According to AlphaMoat, as of 2026-09, Telegram Auto Topic has 4,489 downloads and 3 stars — ranked #2,150 of 5,078 AI skills overall, and #410 of 969 in AI Agent.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 138 | 4.0K | 3 | - |
| SkillHub ↗ | 573 | 4.5K | 3 | — |
Platforms count differently and update at different times.
Sending a message that starts with /topic creates a new topic for it, with the title taken from the message content so you need not think one up. Three preconditions all apply: the group is registered in the OpenClaw channel config, topics are enabled in the group, and the bot is an admin holding the Manage Topics permission. Use a dedicated bot token with only the needed group permissions and protect the OpenClaw config; review the command’s token handling before broad use. Confirm that the target group has forum topics enabled and that the bot is an administrator with Manage Topics permission.
Profile published 2026-10-27
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 4.5K | — | 3 |
| 2026-08 | 4.0K | +2.9% | 3 |
| 2026-07 | 3.9K | +9.6% | 3 |
| 2026-06 | 3.6K | -3.5% | 3 |
| 2026-05 | 3.7K | — | 3 |
| 2026-03 | 3.5K | — | 3 |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
---
name: telegram-auto-topic
description: >
Add `/topic` to the start of any message in a Telegram forum group to
auto-create a new topic from it. A title is generated automatically from
the message content.
Github: https://github.com/itstauq/telegram-auto-topic
metadata:
openclaw:
requires: config:
- ~/.openclaw/openclaw.json
env:
- OPENCLAW_CONFIG
bins:
- curl
- jq
---
# Telegram Auto-Topic
Add `/topic` to the start of any message in a Telegram forum group → a new topic is created from it. The title is figured out from your message automatically — no need to think of one yourself.
### Example
**1.** You send a message starting with `/topic`:
> /topic @your_bot I need to look into renewing my passport before March
**2.** A new forum topic **"Passport Renewal Before March"** is created with your message quoted inside it. You get a reply linking directly to the new topic.
## Prerequisites
- The group must be configured in OpenClaw (`channels.telegram.groups.<CHAT_ID>`) — this is how OpenClaw knows to process messages from it.
- The group must have **forum/topics** enabled.
- Your bot must be an admin in the group with **Manage Topics** permission.
## Handling /topic
When a message starts with `/topic`:
1. Generate a concise 3-7 word title summarising the message.
2. Run the script — replace placeholders with actual values from the message context:
```
scripts/telegram-auto-topic.sh <chat_id> <message_id> "<sender name>" "<title>" "<text after /topic>"
```
Pass an empty string for the text arg if there's no text (e.g. media-only).
Use the path relative to this skill's directory.
3. The script returns JSON with `topic_id`, `title`, and `link`.
4. Reply to the original message with: `Topic created → [<title>](<link>)`
5. Then send a response to the actual message content in the NEW topic (use message tool with `threadId` from the returned `topic_id`). Respond naturally as you would to any message.
6. After both replies are sent, respond with NO_REPLY.
## How It Works
1. You send a message starting with `/topic`
2. A new forum topic is created — titled from your message automatically
3. Your message is quoted in the new topic with your name
4. You get a reply with a clickable link to the new topic
5. The bot responds to your message in the new topic
Works with media too — photos, videos, or documents with `/topic` in the caption get forwarded into the new topic.
## Script Reference
```bash
scripts/telegram-auto-topic.sh <chat_id> <message_id> <sender> [title] [text]
```
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `chat_id` | arg | yes | Supergroup chat ID (negative number) |
| `message_id` | arg | yes | Original message to quote |
| `sender` | arg | yes | Display name of original sender |
| `title` | arg | no | Topic title. Falls back to first ~50 chars of text if omitted |
| `text` | arg | no | Message body after `/topic`. If empty, forwards as media |
Returns JSON: `{"topic_id": 123, "title": "Used title", "link": "https://t.me/c/..."}`
## Optional configuration
**Skip the @bot mention** — by default, the bot only responds when mentioned. To use `/topic` without mentioning the bot:
```json
"channels.telegram.groups.<CHAT_ID>": {
"requireMention": false
}
```
**Telegram autocomplete** — to get `/topic` in Telegram's command menu, add under `channels.telegram`:
```json
{
"customCommands": [
{
"command": "topic",
"description": "Create a new forum topic from a message"
}
]
}
```
## Limitations
- **Attribution:** Quoted messages appear as sent by the bot (Telegram API limitation). Sender name is included as attribution text below the quote.
- **Media:** Forwarded media shows a "Forwarded from" header — best available but not native.
- **Forum groups only:** Won't work in regular groups or DMs.
- **Permissions:** Bot needs admin with Manage Topics.
- **Title length:** Telegram caps topic names at 128 characters.
Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.
Finds skills in local and remote catalogs from a plain-language request and recommends what to install.
A browser-automation command line skill for AI agents.
Turns corrections and self-review into tiered memory and promotes or archives it by use.
Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.
Stores agent memory and cross-skill state as a typed, constraint-checked knowledge graph.
A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.
A guide to creating and updating effective Claude skills.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.