telegram-inbound-run

$npx mdskill add aAAaqwq/AGI-Super-Team/telegram-inbound-run

Run Telegram Inbound Agent to process replies and update CRM.

  • Processes recent Telegram messages and updates lead statuses.
  • Integrates with Telegram API, Claude Haiku, and Git.
  • Classifies replies using AI or rule-based logic.
  • Logs activity and sends notifications to Saved Messages.

SKILL.md

.github/skills/telegram-inbound-runView on GitHub ↗
---
name: telegram-inbound-run
description: Automatic inbound Telegram message processing
---
# Telegram Inbound Agent - Manual Run

> Skill for manually triggering Telegram Inbound Reply Monitor Agent

## When to use

- "check Telegram for replies"
- "run Telegram inbound agent"
- "see if anyone replied on Telegram"
- "check Telegram replies"

## What it does

Agent:
1. Extracts messages from Telegram (last 24 hours)
2. Filters contacts that we messaged (outbound)
3. Classifies replies via Claude Haiku (POSITIVE/NEGATIVE/QUESTION/etc)
4. Logs activity in CRM
5. Updates lead statuses
6. Sends notification to Saved Messages
7. Creates git commit

## How to run

### Dry run (no CRM changes)

```bash
cd $AGENTS_PATH/telegram-inbound
python3 telegram_inbound_agent.py --dry-run --since 24h
```

### Full run

```bash
cd $AGENTS_PATH/telegram-inbound
python3 telegram_inbound_agent.py --since 24h
```

### Notification test

```bash
cd $AGENTS_PATH/telegram-inbound
python3 telegram_inbound_agent.py --notify-test
```

### Without AI (rule-based classification)

```bash
cd $AGENTS_PATH/telegram-inbound
python3 telegram_inbound_agent.py --no-ai --since 24h
```

### Larger time window

```bash
# Last 48 hours
python3 telegram_inbound_agent.py --since 48h

# Last 7 days
python3 telegram_inbound_agent.py --since 7d

# Last 14 days
python3 telegram_inbound_agent.py --since 14d
```

## Output

### Stdout (summary)
```
📬 Telegram Inbound: 2026-02-12 09:00

5 new replies (3 positive, 1 questions)

✅ POSITIVE (3):
  • John Doe: Interested in labeling service
  ...
```

### Files
- **Summary**: `$AGENTS_PATH/logs/telegram-inbound-{date}.md`
- **Run log**: `$AGENTS_PATH/logs/telegram_agent_log.json`
- **Errors**: `$AGENTS_PATH/logs/errors/telegram-inbound-{date}.log`

### CRM updates
- **Activities**: added to `sales/crm/activities.csv`
- **Leads**: updated statuses in `sales/crm/relationships/leads.csv`
- **Git commit**: auto-commit with change description

## Flags

| Flag | Description |
|------|-------------|
| `--dry-run` | Classification only, no CRM updates or notifications |
| `--no-ai` | Rule-based classification (without Claude) |
| `--since <duration>` | Time window: 24h, 48h, 7d, 14d |
| `--notify-test` | Test Telegram notification |

## Scheduled Runs

Agent runs automatically 3 times a day:
- **09:00** - morning check
- **13:00** - midday check
- **17:00** - evening check

Via launchd: `com.yourcompany.telegram-inbound`

## Troubleshooting

### "No actionable contacts found"

```bash
# Check activities.csv for outbound Telegram
grep telegram $CRM_PATH/activities.csv | grep outbound

# Check people.csv for telegram usernames
grep telegram_username $CRM_PATH/contacts/people.csv
```

### "Telegram authorization failed"

```bash
# Re-auth
cd $TG_TOOLS_PATH
python3 tools/tg_auth.py
```

### View recent summary

```bash
cat $AGENTS_PATH/logs/telegram-inbound-$(date +%Y-%m-%d).md
```

## Related skills

- `telegram-send` - sending outbound messages
- `change-review` - review CRM changes before commit
- `update-lead` - manual CRM update
- `log-activity` - manual activity logging

More from aAAaqwq/AGI-Super-Team

SkillDescription
a-fund-monitor监控 A 股基金实时估值与盘后净值,自动判断交易日并生成提醒或分析。
add-leadAdd company/person/relationship to CRM
ads-agentAI-агент для управления Facebook рекламой. Вызывай для анализа, оптимизации, создания кампаний и отчётов.
afrexai-compliance-auditRun internal compliance audits against major governance and security
afrexai-personal-financeComplete personal finance system — budgeting, debt payoff, investing, tax optimization, net worth tracking, and financial independence planning. Use when managing money, building wealth, paying off debt, planning retirement, or optimizing taxes. Zero dependencies.
after-salesUse when managing post-purchase experience, building customer loyalty, or increasing repeat purchases
agent-contactsAI agent contacts — add, list, remove MCP contacts. Use when someone gives an agent URL, or when you need to view/remove contacts.
agent-model-switcher批量查看和切换子 agent 的模型配置,用于统一调整多 agent 的 provider/model 设置。
agent-patternsFormat SPAWN REQUEST messages to launch parallel agents, generate structured agent status reports, and define communication protocols within the sprint system. Use when the user needs to coordinate multiple agents, format spawn requests, produce agent reports, or establish inter-agent communication patterns.
agent-task-confirmUse when confirming whether a dispatched agent task was actually received, activated, and progressing after sessions_send or other task handoff actions.