SKILLEMALL.ai
GitHub ↗ RU Sign in

AC maylo-voice-assistant

Offline-first voice assistant stack for macOS (Wake word + VAD recording + local Whisper ASR + OpenClaw agent response + offline TTS via macOS say). Use to install, run, and troubleshoot the Maylo voice assistant web UI (cyberpunk dashboard with waveform + push-to-talk over WebSocket) and the always-on wake-word listener (e.g., 'Hey Jarvis') on a Mac mini.

modbender/skill-library-mcp Agent Skills author: modbender MIT 15 files · 4 scripts body ≈ 429 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Offline-first voice assistant stack for macOS (Wake word + VAD recording + local Whisper ASR + OpenClaw agent response + offline TTS via macOS say).

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentsData and analyticstype 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
A
91/100
safety, quality, tests
Safety 60%
97
Quality 40%
83
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

    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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • low Dangerous commands cmd-background-process assets/app/run_macmini.sh:29
      Starts a background / autostarted process
      nohup python -u "$ROOT/main.py" --mode full >"$ROOT/recordings/assistant.log" 2>&1 &
    • low Dangerous commands cmd-background-process scripts/run_assistant.sh:26
      Starts a background / autostarted process
      nohup python -u bridge/milo_responder_openclaw.py > recordings/responder.log 2>&1 &
    • low Dangerous commands cmd-background-process scripts/run_assistant.sh:27
      Starts a background / autostarted process
      nohup python -u main.py --mode full > recordings/assistant.log 2>&1 &

    Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 50/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 4 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 100Steps. 32 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 429 tokens
    • 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)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 358: enough signal without eating the budget
    • +4Structure: 6 headings
    • +3Step-by-step instructions: 32 items
    • +3All 3 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.