skills/cost-of-capital-estimator/SKILL.md
Computes cost of equity (CAPM), cost of debt (synthetic rating), and weighted average cost of capital (WACC) for any company in any currency. Handles emerging market risk premiums, bottom-up beta estimation, and multi-country operations. Use when estimating discount rates, computing WACC, determining hurdle rates, analyzing cost of equity or debt, or when user mentions cost of capital, WACC, beta, equity risk premium, country risk premium, or discount rate.
npx skillsauth add lyndonkl/claude cost-of-capital-estimatorInstall 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.
Company: Ambev (Brazilian beverage company)
Step 1 -- Riskfree rate (BRL analysis)
US 10-year Treasury yield: 4.0%. Brazil government bond: 11.0%. Brazil sovereign default spread (Baa2 rating): 2.5%.
Option A -- Subtract default spread: 11.0% - 2.5% = 8.5% (riskfree rate in BRL, captures inflation differential).
Option B -- Build from US rate + inflation differential: (1.04) x (1.06)/(1.02) - 1 = 8.1% (using expected inflation: Brazil 6%, US 2%).
Use 8.5% for this analysis (Option A, simpler and directly observable).
Step 2 -- Equity risk premium buildup
Mature market ERP (implied, S&P 500): 5.0%.
Country risk premiums (CRP):
Operation-weighted CRP = 0.60 x 3.75% + 0.30 x 3.0% + 0.10 x 0% = 3.15%.
Total ERP = 5.0% + 3.15% = 8.15%.
Step 3 -- Bottom-up beta
Comparable beverage firms (global, n=20): Median unlevered beta = 0.80.
Relever at Ambev's capital structure: Levered Beta = 0.80 x (1 + (1 - 0.34) x 0.25) = 0.80 x 1.165 = 0.93.
Step 4 -- Cost of equity
Cost of Equity = 8.5% + 0.93 x 8.15% = 8.5% + 7.58% = 16.08%.
Step 5 -- Cost of debt (synthetic rating)
EBIT: R$20B, Interest expense: R$2.5B. Interest coverage = 8.0x.
Lookup: Coverage of 8.0x maps to A rating for large firms, default spread = 1.00%.
Pre-tax cost of debt = 8.5% + 1.00% = 9.50%.
After-tax cost of debt = 9.50% x (1 - 0.34) = 6.27%.
Step 6 -- WACC
Capital structure weights (market values): E/(D+E) = 80%, D/(D+E) = 20%.
WACC = 16.08% x 0.80 + 6.27% x 0.20 = 12.86% + 1.25% = 14.12%.
Interpretation: This is a BRL-denominated WACC. Use it to discount BRL-denominated cash flows. For USD-denominated analysis, rebuild using USD riskfree rate and adjust the ERP accordingly.
Copy this checklist and track your progress:
Cost of Capital Estimation Progress:
- [ ] Step 1: Determine riskfree rate for analysis currency
- [ ] Step 2: Estimate equity risk premium (mature market + country risk)
- [ ] Step 3: Estimate beta (regression or bottom-up)
- [ ] Step 4: Compute cost of equity
- [ ] Step 5: Compute cost of debt via synthetic rating
- [ ] Step 6: Compute WACC and validate
Step 1: Determine riskfree rate for analysis currency
The riskfree rate anchors the entire computation. It should be denominated in the same currency as projected cash flows.
See resources/methodology.md for the inflation-differential approach and when each method is appropriate.
Step 2: Estimate equity risk premium (mature market + country risk)
Build the ERP in two layers:
See resources/methodology.md for the four-step ERP estimation and resources/methodology.md for the three approaches to corporate country risk exposure.
Step 3: Estimate beta (regression or bottom-up)
Bottom-up beta is preferred over regression beta because it uses a larger sample, reflects the current business mix, and allows you to set the capital structure to the target rather than historical average.
See resources/methodology.md for the complete procedure and the relevering formula.
Step 4: Compute cost of equity
Apply the CAPM formula. For emerging market companies, incorporate the country risk premium into the expected return calculation. See resources/template.md for the calculation worksheet.
