pricing-test

Este extracto es una copia guardada durante la revisión. La fuente externa contiene la versión completa y actual.

---
name: pricing-test
description: "Test pricing strategies with synthetic data. Use when: simulating willingness to pay, price sensitivity, or optimal price points."
---

# /digital-marketing-pro:pricing-test

## Purpose

Test pricing scenarios against synthetic audience panels grounded in real CRM data. Estimate willingness-to-pay by segment, find optimal price points, acceptable price ranges, and the spread between revenue-maximizing and volume-maximizing prices. This command brings Van Westendorp and Gabor-Granger style pricing analysis to AI-simulated panels — giving directional pricing intelligence without the cost and lead time of formal pricing research. Use it before launching a new product, adjusting existing pricing, introducing tiers, or evaluating competitive price positioning. Every output includes confidence limitations so results are treated as informed estimates requiring real-world validation for high-stakes pricing decisions.

## Input Required

The user must provide (or will be prompted for):

- **Product or service description**: What is being priced — features, value proposition, target use case, and any relevant context about how customers perceive the offering. The more specific the description, the more grounded the synthetic panel's price sensitivity responses will be
- **Price points to test**: 3-8 specific price points to evaluate across the audience panel. Price points should span a meaningful range — from a low-anchor price the user suspects is too cheap to a high-anchor price they suspect is too expensive. Evenly spaced intervals work best for identifying sensitivity curves
- **Audience panel**: An existing panel ID from a previous session, or new segment definitions to build from CRM data. Segments should represent meaningfully different buyer types — budget-conscious vs premium, small vs enterprise, new vs loyal — since pricing sensitivity varies dramatically across segments
- **Current price (for reference)**: The existing price point if the product is already on the market. Used as a reference anchor for measuring price change impact on each segment. For new products, omit or provide the price the user is leaning toward
- **Competitive pricing context (optional)**: Known competitor prices for similar products or services. When provided, the analysis includes competitive positioning assessment — where each test price point falls relative to competitors and how that positioning affects each segment's perceived value

## Process

1. **Load brand context**: Read `~/.claude-marketing/brands/_active-brand.json` for the active slug, then load `~/.claude-marketing/brands/{slug}/profile.json`. Apply brand positioning, perceived brand premium or discount, target market income and spending profiles, and competitive landscape. Also check for guidelines at `~/.claude-marketing/brands/{slug}/guidelines/_manifest.json` — if present, load restrictions. Check for agency SOPs at `~/.claude-marketing/sops/`. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults.
2. **Load audience panel**: Reference the existing panel by its ID (list available panels with `python "${CLAUDE_PLUGIN_ROOT}/scripts/audience-simulator.py" --brand {slug} --action list-panels`), or create a new panel via `python "${CLAUDE_PLUGIN_ROOT}/scripts/audience-simulator.py" --brand {slug} --action create-panel --panel-name {name} --segments '[...]'` with CRM data grounding if new segment definitions were provided. Ensure segments include spending behavior and price sensitivity indicators from CRM purchase history.
3. **Test pricing across segments**: Run `python "${CLAUDE_PLUGIN_ROOT}/scripts/audience-simulator.py" --brand {slug} --action test-pricing --panel-id {id} --price-points '[...]' --product-description "..."` for each price point against each segment. For every segment-price combination, estimate purchase likelihood, perceived value rating, price-quality inference (too cheap s