Index of every page on this site: llms.txt
All skills
laude-institute avatar

/telegram

@8db84fd
Run it yourself

Send and receive messages via the Telegram Bot API using curl

  • 1 file
  • 2.4 KB
  • Updated 6 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/laude-institute/headlong/telegram

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈18 tokens for metadata: the name and description. ≈598 when used: this file.

How this Skill uses context

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈72 characters, or 0.9%.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

telegram

Instructions

Use this skill to interact with Telegram via the Bot API. All operations use curl against https://api.telegram.org/bot<TOKEN>/....

Prerequisites

The environment variable TELEGRAM_BOT_TOKEN must be set to a valid Telegram Bot API token (obtained from @BotFather). The variable TELEGRAM_CHAT_ID should be set to the target chat/group/channel ID for sending messages.

Sending a message

curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \
  -d chat_id="${TELEGRAM_CHAT_ID}" \
  -d text="Hello from shellm" \
  -d parse_mode=Markdown

Sending a file/document

curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendDocument" \
  -F chat_id="${TELEGRAM_CHAT_ID}" \
  -F document=@/path/to/file.txt

Getting updates (receiving messages)

Poll for new messages using getUpdates. Use offset to acknowledge previously seen updates and only receive new ones.

# Get latest updates
curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getUpdates" \
  -d limit=10 \
  -d timeout=0

# Acknowledge up to update_id 12345 and get only newer updates
curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getUpdates" \
  -d offset=12346 \
  -d limit=10

Parse the JSON response with jq:

curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getUpdates" \
  | jq -r '.result[] | "\(.update_id) \(.message.from.username): \(.message.text)"'

Replying to a specific message

curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \
  -d chat_id="${TELEGRAM_CHAT_ID}" \
  -d text="Reply text" \
  -d reply_to_message_id=MESSAGE_ID

Getting chat info

curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getChat" \
  -d chat_id="${TELEGRAM_CHAT_ID}" | jq .

Error handling

All Telegram API responses return JSON with an ok field. Check it:

response=$(curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \
  -d chat_id="${TELEGRAM_CHAT_ID}" \
  -d text="test")
if [ "$(echo "$response" | jq -r '.ok')" != "true" ]; then
  echo "Telegram API error: $(echo "$response" | jq -r '.description')" >&2
fi

Rate limits

Telegram limits bots to ~30 messages/second to different chats, and ~20 messages/minute to the same chat. Add short delays between batch sends.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 8db84fd. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 6 months ago

README badge

README badge for laude-institute/headlong/telegram