SkillAgentSearch skills...

deal-desk

Deal desk: reviews, approves, and structures non-standard sales deals

Install / Use

npx skills add borghei/Claude-Skills --skill deal-desk

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

88/100

Category

Sales

Supported Platforms

Universal

Our assessment of deal-desk

deal-desk scores 88/100 on our quality scale, 26th of 41 Sales skills we index.

Its SKILL.md is 18 KB long, well organised into 32 sections with 2 code examples: a thorough specification that gives an agent plenty to work with.

It has 817 GitHub stars, a meaningful sign that others use it.

Substance
30/30
Structure
18/20
Description
12/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so deal-desk is actively maintained.
  • Our last check on 2026-11-01 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

deal-desk compared with similar skills

All 4 of these similar skills score higher than deal-desk; compare them before choosing.

SkillScoreStarsUpdatedFormat
deal-desk (this skill)by borghei8881757d agoSKILL.md
taste-skillby Leonxlnx100117.6k9d agoCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.9k8d agoCLAUDE.md
x402by browser-use100121.0k4d agoSKILL.md
algorithmic-artby anthropics100177.9k56d agoSKILL.md

Frequently asked questions

How do I install deal-desk?
Run npx skills add borghei/Claude-Skills --skill deal-desk. The install tabs above show the steps for each supported agent.
Which AI agents does deal-desk work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is deal-desk safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is deal-desk still maintained?
The repository was last updated about 2 months ago, so deal-desk is actively maintained.

name: deal-desk description: > Deal desk: reviews, approves, and structures non-standard sales deals. Use when standing up a deal desk, building approval-threshold matrices, designing deal-review packets, routing deals, or auditing deals for compliance. license: MIT + Commons Clause metadata: version: 1.0.0 author: borghei category: commercial domain: business-growth updated: 2026-05-27 tags: [deal-desk, sales-operations, discount-approval, commercial-operations, contract-review, deal-velocity, gtm]

Deal Desk

End-to-end deal-desk operational practice: charter, approval thresholds, deal-review packet design, routing automation, velocity analysis, and the governance that turns "every deal is a snowflake" into "we close non-standard deals in 48 hours predictably."

This skill is provider-agnostic: works whether your CRM is Salesforce, HubSpot, Pipedrive, or homegrown. The patterns and decisions transfer.


When to use this skill

| Situation | Skill applies | |-----------|---------------| | Starting a deal-desk function from scratch | Yes — start with charter design | | Reviewing existing deal-desk for slowness / inconsistency | Yes — use scripts/deal_velocity_analyzer.py + bottleneck patterns | | Defining who can approve what discount / term | Yes — use approval threshold matrix + scripts/discount_authority_router.py | | Building the deal-review packet template | Yes — see deal-review packet section + scripts/deal_review_packet.py | | Approving / declining a specific deal | Use the packet generator + approval router | | Setting pricing strategy | Use business-growth/pricing-strategy first | | Forecasting / measuring pipeline | Use business-growth/revenue-operations | | Negotiating an individual contract | Pair with business-growth/contract-and-proposal-writer |


What deal desk does (and doesn't)

Does:

  • Review non-standard deals: discounts beyond rep authority, custom legal terms, custom SLAs, multi-product bundles, payment terms outside policy
  • Make the approval decision (or route to the right approver)
  • Structure the deal: pricing, terms, ramp schedule, success criteria
  • Maintain the deal-desk policy — what's standard, what needs approval
  • Track deal velocity (time from request → decision → signature)
  • Produce evidence for finance / audit (every concession traceable)

Doesn't:

  • Set the published pricing (that's pricing strategy)
  • Negotiate with the customer (that's the sales rep / AE)
  • Close the sale (that's the rep + customer success)
  • Run the order-to-cash workflow (that's billing / RevOps)
  • Replace legal review (legal is one of the approvers, not the function itself)

A clean deal-desk = the lubricant. Without it, every non-standard deal turns into a multi-week negotiation among engineering / product / legal / finance / executive. With it, those people are consulted by deal desk as needed and the rep gets a yes/no in days.


