AB Expenses
Logs, splits, categorizes and reports spending — daily expenses, shared costs, reimbursements, receipts, project and trip budgets. Use when the user paid for something and wants it recorded, when a bill has to be split and someone told what they owe, when a group trip or shared flat needs settling up, when a client owes money back and the claim has to be assembled, when they ask where their money went or why a category jumped, when a renovation, wedding or trip budget needs a remaining number, when something was paid in another currency, when a refund, deposit or duplicate charge has to be booked, or when the log no longer matches the card statement. Not for net worth or debt planning (`personal-finance-tracker`), zero-based budgeting (`zero-based-budgeting`), subscription inventories (`subscriptions`), issuing invoices (`invoice`), OCR archiving of supplier invoices (`invoices`), payment software (`billing`), or bookkeeping (`accountant`).
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 21 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 4580 tokens
- 100Steps. 39 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Description length 954: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 9 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.