deal-desk

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

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.

单笔交易审核与折扣审批路径分配。对交易利润率和风险进行评分，将折扣审批分配给对应的负责人，对照商业政策对条款进行红线标注。绝不自动审批。所有输出均为评分加上给指定人工审批者的路径推荐。

Purpose

用途

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:

```
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.
```
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.
```
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.

Deal Desk（交易支持团队）/ RevOps（营收运营）/ 销售管理层的工作核心是衔接「销售团队申请折扣」与「CFO/CRO/法务签署」之间的环节。本Skill可量化申请内容并分配审批路径。

包含三个确定性工具：

```
deal_scorer.py
```
— 从5个维度（利润率、风险、战略价值、商业适配性、条款模式）对交易进行0-100分的评分，并给出四种verdict之一：APPROVE（批准）/ REVIEW（审核）/ ESCALATE（升级）/ DECLINE（拒绝）——每种结果都对应一条指定的审批者链。
```
discount_approval_router.py
```
— 将折扣比例+交易规模+客户层级映射到指定的审批者链（AE→经理→总监→副总裁→CFO/CRO），并预估周期天数。遵循针对行业优化的政策区间。
```
terms_redliner.py
```
— 检测交易条款中的10种对创始人/销售致命的模式（无上限赔偿、最惠国待遇、永久许可回溯、缺失DPA、NET-60+付款期限、宽泛的挖人限制等），并标注严重程度、标准应对话术以及指定的法务/商务审批者。

When to use

使用场景

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

在以下场景调用本Skill：

销售提出超出AE权限的折扣申请时。
客户返回带有红线标注的MSA，需要在提交给法务前进行分类处理时。
交易需要CFO签署，且需要一份可辩护的利润率细分报告时。
RFP响应需要包含多年期条款，且需要对条款模式进行评分时。
续约扩容捆绑了折扣，需要验证是否符合政策时。
搭建Deal Desk审批队列，需要统一的路径分配规则时。

请勿使用本Skill：撰写提案（使用

business-growth/contract-and-proposal-writer

）、重新设计折扣矩阵（使用

commercial-policy

兄弟Skill）、对完整合同文本进行深度法务红线标注（使用

c-level-advisor/skills/general-counsel-advisor

）。

Workflow

工作流程

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).

Score margin + risk — Run

deal_scorer.py --input deal.json --profile {saas|enterprise-software|services|marketplace}

. Read the composite + per-dimension breakdown + verdict.

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.
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.
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.

接收交易信息 — 销售/AE填写
```
assets/deal_intake_template.md
```
，包含ARR（年度经常性收入）、期限、折扣、付款条款、客户层级、战略标记以及客户标注的所有条款红线（填写耗时约20分钟）。
评分利润率与风险 — 运行
```
deal_scorer.py --input deal.json --profile {saas|enterprise-software|services|marketplace}
```
。查看综合评分+各维度细分评分+判定结果。
分配折扣审批路径 — 运行
```
discount_approval_router.py --input deal.json --profile <same>
```
。获取指定的审批者链+预估周期天数。会明确显示调整项（企业级下限、SMB快速通道）。
标记红线条款 — 运行
```
terms_redliner.py --input deal_terms.json
```
。获取按CRITICAL（严重）/HIGH（高）/MEDIUM（中）/LOW（低）排序的检测结果，以及应对话术和必须签署的审批者。
整理审核包 — 将三个工具的输出整合为Deal Desk审核包。务必包含指定的审批者链。该审核包仅为推荐意见，而非最终审批结果。

Scripts

脚本

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}

脚本	用途	行业配置文件
`scripts/deal_scorer.py`	包含判定结果与审批链的5维度评分卡	saas, enterprise-software, services, marketplace
`scripts/discount_approval_router.py`	将折扣比例映射到指定审批者链+周期天数	saas, enterprise-software, services, marketplace
`scripts/terms_redliner.py`	检测10种风险模式并提供应对话术	n/a (terms-driven)

所有脚本：仅依赖标准库，支持

--help

、

--sample

、

--input <json>

、

--output {human,json}

参数。

References

参考资料

```
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.

```
references/deal_desk_canon.md
```
— Deal Desk操作实践：SaaStr手册（Jason Lemkin）、Winning by Design（van der Kooij + Reichl）、Forrester研究、RevOps Co-op、OpenView基准数据、Bridge Group AE薪酬体系、Salesforce Deal Desk最佳实践。
```
references/discount_economics.md
```
— 折扣计算+LTV（客户终身价值）影响：David Skok（For Entrepreneurs）、Bessemer云状态报告、Tomasz Tunguz、OpenView NRR（净收入留存）研究、Pacific Crest + KeyBanc SaaS调研、Insight Partners营收运营。包含实际利润率计算示例（毛利率80%的产品打7折，利润率损失37.5%，而非30%）。
```
references/contract_landmines.md
```
— 10+种风险模式示例及应对话术：YC创业库、Robert Klingberg（《SaaS协议创始人指南》）、Bowman + Brooke红线指南、IACCM/WorldCC商务管理研究、Practical Law合同库、Bradley Tusk关于企业合同的观点、GC100指南。

Assumptions

假设前提

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.