Deal-desk charter (template)

Every deal desk needs a written charter. Use this template:

purpose:
  Deal Desk reviews, approves, and structures non-standard deals to enable
  sales to close faster while keeping commercial / legal / financial risk
  within company tolerance.

scope:
  In-scope:
    - All deals > $X ARR
    - All deals with discount > Y%
    - All deals with non-standard terms (custom SLAs, custom legal language,
      payment terms beyond Net 30, ramp deals, multi-year discounts > 12 months
      of standard, bundles spanning multiple product lines)
    - All renewals with > 20% expansion or > 10% contraction
    - All deals to enterprise (>1000 employees) or regulated industries
  Out-of-scope:
    - Self-serve / PLG transactions
    - Standard renewals within auto-renewal terms
    - Trial extensions < 30 days
    - Add-ons < $X per existing customer

sla:
  - Standard deal-desk review (no exec approval needed): 1 business day
  - Deal needing CFO/CRO approval: 2 business days
  - Deal needing CEO/Board approval: 5 business days
  - Legal-only review (no commercial concession): 2 business days

intake_format:
  Sales submits via [Salesforce form / CPQ tool / Slack form]. Required fields:
    - Customer name + size + industry
    - Product(s) + ACV
    - Requested deviation from standard (specific list)
    - Justification (competitor situation, customer constraint, strategic value)
    - Standard-pricing total + requested total
    - Contract length + payment terms
    - Implementation / SLA requirements

decision_inputs:
  - Customer LTV estimate
  - Strategic value (logo, reference, vertical foothold)
  - Risk (credit, compliance, integration)
  - Margin impact

outputs:
  - Approve / decline / counter
  - If approve: signed approval packet with terms, conditions, expiration date
  - If counter: list of negotiable items + non-negotiables
  - If decline: reasoning + alternatives

team:
  Deal-desk lead: <name>
  Deal-desk analysts: <names>
  Standing approvers: CRO, CFO, General Counsel, VP Product (escalation paths)
  Consulted as-needed: Engineering Lead, Security Lead, Customer Success Lead

metrics:
  - Median time-to-decision (target: 1 business day)
  - Decision distribution (% approved, % declined, % countered)
  - Discount-on-discount %  (deals where requested discount was further negotiated up)
  - Discount % vs ACV (correlation; outliers reviewed monthly)
  - Win rate of deal-desk-approved deals
  - Concession follow-through (did the customer keep their side?)

See references/deal-desk-charter-and-process.md for the full charter template, including sub-charters per region, intake form spec, and the standard SLAs.


Approval threshold matrix

The matrix defines: for each deal characteristic (discount %, contract length, custom term type), who can approve it.

Standard matrix template

| Deal characteristic | Rep | Sales Manager | Director | VP Sales | CRO | CFO | CEO | |---------------------|-----|---------------|----------|----------|-----|-----|-----| | Discount 0-10% | ✓ | | | | | | | | Discount 10-20% | | ✓ | | | | | | | Discount 20-30% | | | ✓ | | | | | | Discount 30-40% | | | | ✓ | | | | | Discount 40-50% | | | | | ✓ | | | | Discount > 50% | | | | | | | ✓ | | ACV > $250k | | ✓ | | | | | | | ACV > $1M | | | | ✓ | | | | | ACV > $5M | | | | | | | ✓ | | Multi-year > 12mo standard | | ✓ | | | | | | | Non-standard payment terms | | | | | | ✓ | | | Custom SLA / penalties | | | | (with CCO) | | | | | Custom legal language | | | | | | | (Legal must concur) | | MSA red-line on liability cap | | | | | | | (Legal must concur) | | Most-favored-nation clause | | | | | | ✓ | | | Acceptance criteria / payment-on-acceptance | | | | | | ✓ | | | Multi-product / cross-BU bundle | | | (each BU lead approves) | | | | | | Whitelabel / OEM rights | | | | | | | ✓ |

Customize per company stage, ACV distribution, and authority preference (some orgs want CRO at 30%, others delegate further down).

Stacking rule

When multiple non-standard items apply, the highest required approver applies. A $1M deal at 25% discount with custom SLA needs VP Sales (ACV) AND Director (discount) AND VP Sales+CCO (custom SLA) → effectively requires VP Sales sign-off + CCO + Legal concurrence.

Use scripts/discount_authority_router.py --deal deal.yaml to compute the required approvers for any deal.

See references/approval-thresholds-and-routing.md for the full matrix design guide, regional variants, escalation paths, and routing automation patterns.


