Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Telegram Channel Operator

ASecurity

Use when operating Telegram channels and code channels with approval-in-terminal policy, scheduled routines, and mandatory logging. Triggers on \"telegram channel\", \"code channel\", \"approval bypass\", \"channel routine\". Non-triggers: one-off DM reading or replying (use messages-ops). Outcome: channel runbook plus approval policy plus routine schedule plus append-only log.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgo

Works with

terminal

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill telegram-channel-operator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Telegram Channel Operator?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Telegram Channel Operator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-telegram-channel-operator/badge)](https://www.skillsdirectory.com/skills/majinmagros-telegram-channel-operator)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: telegram-channel-operator
description: "Use when operating Telegram channels and code channels with approval-in-terminal policy, scheduled routines, and mandatory logging. Triggers on \"telegram channel\", \"code channel\", \"approval bypass\", \"channel routine\". Non-triggers: one-off DM reading or replying (use messages-ops). Outcome: channel runbook plus approval policy plus routine schedule plus append-only log."
metadata:
  origin: ECC
---

# Telegram Channel Operator

Operate Telegram channels (broadcast) and code channels (agent posts via
bots on Telegram or Discord created with BotFather) with an explicit policy:
approve in the terminal by default, bypass only on a written allowlist,
run on routines, log everything.

## When To Activate

- The user wants an agent posting to a Telegram channel or group.
- The user wants code channels: agent output delivered to Telegram or Discord.
- There is a decision between approval-in-terminal and auto-send bypass.
- A channel needs scheduled routines (digests, alerts, build reports).

## Workflow

### 1. Create the bot and the channel topology

- Create the bot with BotFather; store the token outside the repo.
- Map topology: channel | purpose | audience | posting bot | admin.
- Broadcast channels: only the bot posts; discussion goes to a linked group.
- Code channels: one thread or topic per source (builds, alerts, agent notes).

### 2. Set the approval policy in writing

- Default: every outbound post needs terminal approval (show full text first).
- Bypass allowlist: named routine plus named channel plus content template.
- Anything off-template falls back to approval, no exceptions.
- Record the policy in the runbook; changes need human sign-off.

### 3. Define routines

- Each routine: trigger (cron or event) -> draft -> approval or bypass -> send.
- Morning digest, build status, and alert fan-out are separate routines.
- Quiet hours: queue non-urgent posts; only P1 alerts bypass quiet hours.

### 4. Send with idempotency

- One routine run -> one message; retries reuse the same dedupe key.
- Split messages over platform limits; keep part numbering (1/3, 2/3, 3/3).
- Never edit a sent alert to change its meaning; send a correction instead.

### 5. Log everything (mandatory)

- Append-only log per day: time | channel | routine | approval or bypass | message id | result.
- Missing log entry = failed run, even if the message was sent.
- Review the log weekly; shrink the bypass allowlist on any surprise.

## Anti-Patterns

- Bypass as default -> spam channel with no human in the loop.
- Token in the repo or chat transcript -> rotate immediately.
- Approval shown as summary instead of full text -> bait-and-switch posts.
- No log -> no way to audit what the agent sent.
- Broadcast and discussion in the same channel -> noise drowns signal.
- Routines without quiet hours -> 3am pings that train users to mute.

## Relations

## Exemplo

```text
Canal de builds: BotFather → topologia (canal | builds | time | bot | admin)
Política: terminal aprova tudo; bypass só p/ digest 9h no template fixo
Rotina: build → draft → approval/bypass → send idempotente; log append-only diário
Token fora do repo; DM avulsa é messages-ops, não aqui
```

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →