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 Catch Up

ASecurity

Summarize what the user missed in Telegram — unread chats, who is waiting for a reply, and what needs a decision. Use when the user asks what they missed, wants a digest of their chats, or asks to catch up on a specific chat or time period.

4 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsreact

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add mcp-telegram/mcp-telegram-cloud --skill telegram-catch-up --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Telegram Catch Up?

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

Security grade badge for Telegram Catch Up
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mcp-telegram-telegram-catch-up/badge)](https://www.skillsdirectory.com/skills/mcp-telegram-telegram-catch-up)

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

Download Zip
Files
SKILL.md
---
name: telegram-catch-up
description: Summarize what the user missed in Telegram — unread chats, who is waiting for a reply, and what needs a decision. Use when the user asks what they missed, wants a digest of their chats, or asks to catch up on a specific chat or time period.
---

Use this skill when the user wants an overview of Telegram activity rather than
one specific message. Typical requests: "what did I miss", "catch me up",
"summarize my unread", "anything important in the work group today".

## Gather

1. Call `telegram-get-unread` first. It returns the dialogs with unread
   counters and is the cheapest entry point.
2. If the user named a chat or a folder, resolve it with
   `telegram-search-chats` and work only inside that scope.
3. Read the actual messages with `telegram-read-messages` for each dialog you
   will report on. Never summarize from the dialog preview alone — the preview
   holds one truncated line.
4. For forum-style groups, list topics with `telegram-list-topics` and read
   each active topic with `telegram-read-topic-messages`. Reporting a forum
   group as a single stream loses the structure the user needs.
5. Stop gathering after 10 dialogs. If more are unread, report the busiest 10
   and state how many were left out.

## Report

Group the output by chat, most active first. For each chat give:

- The chat name and the number of unread messages.
- What happened, in one to three sentences.
- Who is waiting for the user: quote the sender and the request.
- A link from `telegram-get-message-link` for anything that needs an answer or
  a decision, so the user can jump straight there.

Finish with a short "needs your reply" list across all chats. If nothing needs
a reply, say so plainly instead of padding the summary.

## Rules

- Report only messages you actually fetched. Never infer content from a chat
  name, an unread count, or a truncated preview.
- Keep the sender's own words for requests and decisions. Paraphrase the
  surrounding chatter, not the ask.
- Do not call `telegram-mark-as-read`. Reading a digest must not clear the
  user's unread state; do it only if the user asks explicitly.
- Do not send, edit, react, or delete anything in this workflow. If the user
  wants to answer, hand over to the `telegram-reply` skill.
- Media is reported as a placeholder with its type and file name. Call
  `telegram-download-media` only when the user asks for the content, and leave
  `full` unset so the cheap thumbnail is returned first.
- If the account is not connected, `telegram-status` explains how to link it.
  Report that instead of guessing.

Attribution

mcp-telegrammcp-telegram
View sourceMore from mcp-telegram →
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 →