/deal-desk

name: deal-desk
description: "Use before closing a deal that needs a discount beyond AE authority, has a redlined MSA or unclear per-deal economics. Scores it with deal_scorer.py, names approvers with discount_approval_router.py and flags risky terms with terms_redliner.py. Never auto-approves."
license: MIT
metadata:
  version: 2.8.0
  author: claude-code-skills
  tags: [commercial, deal-desk, discount, margin, approval, redline, msa, terms]
  compatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]

deal-desk

Per-deal review and discount-approval routing. Scores deal margin + risk, routes discount approval to the right human, redlines T&Cs against commercial policy. **Never auto-approves.** Every output is a score plus a routing recommendation to a named human approver.

Purpose

Deal Desk / RevOps / sales leadership live at the moment between *sales-team-asks-for-discount* and *CFO/CRO/legal-signs*. This skill quantifies the asks and routes them.

Three deterministic tools:

1. `deal_scorer.py` — Scores a deal 0-100 across 5 dimensions (margin, risk, strategic value, commercial fit, term shape) and assigns one of four verdicts: **APPROVE / REVIEW / ESCALATE / DECLINE** — each tied to a named approver chain. 2. `discount_approval_router.py` — Maps a discount-percent + deal-size + tier to a named approver chain (AE → Manager → Director → VP → CFO/CRO) with estimated cycle days. Honors industry-tuned policy bands. 3. `terms_redliner.py` — Detects 10 founder/seller-killer patterns in deal terms (uncapped indemnity, MFN, perpetual license-back, missing DPA, NET-60+, broad non-solicit, etc.) with severity + standard counter + named legal/commercial approver.

When to use

Invoke this skill when:

• Sales has flagged a discount request above AE authority.
• A customer has returned a redlined MSA and you need triage before routing to legal.
• The deal needs CFO sign-off and you want a defensible margin breakdown.
• An RFP response requires multi-year terms and you need to score the shape.
• A renewal expansion is bundled with a discount and you need to verify policy fit.
• You're building a deal-desk approval queue and need consistent routing.

**Do NOT use this skill to**: author the proposal (use `business-growth/contract-and-proposal-writer`), redesign the discount matrix (use the `commercial-policy` sibling skill), or do deep legal redline of full contract text (use `c-level-advisor/skills/general-counsel-advisor`).

Workflow

1. **Intake the deal** — Sales/AE fills `assets/deal_intake_template.md` with ARR, term, discount, payment terms, customer tier, strategic flags, and any customer-flagged term redlines (20-min fill-out). 2. **Score margin + risk** — Run `deal_scorer.py --input deal.json --profile {saas|enterprise-software|services|marketplace}`. Read the composite + per-dimension breakdown + verdict. 3. **Route the discount** — Run `discount_approval_router.py --input deal.json --profile <same>`. Get the named approver chain + estimated cycle days. Modifiers (enterprise floor, SMB fast-lane) are surfaced explicitly. 4. **Flag the redlines** — Run `terms_redliner.py --input deal_terms.json`. Get ranked CRITICAL/HIGH/MEDIUM/LOW findings with the counter-language and the approver who must sign each. 5. **Assemble the packet** — Combine the three outputs into a deal-desk review packet. Always include the named approver chain. The packet is **a recommendation**, not an approval.

Scripts

| Script | Purpose | Industry profiles | |---|---|---| | `scripts/deal_scorer.py` | 5-dimension scorecard with verdict + chain | saas, enterprise-software, services, marketplace | | `scripts/discount_approval_router.py` | Discount % → named approver chain + cycle days | saas, enterprise-software, services, marketplace | | `scripts/terms_redliner.py` | 10-pattern landmine scanner with counters | n/a (terms-driven) |

All three: stdlib-only, `--help`, `--sample`, `--input <json>`, `--output {human,json}`.

References

• `references/deal_desk_canon.md` — Deal-desk operating practice: SaaStr playbooks (Jason Lemkin), Winning by Design (van der Kooij + Reichl), Forrester research, RevOps Co-op, OpenView benchmarks, Bridge Group AE comp, Salesforce Deal Desk best practices.
• `references/discount_economics.md` — Discount math + LTV impact: David Skok (For Entrepreneurs), Bessemer State of the Cloud, Tomasz Tunguz, OpenView NRR research, Pacific Crest + KeyBanc SaaS surveys, Insight Partners revenue ops. Includes worked margin math (a 30% discount on an 80% gross-margin product loses 37.5% of margin, not 30%).
• `references/contract_landmines.md` — 10+ named landmine patterns with example counter-language: YC startup library, Robert Klingberg (Founder's Guide to SaaS Agreements), Bowman + Brooke redline guides, IACCM/WorldCC commercial management research, Practical Law contracts library, Bradley Tusk on enterprise contracts, GC100 guidance.

Assumptions

• The skill assumes the **commercial policy already exists** (discount bands, payment-terms norms, indemnity caps). It applies the policy; it does not design it. See the `commercial-policy` sibling skill for policy design.
• Industry profiles bake in *customary* thresholds. If your company has a documented discount matrix, pass it via `policy_thresholds` in the input JSON to override.
• The terms redliner detects the 10 most common landmines. It is **not** a substitute for General Counsel review on the full contract.
• Scoring weights (margin 30%, risk 20%, strategic 15%, commercial 20%, term 15%) reflect a CFO-leaning bias. RevOps-led shops may want to reweight; the weights are constants at the top of `score_deal()` and are easy to tune.

Anti-patterns

• **Auto-approving deals.** This skill never says "approved". Every verdict (including `APPROVE`) names the human(s) who must sign. The output is a recommendation.
• **Skipping the redline scan** because the score is high. A high composite with `UNC