本Skill假设商业政策已存在（折扣区间、付款条款规范、赔偿上限）。它仅执行政策，不设计政策。如需设计政策，请使用
```
commercial-policy
```
兄弟Skill。
行业配置文件内置了常规阈值。如果贵公司有文档化的折扣矩阵，可通过输入JSON中的
```
policy_thresholds
```
参数覆盖默认值。
条款红线检测工具仅检测10种最常见的风险点。它不能替代总法律顾问对完整合同的审核。
评分权重（利润率30%、风险20%、战略价值15%、商业适配性20%、条款模式15%）偏向CFO视角。以RevOps为主导的团队可能需要调整权重；权重是
```
score_deal()
```
函数顶部的常量，易于调整。

Anti-patterns

反模式

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
```
UNCAPPED_INDEMNITY
```
is still a DECLINE — critical signals override composite.
Using this for legal review of arbitrary contract text. This skill takes a structured terms JSON. For prose redlining, use
```
c-level-advisor/skills/general-counsel-advisor/scripts/contract_risk_scanner.py
```
.
Treating the discount router as a discount calculator. It routes a discount the AE/customer has already proposed; it does not calculate the right discount. Pricing logic lives in
```
commercial/skills/pricing-strategist
```
.
Routing every deal to CFO. The router stops at the lowest-authority hop that can sign the deal. Over-escalation slows the funnel and trains AEs to over-discount.
Hand-editing the chain to skip a hop. Modifiers (enterprise floor, SMB fast-lane) are explicit; hidden skips defeat the audit trail.

自动审批交易：本Skill绝不会输出“已批准”。所有判定结果（包括
```
APPROVE
```
）都会指定必须签署的人员。输出仅为推荐意见。
因评分高而跳过红线扫描：即使综合评分很高，若存在
```
UNCAPPED_INDEMNITY
```
，仍会判定为DECLINE——关键信号优先于综合评分。
使用本Skill对任意合同文本进行法务审核：本Skill接收的是结构化的条款JSON。如需对散文式文本进行红线标注，请使用
```
c-level-advisor/skills/general-counsel-advisor/scripts/contract_risk_scanner.py
```
。
将折扣路径分配工具当作折扣计算器使用：它仅对AE/客户已提出的折扣分配审批路径，不计算合适的折扣。定价逻辑在
```
commercial/skills/pricing-strategist
```
中。
将所有交易都提交给CFO：路径分配工具会在最低权限的审批节点停止。过度升级会减慢漏斗速度，并导致AE习惯性申请过高折扣。
手动修改审批链跳过某一节点：调整项（企业级下限、SMB快速通道）是明确的；隐藏的跳过操作会破坏审计轨迹。

Distinct from

与兄弟Skill的区别

Sibling	Scope	Difference
`commercial/skills/pricing-strategist`	Sets the pricing model (per-seat vs usage vs tiered, list prices, packaging)	Operates at the strategy layer — not per deal
`business-growth/contract-and-proposal-writer`	Authors proposals, SOWs, MSAs	Output is a document; deal-desk is the gate before signing
`commercial/skills/commercial-policy` (sibling)	Designs the discount matrix and approval thresholds	Deal-desk applies that policy to one deal at a time
`c-level-advisor/skills/general-counsel-advisor`	Deep legal redline + term-sheet analysis	Operates on full contract prose; deal-desk uses structured terms JSON
`c-level-advisor/skills/cfo-advisor`	Burn rate, unit economics, fundraising models	Strategic finance; deal-desk is one-deal granularity

兄弟Skill	范围	差异
`commercial/skills/pricing-strategist`	制定定价模型（按席位/使用量/分层定价、标价、包装）	处于战略层面——不针对单笔交易
`business-growth/contract-and-proposal-writer`	撰写提案、SOW（工作说明书）、MSA	输出为文档；Deal Desk是签署前的审核关卡
`commercial/skills/commercial-policy` （兄弟Skill）	设计折扣矩阵和审批阈值	Deal Desk执行该政策，针对单笔交易
`c-level-advisor/skills/general-counsel-advisor`	深度法务红线标注+条款清单分析	针对完整合同文本；Deal Desk使用结构化条款JSON
`c-level-advisor/skills/cfo-advisor`	烧钱率、单位经济效益、融资模型	战略财务层面；Deal Desk针对单笔交易的粒度

Quick examples

快速示例

bash

undefined

bash

undefined

Score a deal

对交易进行评分

python3 scripts/deal_scorer.py --sample python3 scripts/deal_scorer.py --input my_deal.json --profile enterprise-software

Route the discount

分配折扣审批路径

python3 scripts/discount_approval_router.py --sample python3 scripts/discount_approval_router.py --input my_deal.json --profile saas

Flag the redlines

标记红线条款

python3 scripts/terms_redliner.py --sample python3 scripts/terms_redliner.py --input my_deal_terms.json --output json


The sample (a 28%-discount enterprise SaaS deal with uncapped indemnity + MFN) correctly DECLINEs at 55.4 / 100 composite and routes to AE → Deal Desk → VP Sales → CFO → CRO → General Counsel.

python3 scripts/terms_redliner.py --sample python3 scripts/terms_redliner.py --input my_deal_terms.json --output json


示例（一个折扣28%的企业级SaaS交易，包含无上限赔偿+最惠国待遇）的综合评分为55.4/100，正确判定为DECLINE，审批路径为AE→Deal Desk→销售副总裁→CFO→CRO→总法律顾问。

Forcing-question library (Matt Pocock grill discipline)

强制问题库（Matt Pocock grill discipline）

Walked one at a time by

/cs:grill-commercial

or the Commercial orchestrator. Recommended answer + canon citation per question. Never bundled.

