About

Imported from oimiragieo/agent-studio (.claude/skills/enable-telegram/SKILL.md). Install upstream with npx skills add oimiragieo/agent-studio --skill enable-telegram. Copyright stays with the author.

Enable Telegram

Name: enable-telegram
Author: oimiragieo

Step 1: Check if already running

Read .claude/context/runtime/channel-daemon.pid. If it exists and has content, verify the PID is alive using node -e "try { process.kill(PID, 0); console.log('ALIVE') } catch { console.log('DEAD') }". If ALIVE, tell the user the daemon is already running and show them status commands. Done — do NOT try to start again.

Step 2: Start the daemon

Spawn a developer agent:

subagent_type: developer
prompt: Run this command and report the output: node scripts/channels/telegram-ctl.cjs start

Step 3: Auto-detect voice pipeline

Read .env and check for ELEVENLABS_API_KEY or OPENAI_API_KEY. If either is set, tell the user:

"Voice pipeline auto-enabled — voice messages will be transcribed (Whisper) and responded to with audio (ElevenLabs/OpenAI TTS)."

If neither is set, just say:

"Text-only mode. Add ELEVENLABS_API_KEY or OPENAI_API_KEY to .env for voice message support."

Step 4: Confirm

Tell the user what's active:

Daemon status (running on port 3101)
Text messaging: active
Voice pipeline: active/inactive
Memory: loaded (N chats, N profiles)
Commands: type / in Telegram for the menu

Important

Do NOT use curl to check daemon health — it's blocked by security hooks
Use node -e with process.kill(pid, 0) or http.get for health checks
The PID file + kill(0) check is sufficient to confirm the daemon is alive

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/oimiragieo-agent-studio-enable-telegram/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

oimiragieo-agent-studio-enable-telegram.ocm.jsonjson

{
  "ocm": "1",
  "id": "oimiragieo-agent-studio-enable-telegram",
  "kind": "skill",
  "name": "enable-telegram",
  "description": "Start Telegram monitoring. Auto-enables voice pipeline if ElevenLabs or OpenAI TTS keys are detected.",
  "publisher": "oimiragieo",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "telegram",
      "monitoring",
      "background",
      "daemon",
      "voice",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Start Telegram monitoring. Auto-enables voice pipeline if ElevenLabs or OpenAI TTS keys are detected."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/oimiragieo/agent-studio",
      "path": ".claude/skills/enable-telegram/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/oimiragieo/agent-studio/blob/HEAD/.claude/skills/enable-telegram/SKILL.md",
      "key": "oimiragieo/agent-studio/.claude/skills/enable-telegram/SKILL.md"
    }
  },
  "instructions": "# Enable Telegram\n\n## Step 1: Check if already running\n\nRead `.claude/context/runtime/channel-daemon.pid`. If it exists and has content, verify the PID is alive using `node -e \"try { process.kill(PID, 0); console.log('ALIVE') } catch { console.log('DEAD') }\"`. If ALIVE, tell the user the daemon is already running and show them status commands. Done — do NOT try to start again.\n\n## Step 2: Start the daemon\n\nSpawn a developer agent:\n\n```\nsubagent_type: developer\nprompt: Run this command and report the output: node scripts/channels/telegram-ctl.cjs start\n```\n\n## Step 3: Auto-detect voice pipeline",
  "cost": {
    "context_tokens": 359
  }
}

Fetch it by URL: GET /api/v1/registry/oimiragieo-agent-studio-enable-telegram/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.