interactive-bot

Gmail Commander Telegram bot — slash commands for email access + AI-powered free-text routing.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "interactive-bot" with this command: npx skills add terrylica/cc-skills/terrylica-cc-skills-interactive-bot

Interactive Bot

Gmail Commander Telegram bot — slash commands for email access + AI-powered free-text routing.

Mandatory Preflight

Step 1: Check Bot Script Exists

ls -la "$HOME/.claude/plugins/marketplaces/cc-skills/plugins/gmail-commander/scripts/bot.ts" 2>/dev/null || echo "SCRIPT_NOT_FOUND"

Step 2: Verify Environment

echo "TELEGRAM_BOT_TOKEN: ${TELEGRAM_BOT_TOKEN:+SET}" echo "TELEGRAM_CHAT_ID: ${TELEGRAM_CHAT_ID:-NOT_SET}" echo "GMAIL_OP_UUID: ${GMAIL_OP_UUID:-NOT_SET}" echo "HAIKU_MODEL: ${HAIKU_MODEL:-NOT_SET}"

Bot Commands (Sidebar Menu)

Command Description

/inbox Show recent inbox emails

/search Search emails (Gmail query syntax)

/read Read email by ID

/compose Compose a new email

/reply Reply to an email

/drafts List draft emails

/digest Run email digest now

/status Bot status and stats

/help Show all commands

Two-Tier Command System

Tier 1 — Deterministic: Slash commands call Gmail CLI directly.

Tier 2 — Intelligent: Free-text messages route through Agent SDK (Haiku) with 4 Gmail MCP tools (list, search, read, draft).

Safety Controls

  • Mutex: 1 agent query at a time

  • Timeout: 2-minute maximum per query

  • Circuit Breaker: 3 failures in a row disables agent for 10 minutes

  • Anti-contamination: Skill contamination detection on all agent responses

  • Auth Guard: Only responds to authorized TELEGRAM_CHAT_ID

Running Manually

cd ~/own/amonic && bun run "$HOME/.claude/plugins/marketplaces/cc-skills/plugins/gmail-commander/scripts/bot.ts"

References

  • command-reference.md — All commands with examples

  • compose-flow.md — Multi-step compose/reply state machine

  • display-patterns.md — Email rendering rules

Post-Change Checklist

  • YAML frontmatter valid (no colons in description)

  • Trigger keywords current

  • Path patterns use $HOME not hardcoded paths

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

chezmoi-workflows

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

multi-agent-e2e-validation

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

doppler-workflows

No summary provided by upstream source.

Repository SourceNeeds Review