The deal-review packet

Every non-standard deal gets a packet. Without it, approvers ask the same questions repeatedly and decisions take days instead of hours.

Standard packet structure

# Deal Review: <Customer Name>

## Summary
- Customer: <name, size, industry>
- ACV: $<amount>
- Discount %: <%> (vs standard $<list-price>)
- Contract: <length>, <payment terms>
- Decision needed by: <date>

## Standard vs Requested
| Item | Standard | Requested | Delta |
|------|----------|-----------|-------|
| ACV  | $X       | $Y        | -Z%   |
| Term | 12mo     | 36mo      | +24mo |
| Payment | Net 30 | Net 60   | +30d  |
| SLA  | 99.5%    | 99.9%     | +0.4% |
| Liability cap | 1x fees | 2x fees | +1x |
| Termination for convenience | No | Yes (90d) | New |

## Justification
- Why customer wants this: <competitor situation, budget cycle, etc.>
- Why we're considering: <strategic value, logo, vertical>
- Customer leverage: <alternatives they have>

## Financial impact
- Standard ARR: $X
- Discounted ARR: $Y (Z% off)
- Net new gross margin: $A (with cost overlay)
- Projected LTV with this discount: $B
- Discount payback if customer renews: <years>

## Strategic value
- Logo value: <high/medium/low — reasoning>
- Reference value: <will they be a public ref? case study?>
- Vertical foothold: <do we want this vertical?>
- Competitive replacement: <who are we displacing?>

## Risk
- Credit risk: <score / payment history>
- Compliance risk: <regulated? data residency?>
- Technical fit risk: <integration complexity>
- Concession follow-through: <are they likely to honor commitments?>

## Required approvers (per matrix)
- [ ] Director: <name>
- [ ] VP Sales: <name>
- [ ] CFO: <name>
- [ ] Legal: <name>

## Recommendation (from deal desk)
<Approve / Counter / Decline> — with reasoning

## Conditions if approved
- Discount expires <date>
- Customer must agree to: <reference call, case study, etc.>
- Customer agrees this is single-instance (not precedent)
- Payment must close by <date>

Use scripts/deal_review_packet.py --deal deal.yaml to generate this packet from a deal spec.


Velocity analysis

A slow deal desk strangles sales. Measure and tune.

Key metrics

| Metric | Healthy | Warning | |--------|---------|---------| | Median time-to-decision | < 1 business day | > 3 days | | 90th percentile time-to-decision | < 3 business days | > 7 days | | % of deals waiting on a single approver > 24h | < 10% | > 30% | | Deals stuck > 7 days | 0 | > 5 | | Sales rep satisfaction with deal desk (NPS) | > 50 | < 0 | | % approved (high approval rate may mean threshold too low) | 60-80% | > 95% or < 40% | | Discount-on-discount: deals where customer negotiated up after deal-desk approval | < 10% | > 30% |

Run scripts/deal_velocity_analyzer.py --deals deals.csv to compute these from a CRM export.

Common bottlenecks

| Bottleneck | Diagnosis | Fix | |------------|-----------|-----| | Single approver bottleneck (one person on everything) | Routing matrix concentrated authority | Delegate; add back-ups; raise thresholds | | Legal review takes a week | Legal sees every deal | Standard MSA + pre-approved clause library; Legal only on deviations | | Engineering needed for SLA review | Custom SLAs every time | Publish standard SLA tiers; only deviations route to eng | | Approval cycle back-and-forth | Packet missing key info | Use the standard packet template; reject incomplete submissions | | Long executive lag | Exec doesn't have context for every deal | Weekly deal review meeting for batch decisions on smaller items | | Sales submits incomplete packets | Reps don't know what to include | Intake form that enforces required fields | | No SLA enforcement | Deals sit in queue with no urgency | Publish + report SLA; aging dashboard visible to leadership |

See references/discount-and-concession-playbook.md for the discount/concession patterns: legitimate reasons for each concession type, how to evaluate, alternatives to discounting, and how to structure performance-based discounts.


Clarify First

Before generating the deal-desk artifact, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • [ ] Task type — standing up the desk (charter + matrix) vs reviewing one deal (packet) (determines which

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars817
CategorySales
Updated1mo ago
Forks141

Languages

HTML

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium