skills/business-narrative-builder/SKILL.md
Constructs a structured narrative linking a company's qualitative business story to quantitative valuation drivers (revenue growth, target margin, reinvestment efficiency, cost of capital, failure risk). Classifies the company within a 6-stage corporate life cycle and sizes the total addressable market. Use when starting a company analysis, building a valuation narrative, assessing competitive position, sizing TAM, or when user mentions business narrative, story to numbers, life cycle stage, or company analysis.
npx skillsauth add lyndonkl/claude business-narrative-builderInstall 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: Tesla, circa 2018
Narrative: "Tesla will become the mass-market electric vehicle company, leveraging its brand and technology lead to capture a meaningful share of the global auto market as it transitions from internal combustion to electric."
Life Cycle Stage: Stage 2 -- Young Growth
TAM Sizing:
Value Drivers Derived from Narrative:
| Driver | Value | Rationale | |--------|-------|-----------| | Revenue CAGR (next 10 years) | ~25% | From $21B to ~$150B, bounded by TAM | | Target operating margin | 10% | Auto industry top quartile; premium brand with manufacturing scale | | Sales-to-capital ratio | 2.5x | Capital-intensive but improving; factory efficiency gains | | Cost of capital (WACC) | ~8.5% | Young growth firm, high beta (1.3), moderate debt | | Failure probability | 10% | Cash burn concerns, but improving production; distress value ~$50B (brand + factories) |
Alternative narrative: "Tesla remains a niche luxury EV maker with 2-3% of the global auto market, premium margins (12-15%) but limited scale." This narrative produces a lower revenue path (~$50B) but higher margins, yielding a different but defensible valuation.
Copy this checklist and track progress:
Business Narrative Builder Progress:
- [ ] Step 1: Gather company context
- [ ] Step 2: Classify life cycle stage
- [ ] Step 3: Size total addressable market
- [ ] Step 4: Develop business narrative
- [ ] Step 5: Convert narrative to value drivers
- [ ] Step 6: Validate narrative plausibility
Step 1: Gather company context
Collect: industry, current revenues, operating income, invested capital, products/services, competitive landscape, geographic breakdown, company age/stage. See resources/template.md for the context questionnaire.
Step 2: Classify life cycle stage
Place the company in one of 6 stages (Start-up, Young Growth, High Growth, Mature Growth, Mature Stable, Decline). Each stage has distinct characteristics for revenue growth, earnings, funding, and competitive dynamics. See resources/methodology.md for the full stage definitions and classification criteria.
Step 3: Size total addressable market
Estimate TAM using top-down (total market filtered to addressable segment) and bottom-up (unit count times price). Distinguish between TAM (total), SAM (serviceable), and SOM (obtainable). See resources/template.md for the sizing template.
Step 4: Develop business narrative
Write a narrative describing how the business evolves over time. The narrative should answer: What market does the company operate in? How big can it get? What are its competitive advantages? How will it make money? See resources/methodology.md for the 5-step narrative process.
Step 5: Convert narrative to value drivers
Translate the narrative into the five quantitative drivers: (1) revenue growth rate and path, (2) target operating margin, (3) reinvestment efficiency (sales-to-capital), (4) risk profile (cost of capital), and (5) failure probability. Each number should trace back to a specific element of the story. See resources/template.md for the driver mapping table.
Step 6: Validate narrative plausibility
Test whether the narrative is possible (could it happen?), plausible (is it reasonable given evidence?), and probable (is it the most likely outcome?). Develop at least one alternative narrative. Validate using resources/evaluators/rubric_business_narrative_builder.json. Minimum standard: average score of 3.5 or above.
Pattern 1: Young Growth Company
Pattern 2: Mature Growth Company
Pattern 3: Mature Stable Company
Pattern 4: Decline or Turnaround Company
Every narrative should be testable. Frame the narrative so it can be classified as possible (could happen), plausible (reasonable given evidence), or probable (likely outcome). Untestable narratives produce arbitrary numbers.
Revenue growth path should be bounded by TAM. The company cannot grow larger than its addressable market. If a 10-year revenue projection implies market share above 30-40% of a competitive market, revisit the assumptions.
Target operating margin should be benchmarked against industry quartiles. Use mature companies in the same sector as the reference point. A narrative claiming margins 2x the industry median requires a compelling competitive advantage explanation.
Stable growth rate should not exceed the risk-free rate or nominal GDP growth. No company can grow faster than the economy indefinitely. The terminal growth rate in any narrative should converge to 2-4% (nominal).
Failure probability should be stated for young and distressed firms. For companies in Start-up, Young Growth, or Decline stages, explicitly estimate the probability that the firm does not survive as a going concern. Base this on cash burn rate, available capital, and industry failure rates.
Alternative narratives should be acknowledged. A single narrative creates false precision. Develop at least one alternative story (bull/bear, different strategic path) and note how it changes the value drivers. This discipline reduces confirmation bias.
Key formulas:
Expected FCFF = Revenue x Operating Margin x (1 - Tax Rate) - Reinvestment
Revenue Growth (CAGR) = (Target Revenue / Current Revenue)^(1/n) - 1
Sales-to-Capital Ratio = Revenue / Invested Capital
(measures reinvestment efficiency: higher = less capital needed per dollar of revenue)
Reinvestment = Change in Revenue / Sales-to-Capital Ratio
Value of Firm = Sum of [FCFF_t / (1 + WACC)^t] + Terminal Value / (1 + WACC)^n
(preview: detailed DCF mechanics are in intrinsic-valuation-dcf)
Life cycle stages (summary):
| Stage | Revenue Growth | Earnings | Key Question | |-------|---------------|----------|--------------| | 1. Start-up | Minimal | Deep negative | Does the idea have potential? | | 2. Young Growth | Very high (>30%) | Negative/thin | Is there a viable business model? | | 3. High Growth | High (15-30%) | Turning positive | Will it generate profits at scale? | | 4. Mature Growth | Moderate (5-15%) | Growing | Can the business scale further? | | 5. Mature Stable | Low (0-5%) | High and stable | Can the business be defended? | | 6. Decline | Negative | Declining | Will management face reality? |
Resources:
Inputs required:
Outputs produced:
business-narrative.md: Narrative document linking story to numbers, life cycle classification, TAM estimate, value driver table, alternative narrativestesting
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.