Qualitative Valuation logo

Qualitative Valuation

Community
JoelLewis
qualitative-valuation

Assess business quality, competitive positioning, and sustainability of value creation beyond financial models. Use when the user asks about economic moats, competitive advantages, Porter's Five Forces, management quality, ESG integration, or business model analysis. Also trigger when users mention 'does this company have a moat', 'switching costs', 'network effects', 'brand value', 'management track record', 'capital allocation', 'insider ownership', 'red flags', or ask whether a company's advantage is durable.

Overview

PublisherJoelLewis
Repositoryfinance_skills
Skill namequalitative-valuation
Stars
217
Forks
37
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by JoelLewis on GitHub. Read the source before you install it.

Installation

Install the Qualitative Valuation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/JoelLewis/finance_skills/tree/main/plugins/wealth-management/skills/qualitative-valuation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JoelLewis/finance_skills.git /tmp/finance_skills
mkdir -p .claude/skills
cp -r /tmp/finance_skills/plugins/wealth-management/skills/qualitative-valuation .claude/skills/qualitative-valuation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qualitative Valuation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Qualitative Valuation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Qualitative Valuation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Qualitative Valuation

Core Concepts

Economic Moats (Morningstar Framework)

An economic moat is a structural advantage that protects a company's profits from competition. Five sources:

  1. Network Effects: the product becomes more valuable as more people use it (payment networks, marketplaces)
  2. Switching Costs: customers face significant cost, effort, or risk in moving to a competitor (enterprise software, banking relationships)
  3. Intangible Assets: brands, patents, licenses, or regulatory approvals competitors cannot replicate; brands must confer pricing power to qualify
  4. Cost Advantages: structural cost advantages from process technology, scale, location, or unique resources
  5. Efficient Scale: a market that supports only a few players, where new entry would drive returns below the cost of capital (utilities, pipelines, railroads)

Moat Width

  • Wide moat (20+ years): multiple reinforcing moat sources, each backed by hard evidence
  • Narrow moat (10+ years): at least one evidenced moat source with moderate durability
  • No moat: commodity business with no structural advantage; competes on price

A moat claim is only as strong as its evidence. Do not award moat sources based on narrative — use the rubric below.

Evidence Rubric: What Qualifies a Qualitative Claim

Anchor every claim in observable results, with retention and realized pricing as the strongest evidence:

ClaimQualifying evidenceDisqualifying signs
Pricing powerRealized price increases at or above inflation with stable volumes and retention; gross margin held or expanded through input-cost cyclesPrice increases followed by churn spikes; persistent discounting to hold share
Switching costsGross retention >90% (>95% for enterprise) or net revenue retention >100%; multi-year contracts; implementations measured in quarters; deep data/workflow integrationHigh churn; month-to-month terms; easy data export and low migration cost
Network effectsUnit economics measurably improve with scale (take rates, engagement, liquidity per user); winner-take-most share dynamicsUser growth without any engagement, pricing, or cost benefit
Brand (intangible asset)Sustained price premium over comparable products for yearsAwareness without a premium; growth dependent on promotional spend
Cost advantageMargins persistently above peers, traceable to scale, process, or resource accessOne-off cost cuts; margin gap explained by product mix
Management qualityMulti-year ROIC > WACC; buybacks executed below subsequent intrinsic value; acquisitions that met stated return targetsSerial dilutive M&A; buybacks concentrated at price peaks; recurring guidance misses

Mapping Findings to Valuation Inputs

Translate qualitative conclusions into explicit adjustments to discount rate, fade period, or terminal assumptions in quantitative valuation. These ranges are judgment calibrations, not formulas — document the specific evidence behind each adjustment:

FindingCalibrated adjustment
Wide-moat evidence (2+ reinforcing, retention-backed sources)Discount rate -0.5 to -1.0pp, or terminal multiple +1-2 turns, or extend the above-WACC return fade to 15-20 years
Narrow moat (one evidenced source)Fade above-WACC returns over ~10 years; no discount-rate change
No moatFade returns to WACC by terminal year; terminal growth at or below inflation
Confirmed pricing powerHold or modestly expand forecast margins; resist mean-reverting them prematurely
Governance red flags (see checklist)Discount rate +0.5 to +1.5pp, haircut management guidance, or walk away
Material unmitigated ESG/regulatory exposureDiscount rate +0.5 to +1.5pp, or (often more transparent) probability-weight an impaired-earnings scenario
Key-person or succession riskDiscount rate +0.25 to +0.75pp

If combined adjustments exceed roughly 2pp on the discount rate in either direction, the qualitative overlay is driving the valuation — re-examine the base-case cash flow assumptions instead of stacking adjustments.

