Telegram reporting protocol, kept as a historical reference: how a task report to the owner was shaped — success, error, question — with threading on the message being answered. Inactive by default: do not send automatic reports. Use when the user asks how such reporting worked or wants it revived.
Installs into .claude/skills of the current project.
Are you the author of Telegram Report?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/youlianvr-telegram-report)
---
name: telegram-report
description: >
Telegram reporting protocol, kept as a historical reference: how a task report
to the owner was shaped — success, error, question — with threading on the
message being answered. Inactive by default: do not send automatic reports.
Use when the user asks how such reporting worked or wants it revived.
---
> ⚠️ **Historical reference.** Automatic Telegram reports are off by default.
> Do not send a report after a task unless the owner asks for it.
# Telegram report — the shape of a task report
> ⚠️ **Automation is frequently banned.** A user-session client is a reserve, not a
> primary route: prefer the official Bot API or a manual send. Minimum automated
> messages, no mass mailings.
> The agent reports to the owner. One report per task, not a stream.
## How it worked
```
owner (Telegram) agent
│ │
│ "do X" │
│──────────────────────────────►│
│ │ Execute task
│ │
│ "✅ Done: X" │
│◄──────────────────────────────│
│ (via the sender script) │
```
## Intended behavior
**After each action:**
- ✅ Task done → what was done, which files
- ❌ Error → what went wrong, what was tried
- ❓ Need info → question, context, what is needed
## Templates
### Success
```
✅ Done: [task]
What: [what was done]
Files: [modified files]
Time: [duration]
```
### Error
```
❌ Failed: [task]
Error: [what went wrong]
Attempted: [what was tried]
Next: [proposed path]
```
### Question
```
❓ Question: [topic]
Context: [known info]
Need: [what is needed to proceed]
```
## How to send
Use a small sender script of your own that reads the bot token and the target chat
id from the root `.env`, and pass the message as its argument. Where the host has a
native messaging integration, use that instead of a script.
- Plain message: the sender script with one argument.
- Reply to a specific message: the sender script with the original `message_id`,
taken from the message being answered.
- If the send fails, check that the chat id in `.env` is the owner's chat: send one
test message and ask the owner to confirm it arrived before relying on it.
## Rules
- **Reply to the same message** — thread the answer onto the request.
- **Don't spam** — one report per task.
- **Be concrete** — what was done, which files, the result.
- **Error → immediately** — do not wait for the end of the session.
- **Long report → split** into several messages.