Pular para o conteúdo
TakoAPI
Voltar às skills

percept-voice-cmd

por jarvis563

Coding Agents & IDEs
354Downloads informados pelo clawskills.sh
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Voice command detection and action execution for OpenClaw agents.

Descrição

O que esta skill faz

Detects wake words in ambient audio and routes spoken commands to an OpenClaw agent for execution. Supports built-in actions like email, reminders, calendar queries, and notes, plus arbitrary forwarding for custom commands. Speaker authorization limits command execution to approved voices.

Two-tier intent parsing (regex first, LLM fallback) keeps simple commands fast while still handling complex natural language.

Quando usá-la

  • Sending an email hands-free while cooking
  • Setting a reminder without touching a keyboard
  • Checking today's calendar by speaking aloud
  • Taking a quick note during a meeting
  • Texting a contact while driving

Exemplo de fluxo de trabalho

ENTRADA

User says: "Hey Jarvis, remind me in 30 minutes to call the dentist"

AGENTE
  1. 1

    Percept buffers incoming transcript and detects the wake word "Hey Jarvis"

  2. 2

    Buffer extends 5 seconds to capture the full command

  3. 3

    Intent parser matches the reminder pattern via regex

  4. 4

    Contact and time parameters are extracted from the utterance

  5. 5

    Command is dispatched to the OpenClaw CLI to schedule the reminder

SAÍDA

Reminder set for 30 minutes from now with the note "call the dentist"

Requisitos

  • percept-listen skill installed and running
  • Percept dashboard accessible on port 8960 for wake word and speaker configuration

Instalação

clawhub install jarvis563/percept-voice-cmd

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links