SKILLEMALL.ai
GitHub ↗ RU Sign in

BC jetson-cuda-voice

Fully offline, CUDA-accelerated local voice assistant pipeline for NVIDIA Jetson. Wake word (openWakeWord) → real-time VAD → whisper.cpp GPU STT → LLM → Piper TTS. Includes dynamic ambient noise calibration, conversation history, and ReSpeaker LED feedback. Tested on Jetson Xavier NX (sm_72, JetPack 5.1.4) with ReSpeaker USB Mic Array.

modbender/skill-library-mcp Agent Skills author: modbender MIT 6 files · 2 scripts body ≈ 1 903 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Fully offline, CUDA-accelerated local voice assistant pipeline for NVIDIA Jetson.

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructureAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
94
Quality 40%
70
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • 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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Dangerous commands cmd-privilege SKILL.md:145
    Privilege escalation / world-writable permissions
    sudo tee /etc/udev/rules.d/99-u…les << 'EOF'
  • low Dangerous commands cmd-privilege pipeline/setup.sh:82
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    echo "   sudo tee /etc/udev/rules.d/99-u…les << 'UDEV'"
    code literal

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 51/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 100Steps. 25 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1903 tokens
  • 100Running it twice. No mutating operations

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)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 337: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 25 items
  • +4Has examples (9 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.