skills/valuation-reconciler/SKILL.md
Synthesizes intrinsic (DCF) and relative (multiples) valuation outputs into a final value estimate and investment recommendation. Reconciles divergent valuations, reverse-engineers what the market is pricing in (implied growth, implied ROIC), computes margin of safety, and produces a buy/sell/hold recommendation with catalysts. Use when combining multiple valuation approaches, making investment recommendations, reconciling DCF with multiples, or when user mentions reconcile valuations, investment recommendation, margin of safety, implied growth rate, or what is the market pricing in.
npx skillsauth add lyndonkl/claude valuation-reconcilerInstall 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: NovaBrands Inc. -- US consumer goods company, current price $65/share
Valuation inputs:
Reconciliation table:
| Method | Value/Share | Key Assumptions | Confidence Weight | |--------|------------|-----------------|-------------------| | DCF (FCFF) | $85 | 8% revenue growth, 14% operating margin, 9% WACC | 50% | | PE Regression | $78 | Sector regression R-squared 0.62, predicted PE 22x | 25% | | EV/EBITDA Peers | $90 | Median peer 11x, adjusted for higher growth | 25% |
Weighted estimate: $85 x 0.50 + $78 x 0.25 + $90 x 0.25 = $84.50/share
Implied analysis (what the market prices at $65):
Margin of safety: ($84.50 - $65) / $84.50 = 23%
Catalysts:
Recommendation: Buy at $65, target range $80-$85, 12-month horizon. The 23% margin of safety provides a cushion even if growth reaches only 6% instead of 8%.
Risk factors: Private-label competition eroding brand premium; input cost inflation compressing margins; restructuring execution delays.
Copy this checklist and track your progress:
Valuation Reconciliation Progress:
- [ ] Step 1: Collect all valuation estimates
- [ ] Step 2: Identify sources of divergence
- [ ] Step 3: Reverse-engineer market implied assumptions
- [ ] Step 4: Assess catalysts for gap closure
- [ ] Step 5: Compute margin of safety and formulate recommendation
- [ ] Step 6: Write investment thesis
Step 1: Collect all valuation estimates
Gather intrinsic value (DCF), relative valuation estimates (PE, EV/EBITDA, PBV, EV/Sales), and any special-situation adjustments into a single reconciliation table. For each estimate, record the method, per-share value, key assumptions, and a confidence weight reflecting how appropriate that method is for this company type. See resources/template.md for the reconciliation table format.
Step 2: Identify sources of divergence
Compare the highest and lowest valuations. Trace differences to specific assumptions: growth rate, discount rate, margin, multiple selection, peer universe. If DCF and relative values diverge by more than 20%, document the driver of the gap. See resources/methodology.md for the divergence analysis framework.
Step 3: Reverse-engineer market implied assumptions
Back-solve for the growth rate and ROIC that would make the DCF value equal to the current market price. Compare these implied assumptions against your narrative, historical performance, and industry benchmarks. This reveals what the market is pricing in and where your view differs. See resources/methodology.md for the iterative calculation method.
Step 4: Assess catalysts for gap closure
If a value gap exists (intrinsic value differs from market price), identify specific, time-bound events that could cause the gap to close. Catalysts may include earnings reports, product launches, restructuring milestones, regulatory changes, or management actions. Assign estimated timing, value impact, and probability to each catalyst. See resources/template.md for the catalyst template.
Step 5: Compute margin of safety and formulate recommendation
Calculate margin of safety as (intrinsic value - market price) / intrinsic value. Calibrate the required margin based on company characteristics: higher for volatile, unpredictable, or small-cap firms; lower for stable, predictable businesses. Formulate a buy/sell/hold recommendation with a specific price target and time horizon. See resources/template.md for the recommendation format.
Step 6: Write investment thesis
Synthesize the reconciliation into a one-page investment thesis linking business narrative to valuation to recommendation. Include the key risk factors that could invalidate the thesis. See resources/template.md for the thesis format. Validate using resources/evaluators/rubric_valuation_reconciler.json. Minimum standard: Average score >= 3.5.
Pattern 1: Value Gap (DCF > Price)
Pattern 2: Overvaluation Signal (DCF < Price)
Pattern 3: Fair Value / Convergence
Expect divergence between methods. Different valuation methods should produce different numbers. If DCF, PE regression, and peer median all yield the same value, the analysis likely contains confirmation bias. Investigate whether assumptions were inadvertently aligned.
Weight the method most appropriate for the company type. DCF carries more weight for unique businesses with few comparables. Relative valuation carries more weight for commodity businesses in a well-defined peer group. Neither approach alone is sufficient.
Calibrate margin of safety to uncertainty. A 15% margin of safety may suffice for a stable, predictable utility; a 30-40% margin is appropriate for a volatile, high-growth, or distressed company. The required margin should increase with cash flow volatility, forecast horizon, and complexity.
Validate implied assumptions against plausible ranges. Reverse-engineered growth rates and ROIC should be compared to the company's own history, industry averages, and base rates. If the market implies 25% growth for a decade, check how many companies in the same industry have actually achieved that.
Require specific, time-bound catalysts. "The market will eventually recognize value" is not a catalyst. A catalyst has a what, a when, and an estimated impact: "Q3 earnings release showing restructuring savings of $40M, expected October, could close 30% of the value gap."
State a time horizon for the recommendation. A buy recommendation without a time horizon is incomplete. Specify whether the thesis depends on a 6-month, 12-month, or multi-year holding period, and what changes would trigger a reassessment.
Document risk factors explicitly. Every thesis must include at least two specific risk factors that could invalidate the recommendation. For buy recommendations, state what would cause you to sell. For sell recommendations, state what would cause you to reverse.
Key formulas:
Margin of Safety = (Intrinsic Value - Market Price) / Intrinsic Value
Value-to-Price Ratio = Intrinsic Value / Market Price
Implied Growth Rate = g such that DCF(g) = Market Price
(iterate g in DCF model until output equals current price)
Implied ROIC = ROC such that DCF(ROC) = Market Price
(iterate ROC in DCF model until output equals current price)
EVA Value Decomposition:
Firm Value = Invested Capital + PV of Future EVA
where EVA = (ROIC - WACC) x Invested Capital
Growth premium = Firm Value - Invested Capital
Breakeven Sensitivity:
What change in [growth / WACC / margin] flips buy to hold?
Recommendation decision framework:
| Value-to-Price | Margin of Safety | Catalysts | Recommendation | |----------------|-----------------|-----------|----------------| | > 1.30 | > 25% | Identified, time-bound | Buy | | 1.15 - 1.30 | 15-25% | Identified, time-bound | Buy (moderate conviction) | | 0.85 - 1.15 | < 15% | N/A | Hold / Fair value | | 0.70 - 0.85 | Negative | Risk factors present | Sell / Avoid | | < 0.70 | Deeply negative | Risk factors present | Sell (high conviction) |
Key resources:
Inputs required:
Outputs produced:
valuation-reconciliation.md: Reconciliation table, implied assumptions, divergence analysis, margin of safety, sensitivity matrix, catalyst assessment, buy/sell/hold recommendation with price target and time horizon, investment thesis, risk factorsCross-references to other skills:
intrinsic-valuation-dcf provides the DCF per-share value and sensitivity gridrelative-valuation-multiples provides peer comparison and regression-implied valuesspecial-situations-valuation provides adjusted values for high-growth, distressed, private, or financial services firmsbusiness-narrative-builder provides the qualitative story that anchors the thesistesting
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.