一键在 Manus 中运行任何 Skill

telegram-kit

星标2

分支1

更新时间2026年3月28日 07:57

Telegram group/forum provisioning and management. USE WHEN: inviting bots to a group, promoting bots to admin, creating groups/forums, creating topics, sending messages as user or bot, checking bot permissions. DON'T use raw curl/Telegram API for these — this skill wraps safe Telethon (user) and Bot API (bot) scripts. Also use when: you need to add/remove/manage members in a Telegram group where you have admin rights. Triggers on: invite bot, add bot to group, promote bot, create topic, telegram group setup, forum setup. Safety: user API (MTProto) = high-risk, bot API = low-risk, never mix.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

RadonX

RadonX/openclaw-agent-claw-config

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

telegram-kit

Safety invariants (do not violate)

Hard split: user = MTProto human account (high-risk). bot = Bot API token (lower-risk). Never mix.
User API rules: never run unattended; never schedule; expect login/2FA/code prompts; minimize write actions.
Secrets: do not store credentials inside this skill. Read from ~/.openclaw/.env and ~/.openclaw/openclaw.json only.

Interface (CLI-like subcommands)

telegram-kit user … → read references/USER.md
telegram-kit bot … → read references/BOT.md
End-to-end flow → read references/FLOWS.md
Failures / gotchas → read references/TROUBLESHOOT.md

Implementation notes

Scripts live in scripts/:
- MTProto (Telethon): scripts/tg_user.py
- Bot API (stdlib urllib): scripts/tg_bot.py

When executing scripts, run them directly (do not copy/paste code into chat).

同仓库更多 Skills

同仓库

upgrade-guardian

RadonX/openclaw-agent-claw-config

A cognitive protocol for safely managing and auditing OpenClaw application upgrades. Analyzes configuration-level risks (schema, defaults) and runtime-level behavioral shifts (routing, sessions, streaming) using semantic changelog analysis to prevent silent breaking changes.

2026-03-222

restore-session

RadonX/openclaw-agent-claw-config

Restore or migrate OpenClaw session history from a source session to a target session. Use when recovering lost context, migrating sessions after Telegram topic migration, or transferring conversation history between sessions. WARNING This is a HIGH-RISK operation that modifies session files directly.

2026-03-212

config-workflow

RadonX/openclaw-agent-claw-config

OpenClaw configuration management safety protocol and change reporting. Use when modifying OpenClaw configuration that affects runtime behavior: (1) editing openclaw.json (bindings, channels, agents), (2) changing workspace prompt files (SOUL.md, AGENTS.md, IDENTITY.md), (3) restarting gateway or agents, (4) installing/removing skills or tools, or (5) any action that may impact message routing or agent behavior.

2026-03-122

claw-config-skill-creator

RadonX/openclaw-agent-claw-config

Create or review OpenClaw skills for the claw-config agent. Default mode drafts a new skill (proposal-only) with docs-first diagnosis, change control, and claw-config safety constraints; review mode audits an existing skill for correctness and safety.

2026-02-242

bindings-simplifier

RadonX/openclaw-agent-claw-config

Safely simplify OpenClaw `bindings` (routing rules) while preserving behavior. Use when bindings are redundant (per-topic spam), when accounts are exclusive to a single agent, or when you need to reduce binding count without breaking routing/activation.

2026-02-232

proxy-post

RadonX/openclaw-agent-claw-config

Cross-group posting via proxy bot. Route messages from a high-privileged agent (main) to a low-privileged bot account in another group/channel. Use message tool with accountId to specify which bot sends. Covers warm-up strategies for topics/threads and troubleshooting why proxy messages don't appear.

2026-02-122

name

telegram-kit

description

telegram-kit

Safety invariants (do not violate)

Hard split: user = MTProto human account (high-risk). bot = Bot API token (lower-risk). Never mix.
User API rules: never run unattended; never schedule; expect login/2FA/code prompts; minimize write actions.
Secrets: do not store credentials inside this skill. Read from ~/.openclaw/.env and ~/.openclaw/openclaw.json only.

Interface (CLI-like subcommands)

telegram-kit user … → read references/USER.md
telegram-kit bot … → read references/BOT.md
End-to-end flow → read references/FLOWS.md
Failures / gotchas → read references/TROUBLESHOOT.md

Implementation notes

Scripts live in scripts/:
- MTProto (Telethon): scripts/tg_user.py
- Bot API (stdlib urllib): scripts/tg_bot.py

When executing scripts, run them directly (do not copy/paste code into chat).