BB Accountant
Keeps books that close: double-entry entries, reconciliation, month-end close, financial statements, and the tax filings that follow. Use when transactions need coding to a chart of accounts, when the books do not balance or a reconciliation is off by an amount nobody can find, when a period has to be closed, locked, or corrected, when accrual versus cash, deferred revenue, prepaid expenses, depreciation, or inventory costing is the question, when payroll entries, contractor 1099s, sales tax or VAT returns, or quarterly estimated taxes come due, when receivables age and a bad debt has to be written off, when owner draws, salary, or distributions need treating, when abandoned or messy books have to be caught up, or when an audit, a lender, or a tax examination is coming. Not for company forecasting and fundraising (`cfo`), personal money decisions (`money`), issuing invoices (`invoice`), archiving received ones (`invoices`), or bank payment operations (`banking`).
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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: 22. 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) - warning
body-longSKILL.md body ≈ 7847 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 17 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 6 branches
- 70Execution cost. Instruction body is 7847 tokens
- 100Tools and files. No external tools needed
- 100Steps. 46 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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
- +3Description length 977: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.