BB invoice-data-extraction
Use this skill when the user needs data pulled out of invoices, receipts, bills, bank statements, purchase orders, credit notes, payslips or other financial documents into a spreadsheet or structured rows, and especially when reading the files yourself would be unreliable or too slow, such as scanned or photographed pages, PDFs of many pages, many attachments or files at once, line items that must come out row by row, or a batch that has to come out in one consistent shape for a spreadsheet or an accounting import. It covers uploading the files to Invoice Data Extraction, submitting the extraction with instructions in plain words, waiting for it, answering the questions the extraction asks about the documents, reading the rows as JSON or downloading XLSX, CSV or JSON, and checking the credit balance. Needs the user's API key in INVOICE_DATA_EXTRACTION_API_KEY; without one, tell the user how to get a free one.
Use this skill when the user needs data pulled out of invoices, receipts, bills, bank statements, purchase orders, credit notes, payslips or other financial…
As a process B 67/100 · Nearly there — weak spots: result and completion
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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
description-long-hermesdescription is 922 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4435 tokens
- 100Steps. 15 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 922: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (10 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.