ClawHub

Telegram Group Chat

v1.0.0

Manages Telegram group chat replies by responding to @mentions, questions, name calls, technical topics, or priority users while preventing spam and bot loops.

⭐ 0· 70·1 current·1 all-time
byBox@zboxman
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the instructions: the SKILL.md defines when to reply or stay silent for Telegram group chats and does not request unrelated binaries, credentials, or services.
✓
Instruction Scope
All runtime instructions are limited to message-judgment logic (mentions, questions, bot flag, length, emoji, cooldown) and to local config entries (AGENTS.md). The skill does not instruct reading unrelated system files, accessing external endpoints, or sending data outside Telegram/OpenClaw.
✓
Install Mechanism
No install spec and no code files — this is instruction-only so nothing is written to disk or downloaded during install.
✓
Credentials
The skill declares no environment variables, credentials, or config paths as required. The suggested config entries (priority user IDs, name, group ID) are appropriate and minimal for the stated task.
✓
Persistence & Privilege
always is false, the skill is user-invocable and uses normal model invocation. It does not request permanent platform-wide presence or modify other skills' configs.
Assessment
This is an instruction-only reply-policy for Telegram group bots and appears internally consistent. Before enabling: (1) verify your OpenClaw gateway actually treats the literal string NO_REPLY as a silent ack so that the token won't be posted to chat if gateway behavior differs; (2) test the rules in a private/sandbox group to confirm cooldown and bot-loop protections work as intended; (3) configure priority-user IDs carefully (they will grant special-case replies); and (4) note the skill references a local OpenClaw docs path only as a convenience — it does not require you to expose other files or credentials. If you need stronger guarantees, ask the skill author for an example agent config and a minimal test harness to validate behavior in your environment.

Like a lobster shell, security has layers — review code before you run it.

latestvk974z1rnq09ge8qvn03rt6g99583kwya

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments