本文へスキップ
TakoAPI
スキル一覧に戻る

percept-voice-cmd

jarvis563 作

Coding Agents & IDEs
354ダウンロード数はclawskills.shが公開している値です
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Voice command detection and action execution for OpenClaw agents.

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

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

エージェント
  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

出力

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

要件

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

インストール

clawhub install jarvis563/percept-voice-cmd

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク