BB budget-and-fee-manager-scott-margetts
Matter budgeting and ongoing WIP/variance monitoring. Build phase-based fee estimates at matter setup, run bottom-up budgets by jurisdiction or workstream, calculate contingency, and structure AFA arrangements (fixed fee, capped fee, phased fixed fees). Ongoing monitoring: WIP tracking against budget, proportionality assessment (spend vs progress), variance commentary with root cause analysis, forecast-to-complete, realisation monitoring, write-off analysis. Trigger on: 'build a budget', 'fee estimate', 'what will this cost', 'WIP review', 'budget vs actual', 'how are we tracking against budget', 'we're over budget', 'realisation is poor', 'what's our ETC', 'budget for the German workstream', 'model the financial impact of this scope change', 'draft a fee adjustment', 'write-off analysis', 'how much contingency', 'AFA structure', 'fixed fee estimate', 'budget update', 'forecast to complete'.
Matter budgeting and ongoing WIP/variance monitoring.
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6393 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6393 tokens
- 100Tools and files. No external tools needed
- 100Steps. 50 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 904: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 34 headings
- +3Step-by-step instructions: 50 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.