.py implements DCF valuation, WACC calculation, and scenario analysis using pandas and numpy. It leverages rolling windows, geomspace for scenario generation, and crosstab for sensitivity tables.
• Memograms are structured: templates/investor_memo_template.md generates investment committee memos with valuation summaries, scenario tables, and risk disclosures, ensuring consistent reporting.
• References are built-in: references/valuation_methods.md provides canonical knowledge on DCF mechanics, WACC derivation, terminal value methods, and stress-testing frameworks. references/pandas_numpy_financial_api.md offers Context7-grounded guidance on functions like rolling.apply, polyder/polyint for curve fitting, and numerical stability checks.
• Config is standardized: config/wacc_assumptions.json centralizes risk-free rate, equity risk premium, market beta, cost of debt, and tax rate inputs, so you don't hunt for assumptions across files.
• Worked examples clarify expectations: examples/inputs/company_facts.yaml provides a hypothetical public company dataset with historical revenue, capex, working capital, and debt schedules. examples/outputs/dcf_results.json shows the expected output structure, including base/bull/bear valuations and sensitivity tables.
• Execution is wrapped: scripts/run_analysis.sh sets up the virtual environment, runs the DCF engine, and triggers the validator with proper exit code propagation, making it easy to integrate into CI/CD.
• Orchestration is explicit: skill.md guides the agent through the end-to-end workflow, referencing all templates, scripts, references, examples, and config paths.

If you're also modeling real estate cash flows, you can check the Real Estate Investment Pack for complementary ROI calculations and risk assessment strategies.

What's in the Financial Modeling Pack

• skill.md — Orchestrator skill definition that explicitly references templates/, scripts/, references/, examples/, and config/ paths to guide the agent through the end-to-end financial modeling workflow
• templates/dcf_input_schema.json — Production-grade JSON Schema for validating DCF inputs, cash flow projections, and WACC parameters, enforcing strict types and ranges
• templates/investor_memo_template.md — Structured template for generating investment committee memos, including valuation summary, scenario tables, and risk disclosures
• scripts/dcf_engine.py — Executable Python script implementing DCF valuation, WACC calculation, and scenario analysis using pandas/numpy APIs (rolling windows, geomspace, crosstab, is_quarter_end)
• scripts/validate_model.py — Validator script that checks balance sheet identity, FCF reconciliation, and growth rate sanity using numpy.gradient; exits non-zero on failure
• scripts/run_analysis.sh — Bash wrapper that sets up the virtual environment, runs the DCF engine against inputs, and triggers the validator with proper exit code propagation
• references/valuation_methods.md — Canonical knowledge on DCF mechanics, WACC derivation, terminal value methods (perpetuity growth vs exit multiple), and stress-testing frameworks
• references/pandas_numpy_financial_api.md — Curated reference of Context7-grounded pandas/numpy functions for financial time-series: rolling.apply, crosstab normalization, polyder/polyint for curve fitting, and numerical stability checks
• examples/inputs/company_facts.yaml — Worked example input dataset for a hypothetical public company with historical revenue, capex, working capital, and debt schedules
• examples/outputs/dcf_results.json — Expected output structure and sample results from the DCF engine, including base/bull/bear valuations and sensitivity tables
• config/wacc_assumptions.json — Standardized configuration for risk-free rate, equity risk premium, market beta, cost of debt, and tax rate inputs

Install and Ship

Stop guessing valuations. Start shipping DCF models that pass audit. Upgrade to Pro to install the Financial Modeling Pack and bring engineering rigor to your financial workflows.