0xtbug/telbot/telbot-skills

Claude Code and agent skill by 0xtbug/telbot

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Manage Telkomsel quota, packages, and profile via natural language over MCP. Use for: Logging in to Telkomsel, checking quotas, buying packages (pulsa/qris), and scheduling auto-buys.

Install

npx vskill@latest install 0xtbug/telbot/telbot-skills

SKILL.md

Telkomsel MCP Server 📱

This skill connects OpenClaw to your Telkomsel account using the telbot MCP Server. The server must be installed globally on your machine.

Setup

First, ensure you have downloaded and installed the telbot binary from the GitHub Releases, or built it globally using Go.

1. OpenClaw Configuration

OpenClaw reads its main configuration from ~/.openclaw/openclaw.json (or via $OPENCLAW_CONFIG_PATH). This file manages high-level settings and skill loading.

2. MCP Integration (via mcporter)

OpenClaw uses the bundled `mcporter` skill to interface with MCP servers. Add the Telkomsel server to your mcporter configuration (usually located at ~/.mcporter/mcporter.json):

json
{
"mcpServers": {
"telkom": {
"command": "telbot",
"args": ["--mcp"]
}
}
}

Note: The `telbot` MCP server automatically manages its own sessions and configuration internally, so you do not need to pass environment variables directly through the config.

Available Tools

Once connected, OpenClaw has access to the following Telkomsel tools via the MCP protocol:

Authentication
  • login — Start the login process by providing your phone number. This triggers an SMS OTP.
  • submit_otp — Submit the OTP code received on your phone to complete the underlying session login.
  • logout — Clear the stored credentials and active session.
Account & Quota
  • get_profile — Retrieve comprehensive user profile data (balance, active period, status).
  • get_quota — Check current internet and package balances.
Packages & Purchasing
  • get_recommended_offers — List recommended packages available to buy, along with their Offer IDs.
  • get_package_details — Get deep details about a specific package (price, validity, exact bonuses) using its offer_id.
  • buy_package — Purchase a package using its offer_id and specifying a payment_method (pulsa or qris).
Automation
  • start_auto_buy — Start a background monitor that checks quota periodically and auto-purchases a package (via Pulsa) when depleted or below a specific MB threshold limit.
  • auto_buy_status — Check if the monitor is running and what package it is configured to buy.
  • stop_auto_buy — Stop the auto-buy monitor.

Usage Guidelines for the Agent

When the user asks to interact with Telkomsel:

  1. Authentication:

If a tool fails because there is no active session, tell the user to use the login tool. IMPORTANT: Call login first. The tool will return a message that an OTP was sent. STOP and ask the user to provide the OTP they received via SMS. Once the user replies with the OTP, call the submit_otp tool.

  1. Fetching Data First:

Always run get_profile or get_quota if the user asks for a general update, account status, or wants to check if they need to buy a package.

  1. Purchasing Packages:
  • Always run get_recommended_offers to get a list of valid Offer IDs if the user wants to see what they can buy.
  • If the user asks about a specific package in the list, run get_package_details with that offer_id to confirm the price before executing buy_package.
  • When calling buy_package, ensure the payment_method is exactly "pulsa" or "qris".
  1. Auto-Buy Execution:

When setting up auto-buy with start_auto_buy, ask the user for their preferred checking interval (in minutes), which package (by offer_id) they want to monitor, and their preferred MB threshold limit. Remind them that auto-buy relies on their Pulsa balance.

Knowledge from Research

  • Config Locations: OpenClaw defaults to ~/.openclaw/openclaw.json.
  • Skill Loading: Managed via ~/.openclaw/skills, <workspace>/skills, or skills.load.extraDirs.
  • MCP Calls: OpenClaw executes MCP tools via mcporter call <tool_name> [args].

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
79
Repository forks
17
7-day trend score
22

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/0xtbug/telbot/telbot-skills/badge)](https://verified-skill.com/skills/0xtbug/telbot/telbot-skills)

Something wrong with this skill or its page? Tell us.