BB nex-einvoice
Generate Belgian-compliant e-invoices in the Peppol BIS 3.0 UBL format from natural language input in Dutch or English, satisfying mandatory requirements for Belgian B2B invoicing from January 2026 onwards. Create professional invoices directly from conversational descriptions (e.g., "invoice ECHO Management for 5 hours consulting at 95 euros with 21% VAT"). Automatically calculate BTW (Belgian VAT) at correct rates (0%, 6%, 12%, 21%), manage comprehensive customer contact databases with VAT-ID validation against EU VIES, configure seller company information and payment defaults. Track invoice status through complete lifecycle (draft, sent, paid, overdue) with automatic payment date logging and reminders. Export invoices as standardized XML in Peppol BIS 3.0 format for seamless integration with accounting software, e-banking systems, and compliance tools. Supports structured payment references (betaalreferentie), automatic sequential invoice numbering per fiscal year, flexible payment terms (NET30, NET45, etc.), and credit note generation for returns or corrections. View comprehensive statistics on invoiced amounts, outstanding balances, customer breakdowns, and VAT collected for quarterly aangifte filing. Ideal for freelancers, eenmanszaken, and small Belgian SMEs who invoice regularly. All invoice data encrypted and stored locally.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Shorten the description to 1024 characters.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-shell-rcsetup.sh:110Writes to a shell startup fileecho " Add this to your ~/.bashrc or ~/.zshrc"
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1355 chars, limit 1024
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 10 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
- 70When it triggers. States when to use, but not when not to
- 100Steps. 38 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2789 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
- +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 1355: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 38 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.