Tam Sam Som CalculatorSAFE

Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: tam-sam-som-calculator
argument-hint: "[product idea] [market constraints]"
description: Calculate TAM, SAM, and SOM with explicit assumptions, methods, and caveats. Use when sizing a market for a product idea, business case, or executive review.
intent: >-
  Guide product managers through calculating Total Addressable Market (TAM), Serviceable Available Market (SAM), and Serviceable Obtainable Market (SOM) for a product idea by asking adaptive, contextually relevant questions. Use this to build defensible market size estimates backed by real-world citations, economic projections, and population data—essential for pitching to investors, securing budget, or validating product-market fit.
type: interactive
theme: market-intelligence
best_for:
  - "Sizing a market for a business case an executive will question"
  - "Making your market assumptions explicit and attackable"
  - "Replacing a top-down guess with a defensible bottom-up estimate"
scenarios:
  - "I need market sizing for a business case our CFO will pick apart"
  - "Our TAM number came from a slide nobody can source — rebuild it properly"
estimated_time: "20-40 min"
---


## Purpose
Guide product managers through calculating Total Addressable Market (TAM), Serviceable Available Market (SAM), and Serviceable Obtainable Market (SOM) for a product idea by asking adaptive, contextually relevant questions. Use this to build defensible market size estimates backed by real-world citations, economic projections, and population data—essential for pitching to investors, securing budget, or validating product-market fit.

This is not a back-of-napkin guess—it's a structured, citation-backed analysis that withstands scrutiny.

## Input

**Works best with:** The product or idea being sized, and any market constraints you already know (geography, vertical, customer type).
**Also useful:** Pricing assumptions, comparable companies, and the audience for the numbers (investors, execs, business case).

Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended `ARGUMENTS:` line — counts as answers already given. Use it and skip whatever it covers; don't re-ask.

**Arriving empty-handed? That works too.** The calculator opens by asking what you're sizing and for whom, then works through method and assumptions.

**Three entry modes** — pick whichever matches where your evidence lives:
1. **Bring your own numbers** — you have population and ARPU figures; jump to the math (the helper script makes this deterministic)
2. **Guided interview** — up to 4 adaptive questions build the inputs with you (the default flow below)
3. **Autonomous research** — the agent builds a bottom-up, citation-backed estimate from government statistics and filings while you review the evidence (see *Mode 3* in Application)

**Example invocation:** `Size the market: AI scheduling assistant for independent dental practices, US only, $99/mo price point.` — or for research mode: `Research-mode market sizing: field-service dispatch software, DACH region; I have no numbers yet.`

## Key Concepts

### TAM/SAM/SOM Framework
The three-tier market sizing model:

**Total Addressable Market (TAM):**
- The total market demand for a product or service
- "If we captured 100% of the market, what's the revenue?"
- Broadest possible market (no constraints)

**Serviceable Available Market (SAM):**
- The segment of TAM your company can realistically target
- Narrowed by geography, firmographics, demographics, or product constraints
- "Who can we actually reach with our product?"

**Serviceable Obtainable Market (SOM):**
- The portion of SAM you can realistically capture
- Accounts for competition, market constraints, go-to-market capacity
- "What can we capture in the next 1-3 years?"

### Why This Works
- **Top-down validation:** TAM → SAM → SOM ensures estimates are grounded in reality
- **Investor-friendly:** Standard framework VCs and execs understand
- **Citation-backed:** Real data sources (Census, Statista, World Bank) add credibility
- **Adaptive:** Questions adjust based on context (B2B vs. B2C, US vs. global, etc.)

### Anti-Patterns (What This Is NOT)
- **Not a single-number guess:** "The market is $10B" without supporting data
- **Not static:** Markets evolve—reassess annually
- **Not a substitute for customer validation:** Market size ≠ product-market fit

### When to Use This
- Pitching to investors or execs (need market size in deck)
- Validating product ideas (is the market big enough?)
- Prioritizing product lines (which has bigger opportunity?)
- Setting growth targets (what's realistic to capture?)

### When NOT to Use This
- For internal tools with captive users (no external market)
- Before defining the problem (market sizing requires clear problem space)
- As the only validation (pair with customer research)

---

### Facilitation Source of Truth

Use [`workshop-facilitation`](../workshop-facilitation/SKILL.md) as the default interaction protocol for this skill.

It defines:
- session heads-up + entry mode (Guided, Context dump, Best guess)
- one-question turns with plain-language prompts
- progress labels (for example, Context Qx/8 and Scoring Qx/5)
- interruption handling and pause/resume behavior
- numbered recommendations at decision points
- quick-select numbered response options for regular questions (include `Other (specify)` when useful)

This file defines the domain-specific assessment content. If there is a conflict, follow this file's domain logic.

## Application

Use `template.md` for the full fill-in structure.

This interactive skill asks **up to 4 adaptive questions**, offering **enumerated context-aware options** at each step. The agent adapts questions based on previous responses.

---

### Step 0: Gather Context (Before Questions)

**Agent suggests:**

Before we begin, it's helpful to have product context. If available, please share:

**For Your Own Product:**
- Website copy (homepage, product pa

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.