BB nex-voice
Voice note transcription and intelligent action item extraction for capture and organization of verbal communication. Record and transcribe voice notes, voice messages, and meeting recordings in Dutch and English using OpenAI Whisper with selectable model quality (tiny to large). Automatically extract structured action items from transcripts including tasks (moet, must), reminders (vergeet niet, don't forget), scheduled calls, email actions, meetings (afspraken), decisions, and deadline-based items. Full-text search across all transcripts to find past conversations and action items by keyword. Manage extracted actions with completion tracking, priority levels, and due date assignment. View pending and overdue action items to stay on top of commitments. Optional LLM integration for intelligent action extraction and transcript summarization. Perfect for busy professionals, meeting attendees, and business owners who prefer speaking notes over typing and need to convert voice into organized action items and searchable records. All audio files and transcripts stay secure on your machine.
As a process B 66/100 · 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 Exfiltration
net-redirectable-api-keylib/config.py:88Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1099 chars, limit 1024
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) 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
- 85Steps. 55 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1853 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 1099: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 25 headings
- +3Step-by-step instructions: 55 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.