Commercial Policy
Designs a company's commercial policy: the discount matrix, exception approval flow, and governance rules that Deal Desk and AEs operate under. Produces a data-backed policy artifact with approver tiers, margin floors, and a lint report, not per-deal approvals.
✨ What it does
- Builds a 4-dimensional discount matrix (ARR band × term × payment terms × strategic value) with approved discount bands,
- Routes out-of-matrix discount requests through a named approver chain with required compensating commitments and audit-t
- Flags precedent risk when 3+ similar exceptions land in a trailing quarter.
- Lints the matrix for governance defects: approver inversion, band inversion, margin-floor violation, coverage gaps, clif
- Provides industry profiles (saas, enterprise-software, api, marketplace, services) and quarterly review workflow.
- Includes forcing-question library to grill policy design before building.
🎯 When to use it
- A new Head of Commercial or Deal Desk is writing the company's first formal commercial policy.
- The existing discount matrix is older than 6 months and discount drift is appearing in margin reviews.
- Reps are citing past exceptions as precedent and you need to break the precedent loop.
- Q-over-Q exception counts are rising, suggesting matrix bands are mispriced.
- CFO has tightened the margin floor and the matrix must be rebuilt against the new constraint.
🚀 How to use
Trigger: /cs:grill-commercial
Trigger by asking to design or revise a commercial policy, e.g., 'Build a discount matrix for our SaaS business' or 'Revise our commercial policy against a new margin floor.' The skill expects deal data (ARR, discount %, term, payment terms, strategic value, win/loss, NRR) in a JSON intake file. Run the scripts in sequence: discount_matrix_builder.py, policy_linter.py, exception_router.py --sample. Example prompts:
Design a commercial policy for our enterprise software, using the last 4 quarters of CRM data.
Rebuild our discount matrix with a 40% margin floor and lint it before publishing.
📄 Output: A versioned commercial policy artifact: discount matrix JSON, exception flow specification, and a lint report with BLOCKER/MAJOR/MINOR findings.
📦 Add this skill to Claude Code
# 1. Get the skills repo
git clone --depth 1 https://github.com/alirezarezvani/claude-skills /tmp/claude-skills
# 2. Copy this skill into your project (or ~/.claude/skills for all projects)
mkdir -p .claude/skills
cp -r /tmp/claude-skills/commercial/skills/commercial-policy .claude/skills/commercial-policySkill source: commercial/skills/commercial-policy/SKILL.md
⚠️ Good to know
Assumes pricing model and list price already exist (use pricing-strategist); this skill governs discounts off list, not per-deal approval (use deal-desk).
❓ FAQ
What does the skill produce?
It produces the commercial policy itself: a discount matrix, exception flow, and lint report—not a per-deal approval.
How often should the matrix be reviewed?
Quarterly. Re-run the builder and linter against the latest 4-quarter rolling deal corpus; cells with NRR below target are flagged.
What happens if 3+ similar exceptions occur in a quarter?
The exception router flags precedent risk, signaling the matrix band is mispriced and should be rebuilt, not more exceptions approved.
🤖 Overview, features, install steps and FAQ were generated from the project's SKILL.md on Sep 4, 2026. Always check the original source before running commands.