"What's the gross margin at full discount, AND what does next quarter's pipeline look like at the same terms?" Recommended: model both. Refuse to approve until the AE can articulate the precedent risk. Canon: David Skok (For Entrepreneurs — discount math), Tomasz Tunguz benchmarks. Anti-pattern: one 40% precedent reshapes 3 quarters of pipeline.
"Is this discount inside or outside the standard discount matrix?" Recommended: if outside, surface the policy exception explicitly and route to the named exception approver. Canon: OpenView discount benchmarks, RevOps Co-op playbooks.
"What's the strategic value beyond ARR — logo, reference, expansion path?" Recommended: require a named, verifiable expansion or reference commitment in writing. Canon: SaaStr (Jason Lemkin) on logo discounts; Winning by Design on commitment language.
"Has the customer signed an indemnity cap, a liability cap, and a DPA (if EU data)?" Recommended: required. Uncapped indemnity is a critical-signal override that blocks APPROVE regardless of margin. Canon: WorldCC (formerly IACCM) commercial management research, GC100 contract guidance.
"What payment terms — NET-30, NET-45, or NET-60+?" Recommended: prefer NET-30; NET-45+ is a cash flow drag worth quantifying. Canon: KeyBanc SaaS Survey, Pacific Crest data — every 15 days of payment terms costs ~2% of effective deal value.
"Is the term multi-year with annual prepay, or annual auto-renew?" Recommended: multi-year prepay > annual prepay > annual auto-renew. Auto-renew without 60-day notice is a redline. Canon: Salesforce Deal Desk best practices, OpenView NRR studies.
"Who is the named human approver at each hop of the discount chain?" Recommended: surface the name, not just the role. "VP Sales" is not an approver; "Maria Singh, VP Sales" is. Canon: Bridge Group SaaS AE compensation research — named approval reduces precedent drift by 50%+.

Walk depth-first. Lock 1-4 before opening 5-7. After all 7 are answered, invoke

deal_scorer.py

→

discount_approval_router.py

→

terms_redliner.py

in sequence.

由

/cs:grill-commercial

或商务编排器逐一提出。每个问题都有推荐答案和参考资料引用。绝不批量提问。

“全额折扣后的毛利率是多少，且下一季度采用相同条款的销售漏斗情况如何？” 推荐：同时建模两者。在AE能阐明先例风险前，拒绝审批。参考资料：David Skok（For Entrepreneurs——折扣计算）、Tomasz Tunguz基准数据。反模式：一次40%的折扣先例会影响未来3个季度的销售漏斗。
“该折扣是否在标准折扣矩阵范围内？” 推荐：若超出范围，明确标记政策例外，并提交给指定的例外审批者。参考资料：OpenView折扣基准数据、RevOps Co-op手册。
“除ARR外，该交易的战略价值是什么——客户标志、参考案例、扩容路径？” 推荐：要求提供书面的、可验证的扩容或参考案例承诺。参考资料：SaaStr（Jason Lemkin）关于客户标志折扣的观点；Winning by Design关于承诺话术的内容。
“客户是否签署了赔偿上限、责任上限以及DPA（若涉及欧盟数据）？” 推荐：必须签署。无上限赔偿是关键信号，无论利润率如何，都会阻止APPROVE判定。参考资料：WorldCC（原IACCM）商务管理研究、GC100合同指南。
“付款条款是什么——NET-30、NET-45还是NET-60+？” 推荐：优先选择NET-30；NET-45+会拖累现金流，需量化影响。参考资料：KeyBanc SaaS调研、Pacific Crest数据——每延长15天付款期限，相当于损失约2%的有效交易价值。
“合同期限是多年期且每年预付，还是年度自动续约？” 推荐：多年期预付>年度预付>年度自动续约。无60天通知期的自动续约是红线条款。参考资料：Salesforce Deal Desk最佳实践、OpenView NRR研究。
“折扣审批链每个节点的指定人工审批者是谁？” 推荐：明确姓名，而非仅职位。“销售副总裁”不是审批者；“Maria Singh，销售副总裁”才是。参考资料：Bridge Group SaaS AE薪酬研究——指定姓名的审批可将先例偏差降低50%以上。

按深度优先顺序提问。在回答完1-4后再提问5-7。所有7个问题回答完毕后，依次调用

deal_scorer.py

→

discount_approval_router.py

→

terms_redliner.py

。