skills/intrinsic-valuation-dcf/SKILL.md
Performs discounted cash flow valuation using the appropriate model variant (DDM, FCFE, or FCFF) with configurable growth stages. Produces year-by-year cash flow projections, terminal value, equity bridge (subtract debt, add cash, subtract option value), per-share intrinsic value, and sensitivity analysis. Use when valuing a company intrinsically, building a DCF model, estimating fair value, or when user mentions DCF, discounted cash flow, intrinsic value, terminal value, or free cash flow valuation.
npx skillsauth add lyndonkl/claude intrinsic-valuation-dcfInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Scenario: Two-stage FCFF model for a mature growth company
Inputs:
Step-by-step:
Base year after-tax operating income: $500M x (1 - 0.25) = $375M
Base year FCFF: $375M - ($200M - $150M) - $20M = $305M
Year-by-year projections (high-growth, 12% growth, 50% reinvestment):
| Year | After-tax EBIT | Reinvestment | FCFF | PV Factor (9%) | PV of FCFF | |------|---------------|-------------|---------|----------------|------------| | 1 | $420.0M | $210.0M | $210.0M | 0.9174 | $192.7M | | 2 | $470.4M | $235.2M | $235.2M | 0.8417 | $198.0M | | 3 | $526.8M | $263.4M | $263.4M | 0.7722 | $203.4M | | 4 | $590.1M | $295.0M | $295.0M | 0.7084 | $208.9M | | 5 | $660.9M | $330.4M | $330.4M | 0.6499 | $214.8M |
Terminal value (end of year 5):
Firm value = $1,017.8M + $5,631M = $6,649M
Equity bridge:
Sensitivity grid (per-share value):
| WACC \ Growth | 2.0% | 2.5% | 3.0% | 3.5% | 4.0% | |---------------|-------|-------|-------|-------|-------| | 7.5% | $62 | $68 | $76 | $86 | $99 | | 8.0% | $53 | $57 | $62 | $69 | $78 | | 8.5% | $45 | $48 | $52 | $57 | $63 | | 9.0% | $39 | $41 | $44 | $48 | $52 | | 9.5% | $34 | $36 | $38 | $41 | $44 |
Copy this checklist and track your progress:
DCF Valuation Progress:
- [ ] Step 1: Select DCF model variant
- [ ] Step 2: Establish base year cash flows
- [ ] Step 3: Estimate growth rate and high-growth period length
- [ ] Step 4: Project year-by-year cash flows
- [ ] Step 5: Compute terminal value
- [ ] Step 6: Discount, bridge to equity, compute per-share value
- [ ] Step 7: Build sensitivity analysis
Step 1: Select DCF model variant
Choose the model that matches the company and context. See resources/methodology.md for the full decision tree.
Quick selection guide:
Step 2: Establish base year cash flows
Start from cleaned financials (ideally from financial-statement-analyzer output). See resources/template.md for the base year input template.
For FCFF:
For FCFE:
For DDM:
Step 3: Estimate growth rate and high-growth period length
See resources/methodology.md for growth estimation methods.
Three approaches to estimating growth:
High-growth period length depends on competitive advantage magnitude and sustainability (typically 5-10 years).
Step 4: Project year-by-year cash flows
Build the projection table for each year of the high-growth period. See resources/template.md for the projection template.
For each year, compute:
Step 5: Compute terminal value
See resources/methodology.md for terminal value approaches and constraints.
Growing perpetuity (preferred):
Exit multiple cross-check (secondary):
Step 6: Discount, bridge to equity, compute per-share value
See resources/template.md for the equity bridge template.
Step 7: Build sensitivity analysis
See resources/template.md for the sensitivity grid template.
At minimum, vary:
Additional sensitivity dimensions to consider:
Validate using resources/evaluators/rubric_intrinsic_valuation_dcf.json. Minimum standard: Average score of 3.5 or higher.
Pattern 1: FCFF Two-Stage (Most Common)
Pattern 2: FCFE Two-Stage
Pattern 3: Dividend Discount Model (DDM)
Pattern 4: Three-Stage Model
Discounting consistency: Match cash flows to discount rates. FCFF at WACC, FCFE at cost of equity, dividends at cost of equity. Mixing them produces meaningless numbers.
Stable growth rate ceiling: The stable growth rate should not exceed the risk-free rate (for real cash flows) or nominal GDP growth (for nominal cash flows). A company cannot grow faster than the economy in perpetuity.
Terminal value proportion: Terminal value typically represents 50-80% of total value for growth firms. Flag if it exceeds 90% -- this may indicate that the high-growth assumptions are too conservative or the growth period too short.
Reinvestment-growth consistency: In the stable period, reinvestment rate should equal g / ROC. If stable growth is 3% and ROC is 10%, reinvestment rate should be 30%. Disconnect between growth and reinvestment implies value creation from thin air.
Equity bridge completeness: When using FCFF, bridge from firm value to equity by subtracting the market value of debt that was included in the cost of capital, adding cash and non-operating assets, and subtracting employee option value and minority interests.
Diluted share count: Use the diluted share count (treasury stock method for in-the-money options) rather than basic shares outstanding. For companies with large option grants, the difference is material.
Cost of capital convergence: In the stable period, beta should converge toward 1.0, debt ratio toward industry average, and WACC toward the weighted average of the market. A company cannot maintain an extremely high or low cost of capital in perpetuity.
Sensitivity analysis breadth: Vary at least the growth rate and discount rate. The interaction between these two drivers accounts for most of the valuation range. Report the value as a range, not a point estimate.
Common pitfalls:
Key formulas:
FCFF = After-tax EBIT - (CapEx - Depreciation) - Change in Non-cash WC
= After-tax EBIT x (1 - Reinvestment Rate)
FCFE = Net Income - (CapEx - Depreciation) - Change in WC + Net Debt Issued
= Net Income x (1 - Equity Reinvestment Rate)
DDM = Dividends per Share (growing at g, discounted at ke)
Terminal Value (perpetuity) = CF(n+1) / (r - g_stable)
Growth (fundamental):
g_operating_income = Reinvestment Rate x Return on Capital
g_net_income = Retention Ratio x Return on Equity
Reinvestment Rate = (CapEx - Depreciation + Change in WC) / After-tax EBIT
Equity Bridge:
Equity Value = Firm Value - Debt + Cash - Options - Minority Interests
Per Share = Equity Value / Diluted Shares
Model selection quick guide:
| Situation | Model | Discount Rate | Result | |-----------|-------|---------------|--------| | Most companies, changing capital structure | FCFF | WACC | Firm value (bridge to equity) | | Stable capital structure, predictable debt | FCFE | Cost of equity | Equity value | | Mature dividend payers | DDM | Cost of equity | Equity value per share | | Financial services | FCFE or DDM | Cost of equity | Equity value | | Long growth runway, transition needed | Three-stage | WACC or ke | Depends on variant |
Key resources:
Inputs required:
Outputs produced:
dcf-valuation.md: Complete DCF model with year-by-year projections, terminal value, equity bridge, per-share value, sensitivity grid, value decompositiontesting
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.