Pilot voice memo

Skill TeoSlayer/pilot-skills/skills/pilot-voice-memo

80+ agent skills for Pilot Protocol — communication, file transfer, trust, task routing, swarm coordination, and more

Install

npx -y skills add TeoSlayer/pilot-skills --skill pilot-voice-memo

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Send audio file messages between agents over the Pilot Protocol network. Use this skill when: 1. You need to send audio recordings or voice notes 2. You want to transmit audio data between agents 3. You need voice-based communication or audio file exchange Do NOT use this skill when: - You need text messages (use pilot-chat) - You need streaming audio (use pilot-connect) - You need video files (use pilot-send-file)

The file declares its own license as AGPL-3.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.7 KB, 509 tokens by cl100k_base, as published. Nobody here has run it

pilot-voice-memo

Send audio file messages between agents over the Pilot Protocol network. Enables voice-based communication through audio recordings, voice notes, and audio data exchange.

Commands

Record and send audio

# Record audio (example using arecord on Linux)
arecord -f cd -d 10 /tmp/voice-memo.wav

# Send the audio file
pilotctl --json send-file <hostname> /tmp/voice-memo.wav

Receive audio files

Check for received files:

pilotctl --json received

Clear received files

pilotctl --json received --clear

Workflow Example

Send and receive voice memos:

#!/bin/bash
# Sender: Record and send
RECIPIENT="agent-b"
MEMO_FILE="/tmp/project-update-$(date +%Y%m%d-%H%M%S).wav"

# Record 10 seconds of audio
arecord -f cd -d 10 "$MEMO_FILE" 2>/dev/null

# Send file
pilotctl --json send-file "$RECIPIENT" "$MEMO_FILE"

rm "$MEMO_FILE"
echo "Voice memo sent to $RECIPIENT"

# Receiver: Check and download
FILES=$(pilotctl --json received)
echo "Received files:"
echo "$FILES" | jq -r '.files[]? | "\(.filename) from \(.sender)"'

# Files are automatically saved to local directory
# Play audio (Linux: aplay, macOS: afplay)
# aplay received-file.wav 2>/dev/null || afplay received-file.wav 2>/dev/null

# Clear after processing
pilotctl --json received --clear

Audio Formats

WAV: Uncompressed, high quality, large files
MP3: Compressed, good quality, small files (recommended: 64kbps for voice)
Opus: Better quality, ~240KB per minute at 32kbps

Convert to efficient format:

ffmpeg -i input.wav -codec:a libmp3lame -b:a 64k output.mp3 -y

Dependencies

Requires pilot-protocol skill with running daemon, audio recording tool (arecord, sox, ffmpeg), audio playback tool (aplay, afplay, ffplay), and optional ffmpeg for conversion.