AD 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.
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…
As a process D 48/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "compatible_tools"
Process rating: all ten parameters 48/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 34 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2561 tokens
- 100Running it twice. Mutating operations check current state
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 753: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.