dcf-model
DCF valuation: free cash flow projections, WACC, terminal value, sensitivity analysis
npx skills add ginlix-ai/LangAlpha --skill dcf-model --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
This skill creates institutional-quality DCF models for equity valuation, producing a detailed Excel model with sensitivity analysis at the bottom of the DCF sheet.
How it works
- It relies on tools for financial data:
get_financial_statements,get_financial_ratios,get_growth_metrics,get_historical_valuation,get_treasury_rates,get_market_risk_premium, andget_company_overviewto gather data (plus user data and web fetches). - It enforces heavy constraints: populate 75 sensitivity cells with full DCF recalculation formulas, write formulas via openpyxl, add cell comments for every blue input, and verify formulas after creation.
- It builds a DCF in a saved Python script (e.g.,
work/<task_name>/build_dcf.py) rather than inline execution, with iterative debugging and re-running via file edits. - It follows a stepwise process: data retrieval and validation, historical analysis, revenue projections, operating expenses, FCF calculation, WACC research, discounting, terminal value, equity bridge, and finally sensitivity tables.
- It uses a three-scenario (Bear/Base/Bull) framework organized in separate blocks, with a consolidation column controlled by a case selector (1=Bear, 2=Base, 3=Bull) to pull the correct scenario values for projection years.
- It requires a mid-year convention for discounting, a terminal value via perpetuity growth (with restrictions), and standard PV computations for FCF and terminal value.
When to use it
- Use when performing equity valuation via DCF following investment banking standards. Triggered when building a formal, Excel-based DCF model with sensitivity analyses and three scenario blocks.
What it can touch
- Access to data sources via:
get_financial_statements,get_financial_ratios,get_growth_metrics,get_historical_valuation,get_treasury_rates,get_market_risk_premium,get_company_overview. - Interacts with a local Excel file
model.xlsxfor recalculation (viapython .agents/skills/xlsx/scripts/recalc.py model.xlsx 30). - Uses openpyxl to write formulas and cell comments, and saves a Python-based model builder script (e.g.,
work/<task_name>/build_dcf.py).
Caveats
- The model adheres to exact formatting and structural constraints: 75-sensitivity-cell coverage, formula recalculation, and specific scenario-block organization with consolidation column, as described in the steps. No outcomes are promised beyond producing the model and ensuring it can recalc; errors must be fixed until status is success.
- Terminal value and WACC inputs have specific constraints (e.g., Terminal Growth must be less than WACC). The approach uses a perpetuity growth method as the preferred terminal value method.
- The implementation relies on multiple data sources that may vary over time; accuracy depends on data retrieval steps and validation checks.
# DCF Model Builder ## Overview This skill creates institutional-quality DCF models for equity valuation following investment banking standards. Each analysis produces a detailed Excel model (with sensitivity analysis included at the bottom of the DCF sheet). ## Tools - **fundamentals MCP**: `get_financial_statements`, `get_financial_ratios`, `get_growth_metrics`, `get_historical_valuation` - **macro MCP**: `get_treasury_rates`, `get_market_risk_premium` - **`get_company_overview` tool**: analyst consensus, growth estimates, company profile - User-provided data and web search/fetch as supplements ## Critical Constraints - Read These First These constraints apply throughout all DCF model building. Review before starting: **Sensitivity Tables:** - Populate ALL 75 cells (3 tables × 25 cells) with full DCF recalculation formulas - Use openpyxl loops to write formulas programmatically - NO placeholder text, NO linear approximations, NO manual steps required - Each cell must recalculate full DCF for that assumption combination **Cell Comments:** - Add cell comments AS each hardcoded value is created - Format: "Source: [System/Document], [Date], [Reference], [URL if applicable]" - Every b
- Overview
- Tools
- Critical Constraints - Read These First
- DCF Process Workflow
- Step 1: Data Retrieval and Validation
- Step 2: Historical Analysis (3-5 years)
- Step 3: Build Revenue Projections
- Step 4: Operating Expense Modeling
- Step 5: Free Cash Flow Calculation
- Step 6: Cost of Capital (WACC) Research
- Step 7: Discount Rate Application (5-10 Year Forecast)
- Step 8: Terminal Value Calculation
- Step 9: Enterprise to Equity Value Bridge
- Step 10: Sensitivity Analysis
python .agents/skills/xlsx/scripts/recalc.py [path_to_excel_file] [timeout_seconds]
python .agents/skills/xlsx/scripts/recalc.py $WORK_DIR/work/{task}/AAPL_DCF_Model.xlsx 30What does the dcf-model skill do?
DCF valuation: free cash flow projections, WACC, terminal value, sensitivity analysis
How do I install it?
Run `npx skills add ginlix-ai/LangAlpha --skill dcf-model --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ginlix-ai/LangAlpha, a repository with 1,604 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.