Telegram Formatting

Formats all Telegram bot replies to be short, scannable, and properly styled with MarkdownV2. Use when replying to Telegram messages via the Telegram MCP plugin — ensures bold, emojis, bullet points, and correct special character escaping.

58 stars 18 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add EricTechPro/startup-claude-skills --skill telegram-formatting
Manual install
git clone --depth 1 https://github.com/EricTechPro/startup-claude-skills.git /tmp/startup-claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/startup-claude-skills/skills/telegram-formatting ~/.claude/skills/telegram-formatting

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Telegram Formatting — Claude Code Reply Style

Ensures every Telegram reply is **short, concise, and mobile-friendly** using MarkdownV2.

## When to Use

Apply this skill whenever replying via `mcp__plugin_telegram_telegram__reply`. Every reply must use `format: "markdownv2"`.

## Rules

| Rule | Requirement |
|------|-------------|
| **Length** | Under ~800 chars when possible |
| **Format** | Always set `format: "markdownv2"` |
| **Structure** | Emojis as section headers + bullet points |
| **Emphasis** | Bold key terms and outcomes |
| **Tone** | Direct, no filler, no preamble |

## MarkdownV2 Syntax

| Entity | Syntax |
|--------|--------|
| Bold | `*bold text*` |
| Italic | `_italic text_` |
| Underline | `__underline__` |
| Strikethrough | `~strikethrough~` |
| Spoiler | `\|\|spoiler\|\|` |
| Inline code | `` `code` `` |
| Pre block | ` ```pre``` ` |
| Link | `[text](URL)` |
| Bold italic | `*_bold italic_*` |

## Escaping (CRITICAL)

These characters **MUST** be escaped with `\` when they appear **outside** formatting entities:

```
_ * [ ] ( ) ~ ` > # + - = | { } . !
```

### Escaping by context

| Context | What to escape |
|---------|---------------|
| Plain text | All 18 special chars listed above |
| Inside `(...)` of links | `)` and `\` only |
| Inside code/pre | `` ` `` and `\` only |

### Common gotchas

- `Done!` must be `Done\!`
- `file.txt` must be `file\.txt`
- `A - B` must be `A \- B`
- `key=val` must be `key\=val`
- `(test)` must be `\(test\)`
Read the full skill on GitHub

Details

Skill name
telegram-formatting
Path
skills/telegram-formatting/SKILL.md
License
MIT
Repo updated
5 June 2026

FAQ

What does the Telegram Formatting skill do?

Formats all Telegram bot replies to be short, scannable, and properly styled with MarkdownV2. Use when replying to Telegram messages via the Telegram MCP plugin — ensures bold, emojis, bullet points, and correct special character escaping.

How do I install the Telegram Formatting skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add EricTechPro/startup-claude-skills --skill telegram-formatting. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Telegram Formatting popular?

It lives in EricTechPro/startup-claude-skills, which has 58 GitHub stars and 18 forks.

Related skills

Develop Team

58

EricTechPro/startup-claude-skills

This skill should be used when the user asks to "develop a feature", "implement a ticket", "build PROJ-123", "run the development pipeline", "develop this ticket end to end", or wants fully autonomous feature implementation with parallel research agents, planning, phased implementation, review, and PR creation. Zero checkpoints; pauses only on blockers.

Software Development18

Fix Sentry

58

EricTechPro/startup-claude-skills

Scan all unresolved Sentry errors, group by root cause, fix in batch with TDD, and resolve in Sentry after deploy. Use when the user says 'fix sentry errors', 'scan sentry', 'resolve sentry issues', 'fix all errors', 'sentry cleanup', or wants to proactively fix production errors from Sentry monitoring.

DevOps & Cloud18

Fix Ticket

58

EricTechPro/startup-claude-skills

Automate the full Jira bug-fix pipeline end-to-end. Use when the user says 'fix ticket', 'fix PROJ-123', 'fix this bug', 'resolve PROJ-XXX', 'fix and ship this ticket', or passes a Jira ticket ID for autonomous bug resolution. Reads the Jira ticket, implements the fix, reviews it, commits, moves the ticket to QA, assigns to QA engineer, and comments with a summary. Also use when the user wants to automate the fix-review-commit-handoff cycle for any Jira bug ticket.

Testing & QA18

AI Tells

39

kdgbalmer/ai-tells

Reviews any draft for AI writing tells and produces a clean rewrite. Catches vocabulary fingerprints (delve, tapestry, leverage, robust, multifaceted, navigate, foster), structural fingerprints (negative parallelism like "It's not X, it's Y", bullet-everything, Title Case headings, adjective triads), tone fingerprints ("Great question!", "I'd be happy to help", "In conclusion"), and punctuation fingerprints (em dash overuse, knowledge-cutoff disclaimers). Use this skill whenever the user asks to humanize, de-AI, edit, polish, or sanity-check writing, including phrases like "does this sound lik

AI, LLMs & Agents

Repo First Defense

70

alexdcd/Mafia-Claude-Skills

Auditoría defensiva para repositorios AI-native. Usar SIEMPRE que el usuario quiera revisar un repo antes de lanzar, mergear, actualizar dependencias, migrar package manager, configurar un agente IA, MCP, Claude/Cursor/Codex/OpenClaw, o cuando mencione supply chain, prompt injection, secretos, GitHub Actions, npm/pnpm, paquetes maliciosos, scripts peligrosos, o riesgos de seguridad en repos con IA. Activar también si el usuario dice "revisa el repo", "está seguro esto", "antes de producción", "audita el PR" o cualquier variación.

AI, LLMs & Agents18

Design Os

37

jangtrinh/design-os

Use when working with DESIGN:OS CLI — Multi-runtime design operating system and CLI for Claude Code, OpenAI Codex, Gemini CLI, and Google Antigravity.

AI, LLMs & AgentsIn 1 list

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.