Qualitative Red Flags Checklist

Any single flag warrants deeper investigation before relying on a valuation model:

  • Aggressive accounting: revenue recognition changes, newly capitalized expenses, non-GAAP adjustments that always exceed GAAP. Check: trend in the non-GAAP-to-GAAP gap over 3+ years.
  • Related-party transactions: deals with insider-controlled entities that may not be at arm's length. Check: proxy statement and footnote disclosures.
  • Excessive M&A: serial acquisitions that obscure weak organic growth and add integration risk. Check: organic growth disclosed vs reported growth.
  • High management turnover: frequent CFO or auditor changes signal potential problems. Check: 8-K filings for departures and stated reasons.
  • Divergent cash flow and earnings: net income growing while operating cash flow stagnates. Check: accruals (net income minus OCF) as a share of assets over time.

Worked Examples

Example 1: Moat Assessment — Enterprise Software Company

Given:

  • Cloud-based ERP platform with 95% gross retention, 120% net revenue retention
  • Average customer implementation takes 12-18 months
  • Data integration with customer systems creates deep embedding
  • No network effects; moderate brand value; costs in line with peers

Assess: Moat sources and width, using the evidence rubric

Solution:

  1. Switching Costs — STRONG (qualifies): 95% gross retention and 120% net revenue retention clear the rubric thresholds, and 12-18 month implementations with deep data integration explain why. The 120% net retention also evidences realized pricing power: existing customers are paying more each year without offsetting churn.
  2. Network Effects — ABSENT: an ERP system does not become more valuable to one customer because another adopts it.
  3. Intangible Assets — DOES NOT QUALIFY: the brand is recognized but confers no measurable price premium over peers.
  4. Cost Advantages — ABSENT: cost structure in line with competitors.
  5. Efficient Scale — ABSENT: the market supports multiple competitors.

Assessment: Narrow-to-wide moat. One moat source, but with unusually strong retention evidence; durability 15-20+ years barring a technology shift. Valuation-input mapping: extend the above-WACC return fade toward 15-20 years and hold forecast margins, but skip the full wide-moat discount-rate reduction because there is no second reinforcing source.

Example 2: Governance and Regulatory Risk — Discount Rate Calibration

Given: Base cost of equity 9.0%. The company operates in a high-carbon industry with no transition plan; pending carbon-tax legislation could reduce EBIT by 15%. Governance is strong: independent board, aligned compensation, no red flags.

Calibrate: Adjusted cost of equity

Solution:

  • Unmitigated regulatory/environmental exposure: +1.5pp (top of the +0.5 to +1.5pp range — exposure is material, unmitigated, and legislation is pending)
  • Strong governance: -0.25pp partial offset (well-governed firms adapt better)

Adjusted cost of equity = 9.0% + 1.5% - 0.25% = 10.25%

Alternative (often more transparent): keep the 9% discount rate and probability-weight a scenario in which EBIT falls 15% when the carbon tax passes. Both approaches capture the same risk; do not apply both at once.

Common Pitfalls

  • Narrative fallacy: a compelling story is not evidence — require the rubric's observable results before crediting a moat
  • Confirmation bias: seeking information that supports a pre-existing thesis while dismissing contradictory evidence
  • Moat erosion: technology disruption can destroy moats faster than historical patterns suggest (e.g., retail disrupted by e-commerce)
  • Double-counting: adjusting the discount rate and the cash flows for the same risk overstates the impact
  • Overweighting management charisma: a compelling CEO presentation does not equal good capital allocation — check the multi-year ROIC and M&A record
  • Static analysis: moats, competitive positioning, and regulatory risks evolve — reassess periodically

Cross-References

  • quantitative-valuation (wealth-management plugin): quantitative models that qualitative analysis informs and contextualizes
  • financial-statements (wealth-management plugin): ROIC, margins, and cash flow patterns that validate qualitative assessments
  • forward-risk (wealth-management plugin): risk premium adjustments from ESG and business quality factors
  • diversification (wealth-management plugin): qualitative sector/factor analysis informs diversification decisions

Frequently asked questions

What does the Qualitative Valuation AI skill do?

Assess business quality, competitive positioning, and sustainability of value creation beyond financial models. Use when the user asks about economic moats, competitive advantages, Porter's Five Forces, management quality, ESG integration, or business model analysis. Also trigger when users mention 'does this company have a moat', 'switching costs', 'network effects', 'brand value', 'management track record', 'capital allocation', 'insider ownership', 'red flags', or ask whether a company's advantage is durable.

Why use Qualitative Valuation on TypingMind?

Because you install it once and use it with any model. Qualitative Valuation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Qualitative Valuation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JoelLewis/finance_skills/tree/main/plugins/wealth-management/skills/qualitative-valuation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Qualitative Valuation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Qualitative Valuation?

As many as you like. As long as a model supports skills, you can use Qualitative Valuation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Qualitative Valuation AI skill free?

Yes. It is published on GitHub by JoelLewis under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