OpenParable
Skip to content
← Back to skills

Human Auth Microphone

Apps & Automation
human-auth-microphone

Human Auth Microphone is an Agent Skill for apps & automation published in the pockebot/openpocket repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Handle microphone audio recording delegation from Human Phone. Covers audio capture, push to Agent Phone, and audio file usage in apps.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/pockebot/openpocket/blob/HEAD/skills/human-auth-microphone/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/human-auth-microphone, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Human Auth: Microphone

Use this when an app needs microphone input (voice recording, audio message, speech-to-text).

When to Trigger

  • App requests microphone permission or opens an audio recording UI.
  • App is waiting for voice input (voice search, voice message, audio note).
  • Capability Probe detects microphone / RECORD_AUDIO activity.

How to Call

request_human_auth(
  capability: "microphone",
  instruction: "Please record audio: [describe what to say or capture].",
  uiTemplate: {
    allowAudioAttachment: true,
    requireArtifactOnApprove: true,
    title: "Audio Recording Needed",
    summary: "Record audio with your phone microphone."
  }
)

After You Receive the Artifact

The audio file is already pushed to Agent Phone Downloads. The result includes device_path=....

  1. Exit current screen state. The app may have a recording UI or microphone dialog open. Press keyevent KEYCODE_BACK to dismiss it.

  2. Re-navigate the app to its file attachment or audio upload option.

  3. Select the audio file from Downloads in the file picker (look for the openpocket-human-auth-* file).

  4. If the app needs speech-to-text rather than an audio file, and the human provided text in the decision note, type that text directly instead.

Tips

  • Audio files may be in WebM or OGG format. Most Android apps handle these natively.
  • Some voice message features (WhatsApp, Telegram) require holding a button — these may not work with file upload. In that case, consider Remote Takeover.