commercial-policy

Designs data-backed discount matrices, exception flows, and policy lint reports for commercial governance.

25.3k|3.6k|Updated Oct 19, 2025
One-click install
npx skills add https://github.com/alirezarezvani/claude-skills --skill commercial-policy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: commercial-policy
Source: https://github.com/alirezarezvani/claude-skills/tree/main/commercial/skills/commercial-policy
Command: npx skills add https://github.com/alirezarezvani/claude-skills --skill commercial-policy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Companies lose margin when discounting happens ad hoc: AEs cite past exceptions as precedent, approver tiers drift out of alignment with margin floors, and "strategic value" becomes a catch-all that renders the discount matrix meaningless. This Skill designs the commercial policy itself — the rules of engagement governing discounts off list price — as a versioned, data-backed, linted artifact.

Core Features & Use Cases

  • Discount Matrix Builder: Generates a 4-dimensional matrix (ARR band x term length x payment terms x strategic value tier) with approved discount bands, approver tiers, margin floors, and observed win-rate/NRR backing per cell, across five industry profiles (saas, enterprise-software, api, marketplace, services).
  • Exception Router: Routes out-of-policy discount requests through a named approver chain, attaches severity-scaled compensating commitments (multi-year prepay, named expansion path, reference commitment, MSA tightening), emits machine-readable audit-trail JSON, and flags precedent risk when 3+ similar exceptions land in a quarter.
  • Policy Linter: Runs 10 deterministic lint rules (approver inversion, band inversion, margin-floor violation, cliff edges, undefined strategic tiers, thin data) and returns a ranked BLOCKER/MAJOR/MINOR findings report.
  • Use Case: A new Head of Deal Desk pulls 4 quarters of closed-won/lost deals from the CRM, fills the intake template, runs the builder and linter, and publishes a defensible discount matrix with a quarterly review cadence.

Quick Start

Ask the agent to design a discount matrix from your last four quarters of CRM deal data using the saas profile, then lint the resulting matrix and walk a sample exception through the router.

Frequently Asked Questions about commercial-policy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design a SaaS discount matrix with data backing?

Pull the last 4 quarters of closed-won and closed-lost deals from your CRM into a JSON intake with arr, discount_pct, term_months, payment_terms_days, strategic_value, win_lost, and nrr_12mo per deal. Run discount_matrix_builder.py with your industry profile to get a 4-dimensional matrix with bands, approver tiers, and margin floors per cell.

How do I handle discount exceptions above the policy maximum?

Route the request through exception_router.py with the deal details, policy matrix, and recent exceptions. It returns the approver chain, severity-scaled compensating commitments such as multi-year prepay and named expansion paths, an audit-trail JSON block, and a precedent-risk flag.

What is the difference between commercial-policy and deal-desk skills?

Commercial-policy designs the discount matrix and exception flow itself, while deal-desk applies that policy to individual deals. Pricing-strategist is a separate skill that sets the pricing model and list price, which commercial-policy assumes already exist.

Does the discount matrix builder require external Python packages?

No, all three scripts are stdlib-only Python 3. Each supports --sample, --input with a JSON file, and --output markdown or json, so they run in any standard Python environment without pip installs.

Why does my discount matrix fail the policy lint check?

BLOCKER findings include approver hierarchy inversions, inverted bands where min exceeds max, and margin floors below 50 percent. MAJOR findings cover cliff edges over 10 points between adjacent cells, undefined strategic value tiers, and thin data in enterprise or strategic cells.

When should I not use this commercial policy skill?

Do not use it to approve a specific deal, set the pricing model or list price, or author proposal and MSA prose. It is a policy-design tool for the moment of writing or revising governance, not per-deal application or strategic pricing decisions.