CC invoice-review-compliance
Invoice review, non-compliance flagging, rejection communication, billing trend analysis, and conversation preparation for in-house legal ops teams managing outside counsel. Review invoices against billing guidelines; flag block billing, prohibited fees, rate violations, staffing violations, late submission. Produce line-item review report and approval note. Draft rejection letter to outside counsel. Build invoice review checklist. Analyse billing trends across multiple invoices and produce a structured conversation guide for the relationship review. Identify systemic patterns and produce formal non-compliance notice. Trigger on: 'review this invoice', 'flag billing issues', 'check invoice against guidelines', 'write the rejection letter', 'build an invoice checklist', 'block billing', 'UTBMS', 'billing non-compliance', 'analyse our invoices', 'billing trends', 'prep for the billing conversation', 'relationship review', 'the firm keeps doing this', 'escalate'.
Invoice review, non-compliance flagging, rejection communication, billing trend analysis, and conversation preparation for in-house legal ops teams managing…
As a process C 57/100 · Has gaps — weak spots: result and completion, consistency, execution cost
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 ≈ 11959 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 15 mutating operations with no state check
- 40Consistency. Frontmatter name (invoice-review-compliance) differs from the folder (invoice-review-compliance-scott-margetts)
- 40Execution cost. Instruction body is 11959 tokens: crowds the task out of the window
- 55Failures and branches. 1 branches
- 60Steps. 96 steps, 4 vague phrases
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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 974: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 42 headings
- +3Step-by-step instructions: 96 items
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.