Step 5: Compute cost of debt via synthetic rating
Estimate what rating the company would receive based on its interest coverage ratio, then look up the corresponding default spread.
See resources/methodology.md for the complete interest-coverage-to-rating-to-spread lookup table.
Step 6: Compute WACC and validate
Combine cost of equity and after-tax cost of debt using market value weights.
See resources/template.md for the complete worksheet. Validate using resources/evaluators/rubric_cost_of_capital_estimator.json. Minimum standard: Average score of 3.5 or higher.
Pattern 1: US / Developed Market Company
Pattern 2: Emerging Market Company
Pattern 3: Private Company
Pattern 4: Multi-Division Conglomerate
Currency consistency: The riskfree rate, cash flows, and WACC should all be denominated in the same currency. Mixing a USD riskfree rate with BRL cash flows produces meaningless results.
Implied ERP over historical: Use the implied equity risk premium derived from current market levels rather than long-run historical averages. The implied ERP reflects what investors are demanding today; historical averages are backward-looking and vary widely depending on the time period chosen.
Bottom-up beta preferred: Regression betas have high standard errors (often 0.20+), reflect historical business mix, and use historical capital structure. Bottom-up betas from 15-20 comparable firms produce a more stable and forward-looking estimate.
Relevering formula: Levered Beta = Unlevered Beta x (1 + (1 - Tax Rate) x (Debt/Equity)). Use market values for debt and equity, not book values. The tax rate should be the marginal rate.
Synthetic rating from interest coverage: Map current interest coverage (EBIT / Interest Expense) to a credit rating using the appropriate table (large firm vs. small firm). Do not rely on assigned ratings for companies that may not be rated.
Market value weights: WACC uses market value of equity (not book) and market value of debt (approximate with book if trading data unavailable). Book value weights systematically underweight equity for profitable firms.
WACC matches cash flow currency: If cash flows are in BRL, the WACC should be in BRL. If cash flows are in USD, the WACC should be in USD. Converting a WACC across currencies requires adjusting for the inflation differential between the two currencies.
Key formulas:
Cost of Equity (CAPM) = Riskfree Rate + Beta x Equity Risk Premium
For emerging markets:
Cost of Equity = Riskfree Rate + Beta x Mature ERP + lambda x CRP
(Simplified: lambda = 1, so CRP is added directly)
Riskfree Rate (local currency) = Local Govt Bond Yield - Sovereign Default Spread
OR = (1 + US Rf) x (1 + Inflation_local) / (1 + Inflation_US) - 1
Country ERP = Sovereign Default Spread x (Equity Volatility / Bond Volatility)
Typical ratio: 1.5x
Operation-weighted CRP = Sum of (Revenue_i% x CRP_i) for each country i
Levered Beta = Unlevered Beta x (1 + (1 - Tax Rate) x (D/E))
Unlevered Beta = Levered Beta / (1 + (1 - Tax Rate) x (D/E))
Total Beta (private, undiversified) = Market Beta / Correlation with Market
Cost of Debt (pre-tax) = Riskfree Rate + Default Spread (from synthetic rating)
Cost of Debt (after-tax) = Pre-tax Cost of Debt x (1 - Marginal Tax Rate)
WACC = ke x (E / (D+E)) + kd(1-t) x (D / (D+E))
Current estimates (update periodically):
| Parameter | Typical Range | Source | |-----------|--------------|--------| | US 10-year Treasury | 3.5% - 5.0% | Federal Reserve | | Implied ERP (S&P 500) | 4.5% - 6.0% | Damodaran annual update | | Equity/Bond volatility ratio | 1.3x - 1.7x | Use 1.5x as default | | Unlevered beta (typical ranges) | 0.5 - 1.5 | By industry sector |
Key resources:
Inputs required:
Outputs produced:
cost-of-capital.md: Complete WACC computation with riskfree rate derivation, ERP buildup, beta estimation, synthetic rating, cost of equity, cost of debt, and final WACC with sensitivity analysistesting
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.