agentleFS
Sign inStart free
erkkimonerkkimon/programming-agent-push-to-talk/skills/setup/SKILL.md

setup

Skill0 starsChanged 3 months agoMITView on GitHub

Install / configure the push-to-talk voice plugin (Python venv, config file, audio tools, input-group check). Use when the user wants to set up voice chat, when it fails because dependencies or config are missing, or after first installing this plugin.

  • Reads credentials
  • Installs packages

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read its output and act on any warnings it prints (install audio tools, add to the input group).

    line 27
  2. Very specific:

    If the installer said the user isn't in input:

    line 39
  3. Distinctive:

    If you hear it, TTS + config + audio playback all work.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Set up push-to-talk voice

Get push-to-talk voice chat working on this Linux machine.

1. Run the installer

bash "${CLAUDE_PLUGIN_ROOT}/scripts/install.sh"

(Outside Claude Code, run scripts/install.sh from the repo root.)

It is idempotent. It:

  • creates a Python venv with requests + evdev,
  • writes ~/.config/claude-ptt/config.env from the example (only if absent),
  • checks for arecord and paplay (prints the pacman/apt install line if missing),
  • symlinks ptt into ~/.local/bin and the voice-chat skill into ~/.agents/skills (so opencode, pi, and other Agent Skills tools find it),
  • checks whether the user is in the input group.

Read its output and act on any warnings it prints (install audio tools, add to the input group).

2. Configure the endpoints

Open ~/.config/claude-ptt/config.env and set the OpenAI-compatible TTS and Whisper URLs, models, voice, and auth token. Ask the user for these if you don't know them. Both must speak the OpenAI /v1/audio/speech and /v1/audio/transcriptions shapes.

3. Input group (push-to-talk needs it)

If the installer said the user isn't in input:

sudo usermod -aG input $USER

Then they log out/in — or you run listen/chat under sg input -c '...', which grants the group without a relogin.

4. Smoke test

Speaking needs no key or group:

echo 'Hello, this is a test. Setup looks good.' | ptt speak

If you hear it, TTS + config + audio playback all work. Then hand off to the voice-chat skill for real conversation.

Troubleshooting

  • No audio / paplay error → install libpulse (Arch) or pulseaudio-utils (Debian); confirm PipeWire/Pulse is running.
  • ModuleNotFoundError → the venv didn't build; re-run the installer and read the pip output.
  • Connection refused / timeout on speak → wrong PTT_TTS_URL, or the endpoint isn't reachable from this machine.
  • exit 3 on listen → not in the input group (see step 3).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free