KS
Killer-Skills

telegram-watch-dev — Categories.community

v1.0.0
GitHub

About this Skill

Ideal for Social Media Monitoring Agents requiring advanced Telegram data capture and analysis capabilities powered by Telethon Fully local Telegram watcher powered by Telethon — monitor specific users in a target group/channel, capture messages/media into SQLite, and push periodic HTML reports back to a control chat.

# Core Topics

o1xhack o1xhack
[7]
[0]
Updated: 2/13/2026

Quality Score

Top 5%
26
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add o1xhack/telegram-watch

Agent Capability Analysis

The telegram-watch-dev MCP Server by o1xhack is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for cli, monitoring, privacy.

Ideal Agent Persona

Ideal for Social Media Monitoring Agents requiring advanced Telegram data capture and analysis capabilities powered by Telethon

Core Value

Empowers agents to monitor specific Telegram users and channels, capturing messages and media into SQLite databases and generating periodic HTML reports via Telethon, leveraging SQLite for data storage and HTML for report generation

Capabilities Granted for telegram-watch-dev MCP Server

Monitoring target groups for specific keywords
Capturing and analyzing user-generated media in Telegram channels
Generating periodic HTML reports for social media insights

! Prerequisites & Limits

  • Requires Telethon library
  • SQLite database setup needed
  • Must follow specific workflow for request approval and intake
SKILL.md
Readonly

When using this skill, ALWAYS follow this workflow:

  1. Requirements workflow is mandatory (no exceptions)
  • Source of truth: docs/requests/
  • Intake: docs/inbox.md
  • Template: docs/templates/REQ_TEMPLATE.md
  1. Before coding: pick work from Approved requests
  • List docs/requests/ and find requirements with Status: Approved.
  • If multiple exist, choose the lowest-numbered / smallest-scope one unless the user specifies an ID.
  1. If there is NO Approved request
  • Read docs/inbox.md (if present) and/or the user’s latest message.
  • Create ONE new Draft requirement file:
    • Path: docs/requests/REQ-YYYYMMDD-###-slug.md
    • Content: must follow docs/templates/REQ_TEMPLATE.md
    • Set Status: Draft
  • STOP after creating the Draft and ask the user to approve it.
  • Do NOT implement anything until the user confirms approval (Status becomes Approved).
  1. When starting implementation of an Approved request
  • Update the chosen REQ:
    • Status: Approved -> Status: Implementing
    • Add a short plan in the REQ (2–6 bullets max).
  • Implement the request strictly as written; avoid unrelated refactors.
  1. Build order for MVP code work
  • Implement in this order: doctor -> once -> run.

4.1) README localization rule

  • Any time you add or update content in README.md, you must apply the same change (or equivalent translation) to every localized README (README.zh-Hans.md, README.zh-Hant.md, README.ja.md). Language switch links at the top must also stay in sync.
  1. After each change set, run validations
  • python -m telegram_watch doctor --config config.toml
  • python -m telegram_watch once --config config.toml --since 10m
  1. Completion protocol
  • Ensure all Acceptance Criteria in the REQ and ACCEPTANCE.md are satisfied.
  • Update the REQ:
    • Tick the acceptance checkboxes
    • Add “What changed” (files touched + brief rationale)
    • Status: Implementing -> Status: Done
  1. Security / open-source hygiene (never violate)
  • Never print or commit secrets (api_hash, phone, session).
  • Ensure .gitignore excludes: config.toml, *.session, data/, reports/.
  • Keep data local by default; do not add cloud dependencies unless explicitly approved.
  1. Commit protocol
  • When the user says “commit”, always include both a summary and a description in the commit message.
  • Use this format:
    • git commit -m "SUMMARY" -m "DETAILS"
    • SUMMARY: short, action-oriented, and specific.
    • DETAILS: 2–6 bullets or sentences describing key changes, ordered by importance.

Related Skills

Looking for an alternative to telegram-watch-dev or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
Design

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication