/pricing-strategist

name: pricing-strategist
description: "Use when choosing or revisiting pricing: seat, usage, value-based, freemium or hybrid, Van Westendorp willingness-to-pay analysis, or Good/Better/Best tiers. Runs pricing_model_picker.py, wtp_analyzer.py and packaging_designer.py and returns a range, not one number."
license: MIT
metadata:
  version: 2.8.0
  author: claude-code-skills
  tags: [commercial, pricing, packaging, wtp, van-westendorp, value-based-pricing, saas-pricing]
  compatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]

pricing-strategist

Purpose

Help Commercial, Product Marketing, and CMO functions answer three questions at the pricing-design moment:

1. **Which pricing model fits this product + customer + market?** (subscription seat-based, usage-based, value-based, freemium, hybrid) 2. **What does the customer actually pay before it feels too expensive?** (Van Westendorp PSM on WTP survey responses) 3. **How should we package this into tiers?** (Good / Better / Best — with anti-pattern detection)

The skill recommends **a model and a range**. The human picks the number, owns the trade-offs, and runs the GTM.

When to use

• Launching a new SaaS / API / AI tool and choosing the first pricing model
• Revisiting pricing after 18+ months of GTM data (model shift, not just price increase)
• Designing or redesigning tier packaging (Good/Better/Best, Bronze/Silver/Gold)
• You have Van Westendorp survey data and want the optimal price range
• A board / exec is asking "what should we charge?" and you need the structured answer
• You suspect your packaging has anti-patterns (decoy tier, feature dump, no upgrade trigger)

**Do not use for:**

• Per-deal discount approval → `deal-desk`
• Strategic CMO positioning, brand, category creation → `c-level-advisor/cmo-advisor`
• Whole-company revenue strategy → `c-level-advisor/cro-advisor`
• Technical-sale enablement → `business-growth/sales-engineer`

Workflow

Step 1 — Assess customer context

Fill `assets/pricing_brief_template.md` (≈ 20 min). Capture: industry, deal size avg, customer count, value drivers, adoption curve, consumption pattern (seat / usage / value / hybrid), competitor models.

Step 2 — Pick the pricing model

Run `scripts/pricing_model_picker.py --input brief.json --profile saas --output markdown`. Output ranks 5 models by fit-score 0-100 with trade-offs. Decision logic is deterministic: low usage variance + high seat-attach → subscription wins; power-law usage + variable customer value → usage-based wins.

Step 3 — Validate WTP with Van Westendorp PSM

If you have survey data (≥ 4 questions per respondent: too cheap / bargain / getting expensive / too expensive), run `scripts/wtp_analyzer.py --input survey.json --output markdown`. Output: 4 intersection points (OPP, IDP, PMC, PME) and the Range of Acceptable Prices.

PSM gives a **range**, not the price. See `references/van_westendorp_methodology.md` for common misinterpretations.

Step 4 — Design packaging

Run `scripts/packaging_designer.py --input features.json --profile saas --output markdown`. Output: 3-tier Good/Better/Best assignment with anti-pattern flags (decoy tier, feature dump, no upgrade trigger, Bronze loss leader, Enterprise no-anchor).

Step 5 — Decide

Take model + range + packaging into the pricing committee. Skill does not commit the number — you do.

Scripts

• `scripts/pricing_model_picker.py` — 5-model fit scorer (subscription / usage / value / freemium / hybrid)
• `scripts/wtp_analyzer.py` — Van Westendorp PSM implementation
• `scripts/packaging_designer.py` — Good/Better/Best tier designer with anti-pattern detection

All scripts: stdlib only. `--help` and `--sample` work on all three.

Quick example

# Emits a scored 5-model pricing-fit recommendation (subscription / usage / value / freemium / hybrid) for the built-in example
cd commercial/skills/pricing-strategist && python3 scripts/pricing_model_picker.py --sample

References

• `references/saas_pricing_canon.md` — Skok, Tunguz, Campbell, Ramanujam, BVP, Shevlin, Stanford GSB
• `references/van_westendorp_methodology.md` — original 1976 paper, NMS refinement, Conjoint.ly, Sawtooth, ESOMAR, Lipovetsky, Decision Analyst
• `references/packaging_anti_patterns.md` — ProfitWell, OpenView, BVP vertical SaaS, Ramanujam, Poyar, SaaS Capital

Assumptions

• Pricing decisions are joint: Commercial owns the model + tier shape, Product owns the features-per-tier, Finance owns the discount envelope, Legal owns the contract.
• Van Westendorp PSM is a **directional** tool. N ≥ 30 minimum, N ≥ 100 preferred. Below 30, the script emits a sample-size warning.
• "Value-based pricing" requires a measurable customer value driver (revenue lift, cost saved, time recovered). If you can't measure it, don't pick value-based.
• Industry profiles tune defaults — they don't override your data.
• This is a decision-support skill, not a price oracle. Output is a model + range, never the number.

Anti-patterns

• **Recommending a specific number.** This skill emits a model and a range. Final price is a human commercial decision involving deal-desk policy, competitive intel, and strategic intent that this skill cannot know.
• **Using PSM with N < 30.** Statistical noise dominates. The script warns; respect the warning.
• **Treating PSM as "the price."** PSM gives a Range of Acceptable Prices (RAP) and an Optimal Price Point (OPP). Test the range in market, don't anchor on a single intersection.
• **Picking value-based pricing without a measurable value metric.** Without instrumentation to show customer ROI, value-based collapses into "whatever they'll pay" — which is just bad usage-based pricing.
• **Designing tiers before picking a model.** Tier structure depends on the model. Run pricing_model_picker first.
• **Packaging "feature dumps" into the Best tier.** If Best has 3x the features for 2x the price, customers buy Better and never