Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
["Always call isChannelRunning() before startChannel() to avoid duplicate sessions","Track PID via terminal-tracker after every start","Run health check within 10 seconds of start to confirm session is live","Use CHANNEL_AUTO_START=true in .env only for supervised production environments"]
error_handling
strict
streaming
not-applicable
source
builtin
trust_score
100
provenance_sha
76303e7de92f80e4
Channel Management
Overview
This skill manages the full lifecycle of a Claude Code --channels session (Telegram bot, Discord bot, or any plugin-based channel integration). It wraps the CLI tools at .claude/tools/cli/channel-manager.cjs and .claude/tools/cli/terminal-tracker.cjs and provides a repeatable, observable workflow for:
Starting a channel session in a new Windows Terminal tab
Stopping a running channel session cleanly
Checking status and PID liveness
Health-checking the session via the terminal tracker
When to Invoke
Skill({ skill: 'channel-management' });
Invoke when:
CHANNEL_AUTO_START=true is set and session startup must be verified on agent boot
A user or cron job requests manual channel lifecycle management
A channel session appears to have crashed and needs restart
Diagnosing why Telegram/Discord messages are not being received
Inspecting or pruning orphaned channel PID entries
The Iron Law
NEVER start a channel session without checking isChannelRunning() first.
NEVER assume a tracked PID is alive without calling isPidAlive(pid).
NEVER restart after a crash without calling killOrphaned() to prune stale entries.
Workflow
Step 0: Read Memory Context (MANDATORY)
Before executing any lifecycle action, read memory to check for known issues:
Expected output:{"ok":true,"pid":12345,"reason":"started"} on success, or {"ok":false,"pid":null,"reason":"TELEGRAM_BOT_TOKEN not set — skipped"} when token missing.
Verify:ok: true in JSON output. Exit code 0.
Step 3: Track PID
After a successful start, confirm the PID is registered in the tracker: