
tg-bot-binding
Telegram bot binding: create the bot, connect to Starchild, verify, troubleshoot. Two ways to bind: (1) scan-to-create (recommended, auto-bind) or (2) manual BotFather + token + verify. Use when setting up Telegram delivery (e.g. add my TG bot, bot binding code, fix "telegram not pushing", whitelist a TG username).
- Installs
- 2.2K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/starchild-ai-agent/official-skills --skill tg-bot-binding- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads tg-bot-binding automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Telegram Bot Binding Guide
When the user asks about Telegram Bot binding, setup, connection, verification, or any related topic, provide them with the following guide. Always respond in the user's language.
Overview
Starchild lets you connect your own Telegram Bot so you can chat with your AI agent directly in Telegram. There are two ways to bind a bot:
- Scan to create bot (Recommended) — scan a QR code, confirm creation in Telegram, and Starchild completes the binding automatically. No token to copy, no verification code.
- Manual binding — create a bot via @BotFather, paste the token in the Dashboard, then verify ownership with a code.
Prefer the scan-to-create method whenever possible — it's faster and has fewer steps.
Method A: Scan to Create Bot (Recommended)
This method creates a new bot for you and binds it in a single flow — no token and no verification code.
Step 1: Open the Telegram Bot section
- Go to the Starchild Dashboard (web interface).
- Click your avatar at the bottom-left corner of the page.
- In the Account Management popup, find the Telegram Bot section.
- Click "Scan to create bot".
Step 2: Scan the QR code
A QR code appears together with a link. Do either of the following:
- Scan the QR code with your Telegram app (camera → scan), or
- Click "Open in Telegram" to jump straight to the creation page.
Step 3: Confirm creation in Telegram
Telegram opens a bot-creation page. Confirm that you want to create the bot.
Step 4: Done!
Starchild detects the new bot and completes the binding automatically. The bot goes straight to "running" — no verification code needed. Send /start in Telegram to begin chatting with your AI agent.
Note: A bot created this way is managed by Starchild's bot infrastructure. To remove it later, use the Delete Bot action in the Dashboard (not @BotFather).
Method B: Manual Binding (BotFather + Token)
Use this flow if you prefer to create and own the bot token yourself via @BotFather.
Step 1: Create a Telegram Bot via BotFather
- Open Telegram and search for @BotFather (the official Telegram bot for creating bots).
- Send
/newbotto BotFather. - Follow the prompts:
- Enter a display name for your bot (e.g., "My Starchild Agent").
- Enter a username for your bot (must end in
bot, e.g.,my_starchild_bot).
- BotFather will reply with your Bot Token — a string like
123456789:ABCdefGHIjklMNOpqrsTUVwxyz. Copy this token and keep it safe. Do not share it publicly.
Step 2: Add the Bot Token in Starchild Dashboard
- Go to the Starchild Dashboard (web interface).
- Click your avatar at the bottom-left corner of the page.
- In the Account Management popup, find the Telegram Bot section.
- Paste your Bot Token and submit.
- The system will:
- Verify the token with Telegram's API (calling
getMe). - Generate a 6-digit verification code (valid for 5 minutes).
- Set the bot status to "pending".
- Verify the token with Telegram's API (calling
- You will see the verification code displayed on the dashboard. Copy this code.
Step 3: Verify Bot Ownership in Telegram
You have two ways to verify:
Option A: Deep Link (Recommended)
Click the verification link provided on the dashboard. It will open your bot in Telegram and automatically submit the verification code. The link format is:
https://t.me/<your_bot_username>?start=verify_<CODE>
Option B: Manual Verification
- Open your bot in Telegram (search for
@<your_bot_username>). - Send
/start— the bot will prompt you to enter the verification code. - Type the 6-digit code and send it.
Step 4: Done!
Once verified, the bot status changes to "active" briefly, then automatically transitions to "running" — meaning your bot is live and ready. You can start chatting with your AI agent through Telegram. Send /start to see the welcome message and available commands.
Bot Status Reference
| Status | Meaning |
|---|---|
pending | Bot token added, awaiting ownership verification (manual flow only) |
active | Ownership verified, transitioning to running |
running | Bot is live and ready to use |
deleted | Bot has been removed by the user |
Troubleshooting
"Verification code expired"
The verification code is valid for 5 minutes. If it expires:
- Go back to the Dashboard and click "Refresh Code" to generate a new one.
- Then verify again in Telegram with the new code.
"Too many failed attempts"
After 5 incorrect attempts, the verification code is invalidated for security:
- Go to the Dashboard, delete the bot, and add it again to get a fresh code.
"Bot token is already registered by another user"
Each Bot Token can only be bound to one Starchild account. If you see this error:
- Make sure you're using a new, unused bot token.
- If you previously used this token, the old binding may still exist. Create a new bot via @BotFather.
"You already have an active bot"
Each account can only have one active bot at a time:
- To switch bots, first delete the current bot from the Dashboard, then add the new one.
- Note: After deleting a bot, there is a 1-hour cooldown before you can add a new one.
"Cooldown active — Please wait before adding a new bot"
After deleting a bot, you must wait 1 hour before adding a new one. The dashboard will show the cooldown expiration time.
"Too many attempts. Please wait a moment and try again."
The scan-to-create flow is rate-limited. If you see this message, wait a short while before clicking "Scan to create bot" again.
"Authorization expired. Please try again."
The scan-to-create QR code / link is only valid for a limited time. If it expires:
- Cancel the current pairing, then click "Scan to create bot" again to get a fresh QR code.
Bot is not responding in Telegram
- Check the bot status on the Dashboard — it should be "running".
- If the status is "pending", complete the verification step (manual flow).
- Try sending
/startto the bot. - If the issue persists, try deleting and re-adding the bot (after the 1-hour cooldown).
Quick Reference
| Action | Where |
|---|---|
| Create + bind a bot (fastest) | Starchild Dashboard → bottom-left avatar → Account Management → Telegram Bot → "Scan to create bot" → scan QR code → confirm in Telegram |
| Create a new Telegram bot manually | Telegram → @BotFather → /newbot |
| Add bot token | Starchild Dashboard → bottom-left avatar → Account Management → Telegram Bot |
| Verify ownership | Telegram → Your bot → enter verification code |
| Refresh verification code | Starchild Dashboard → Account Management → Telegram Bot → "Refresh Code" |
| Delete bot | Starchild Dashboard → Account Management → Telegram Bot → "Delete Bot" |
| Check bot status | Starchild Dashboard → Account Management → Telegram Bot |
Important Notes
- Recommended flow: Use "Scan to create bot" — it creates and binds the bot automatically with no token or verification code.
- Scan-created bots are managed by Starchild: They are created through Starchild's bot infrastructure. Delete them from the Dashboard, not from @BotFather.
- Security: In the manual flow, your Bot Token is encrypted (AES-256) before storage. It is never exposed in API responses.
- One bot per account: You can only have one active Telegram bot at a time.
- Cooldown: After deleting a bot, wait 1 hour before adding a new one.
- Rate limits: Adding a bot and refreshing codes are limited to 3 requests per minute.
- Verification attempts: You have 5 attempts to enter the correct code before it's invalidated.
FAQ
What does the tg-bot-binding skill do?
Telegram bot binding: create the bot, connect to Starchild, verify, troubleshoot. Two ways to bind: (1) scan-to-create (recommended, auto-bind) or (2) manual BotFather + token + verify. Use when setting up Telegram delivery (e.g. add my TG bot, bot binding code, fix "telegram not pushing", whitelist a TG username).
How do I install tg-bot-binding?
Run npx skills add https://github.com/starchild-ai-agent/official-skills --skill tg-bot-binding in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/tg-bot-binding/ (personal) or .claude/skills/tg-bot-binding/ (project).
Which AI agents can use tg-bot-binding?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is tg-bot-binding safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains tg-bot-binding?
It is published by starchild-ai-agent in starchild-ai-agent/official-skills. It has 2,158 recorded installs.
More from starchild-ai-agent/official-skills
coinglass
starchild-ai-agent/official-skills
Crypto derivatives data: funding rates, open interest, liquidations, long/short ratios. Use when researching perp markets or comparing ETF flows (e.g. BTC funding, ETH OI). NOTE: platform API key is Startup tier — liquidation heatmap, coins-markets detail, liquidation order book and Hyperliquid positions require higher plans (see Plan Tiers).
wallet
starchild-ai-agent/official-skills
Multi-chain wallet: EVM and Solana balances, transfers, signing, and policy. Use when checking balances, sending tokens, signing typed data, or proposing a wallet policy (e.g. send 10 USDC on Base, sign EIP-712, Solana balance).
hyperliquid
starchild-ai-agent/official-skills
Trade perp futures, spot, and RWA on Hyperliquid DEX with up to asset max leverage. Use when placing perp or spot orders, setting TP/SL, or moving funds on Hyperliquid (e.g. long BTC 5x, sell ETH, deposit USDC, set stop).
coingecko
starchild-ai-agent/official-skills
Crypto spot prices, OHLC charts, market discovery, and global stats. Use when looking up coin prices, market caps, trending coins, sector rankings, or comparing tokens (e.g. BTC price, ETH chart, top gainers).
starchild-ai-agent/official-skills
Twitter/X data: fetch tweets, search, user profiles, followers, replies, trends. Use for any x.com or twitter.com URL or lookup (e.g. summarize this tweet, recent posts by @vitalikbuterin, search $SOL minfaves:50).
skill-creator
starchild-ai-agent/official-skills
Scaffold new skills with valid frontmatter, directory layout, and a starter SKILL.md. Use when building a new reusable workflow or wrapping a new API (e.g. create a kalshi skill, scaffold an API helper, start a charting skill).
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available