deal-desk

Use when reviewing a specific inbound deal before close — when sales has asked for a discount that exceeds AE authority, when the customer has redlined the MSA, when per-deal economics (margin after discount, multi-year payment shape, indemnity exposure) need to be quantified, or when discount approval needs to be routed to a named human approver (Sales Director, VP Sales, CFO, CRO, General Counsel). Covers deal review, discount approval routing, per-deal margin scoring, deal exception handling, MSA redline triage, contract landmine detection (uncapped indemnity, MFN, perpetual license-back, missing DPA), and named-approver chain assembly. NEVER auto-approves — every output is a numeric scorecard plus a routing recommendation to a named human.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, highly actionable body with concrete CLI commands, a clear sequenced workflow, and real one-level-deep reference files. The main weakness is the inlined forcing-question library, which adds verbosity and would be better placed in a dedicated reference file.

Suggestions

Move the 'Forcing-question library' into its own reference file (e.g. references/forcing_questions.md) and surface it as a one-line pointer to tighten the SKILL.md body and improve progressive disclosure.

Add an explicit validation/retry checkpoint to the Workflow (e.g. 'If any CRITICAL landmine is present, stop and route to legal before assembling the packet') to make the critical-signal override a visible step rather than only an anti-pattern note.

Tighten the References bullets by dropping the inline source-name lists (SaaStr, Lemkin, Skok, etc.) into the referenced files, keeping SKILL.md to a one-line purpose per reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete tables, commands, and anti-patterns that earn their tokens, but the inlined 7-question 'Forcing-question library' with per-question canon citations is reference-like content that could be trimmed or moved to a reference file.	4 / 5
Actionability	Fully executable: a scripts table with purpose + profiles, a uniform CLI contract ('stdlib-only, --help, --sample, --input <json>, --output {human,json}'), and copy-paste Quick examples covering score/route/redline for the common cases.	5 / 5
Workflow Clarity	A clear 5-step sequence (Intake → Score → Route → Flag → Assemble) with a concrete command per step and validation gates ('critical signals override composite', 'Lock 1-4 before opening 5-7'), though there is no explicit error-recovery feedback loop in the main workflow.	4 / 5
Progressive Disclosure	Good structure with well-signaled, verified one-level-deep references (deal_desk_canon.md, discount_economics.md, contract_landmines.md) and a scripts/assets table, but the forcing-question library is inlined in SKILL.md rather than split into a reference, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An excellent description: explicit 'Use when' triggers, concrete action coverage, named approver roles, and a clear never-auto-approve boundary. The only soft spot is minor overlap risk with closely related commercial/legal siblings, which keeps distinctiveness at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'deal review, discount approval routing, per-deal margin scoring, deal exception handling, MSA redline triage, contract landmine detection (uncapped indemnity, MFN, perpetual license-back, missing DPA), and named-approver chain assembly' — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both: 'Use when reviewing a specific inbound deal before close — when...' gives concrete when-triggers, and 'Covers deal review, discount approval routing...' gives a clear what; the 'NEVER auto-approves' guard adds a precise scope boundary.	5 / 5
Trigger Term Quality	Natural trigger phrases a deal-desk user would actually say — 'when sales has asked for a discount that exceeds AE authority', 'when the customer has redlined the MSA', 'when discount approval needs to be routed to a named human approver (Sales Director, VP Sales, CFO, CRO, General Counsel)' — with strong synonym/role-name coverage.	5 / 5
Distinctiveness Conflict Risk	Carves a clear per-deal niche distinct from sibling skills, but the broader 'deal review' framing has minor overlap risk with the related commercial-policy and general-counsel skills referenced in the body.	4 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: commercial/skills/deal-desk/SKILL.md
Commit: 19392f7

Reviewed: ~10 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.