AB bookkeeping-close
Runs small and midsize business bookkeeping operations - categorizes bank and card transactions to a chart of accounts, reconciles a bank or card statement against the ledger, works a month-end close checklist, and produces a close package for the accountant. Works from QuickBooks Online, Xero, bank CSV/OFX, or Mercury exports, and from the Xero, QuickBooks, or Mercury connectors when present. Use it whenever the user says "reconcile", "bank rec", "categorize transactions", "month end close", "close the books", "books don't match the bank", "reconciliation is off by", "uncategorized expenses", or shares a QuickBooks or Xero export or a bank statement CSV, even if they do not name the task. Never plugs a difference; every unreconciled dollar is explained or listed.
Runs small and midsize business bookkeeping operations - categorizes bank and card transactions to a chart of accounts, reconciles a bank or card statement…
As a process B 78/100 · Nearly there — weak spots: running it twice, progress reporting
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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 78/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 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
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1758 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 774: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 17 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.