BB Invoices
Files, checks, and audits the invoices you receive: OCR and e-invoice XML, duplicate and fraud checks, VAT deduction, and a searchable archive. Use when an invoice, bill, or receipt arrives as a PDF, photo, email attachment, or portal download and has to be filed; when asked where an old invoice is, or what was spent with a supplier last quarter; when preparing a VAT return or an export for an accountant; when an invoice looks wrong, duplicated, or larger than usual; when a supplier's bank details changed on the document; when a recurring invoice never arrived; and when a credit note, reverse charge, import VAT, or a foreign currency has to be booked correctly. Covers Factur-X/ZUGFeRD, XRechnung, Peppol, supplier normalization, and retention mandates. Not for issuing invoices to your own clients (`invoice`), tracking personal spending (`expenses`), chasing a client who owes you money (`clients`), or building a billing system (`billing`).
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions, 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: 16. 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 ≈ 6163 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
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6163 tokens
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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 951: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.