CB fee-arrangement-structuring
AFA design, scope-to-fee matching, negotiation preparation, health check, and scope dispute assessment for in-house legal ops teams managing outside counsel arrangements. Design fee structures (fixed, capped, collar, blended, phased, success). Assess whether scope supports a proposed AFA. Prepare commercial positions for fee negotiations. Review existing AFAs against delivery data. Assess OOS claims and build dispute response. Trigger on: 'structure the fee', 'move off hourly', 'design an AFA', 'does scope support a fixed fee?', 'negotiate the fee', 'renegotiate the arrangement', 'is our AFA holding?', 'fee health check', 'cap is being approached', 'firm is claiming OOS', 'is this in scope?', 'is this OOS?', 'AI should reduce the cost', 'blended rate vs fixed', 'collar arrangement', 'phased fees'.
AFA design, scope-to-fee matching, negotiation preparation, health check, and scope dispute assessment for in-house legal ops teams managing outside counsel…
As a process B 75/100 · Nearly there — weak spots: consistency, execution cost, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10259 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 75/100
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (fee-arrangement-structuring) differs from the folder (fee-arrangement-structuring-scott-margetts)
- 40Execution cost. Instruction body is 10259 tokens: crowds the task out of the window
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 86 steps
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Running it twice. Mutating operations check current state
- low 12 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 808: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 40 headings
- +3Step-by-step instructions: 86 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.