Qbt Hub logo

Qbt Hub

Organization
OpenMinis
qbt-hub

Manage qBittorrent downloads via WebUI API (v5.0+). Use this skill whenever the user asks to add a torrent or magnet link, check download progress, search/filter tasks, delete tasks, set speed limits, manage tags/categories, or do anything related to qBittorrent. Trigger keywords: qBittorrent, qbt, torrent, magnet, download task, seeding, add torrent, qbt-hub.

Overview

PublisherOpenMinis
RepositoryMinisSkills
Skill nameqbt-hub
Stars
543
Forks
86
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by OpenMinis on GitHub. Read the source before you install it.

Installation

Install the Qbt Hub AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/OpenMinis/MinisSkills/tree/main/qbt-hub
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git /tmp/MinisSkills
mkdir -p .claude/skills
cp -r /tmp/MinisSkills/qbt-hub .claude/skills/qbt-hub
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qbt Hub in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Qbt Hub on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Qbt Hub is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

qbt-hub

Manage qBittorrent (v5.0+) via its WebUI API using the bundled scripts/qbt.py.

Authentication

Credentials are read from env vars (set once, reused forever):

  • QBT_HOST — e.g. http://qbt.example.com
  • QBT_USER — WebUI username
  • QBT_PASS — WebUI password

Can also be overridden per-call: --host / --user / --pass

Script Location

/var/minis/skills/qbt-hub/scripts/qbt.py

Alias for convenience:

bash
alias qbt="python3 /var/minis/skills/qbt-hub/scripts/qbt.py"

Commands

Add a task

bash
# magnet link
python3 qbt.py add "magnet:?xt=urn:btih:..."

# https .torrent URL
python3 qbt.py add "https://example.com/file.torrent"

# local .torrent file
python3 qbt.py add ~/Downloads/movie.torrent

# with options
python3 qbt.py add "magnet:..." --savepath /data/movies --category Movies --tags "4K,DV" --paused --sequential

List / filter tasks

bash
python3 qbt.py list                              # all tasks
python3 qbt.py list --filter downloading         # active downloads
python3 qbt.py list --filter completed
python3 qbt.py list --tag 4K --sort size         # filter by tag, sort by size
python3 qbt.py list --category Movies --asc

Filter choices: all downloading seeding completed paused active inactive stalled errored Sort choices: name size progress dlspeed upspeed ratio added_on

Search

bash
python3 qbt.py search ubuntu          # fuzzy match on task name

Global status

bash
python3 qbt.py status                 # DL/UL speed, totals, limits, turtle mode

Task details

bash
python3 qbt.py info ubuntu            # progress, files, trackers, peers

Pause / Resume / Recheck

bash
python3 qbt.py pause ubuntu
python3 qbt.py resume all
python3 qbt.py recheck ubuntu

Delete

bash
python3 qbt.py delete ubuntu          # keep local files
python3 qbt.py delete ubuntu --files  # also delete local data

Speed limits

bash
# per-task
python3 qbt.py limit ubuntu --dl 500 --ul 100   # KB/s
python3 qbt.py limit ubuntu --dl 0              # remove limit

# global
python3 qbt.py speedlimit                        # show current
python3 qbt.py speedlimit --dl 2048 --ul 512
python3 qbt.py speedlimit --dl 0                 # unlimited
python3 qbt.py speedlimit --alt                  # toggle turtle mode

Tags

bash
python3 qbt.py tag ubuntu --tags "linux,iso"
python3 qbt.py untag ubuntu --tags "iso"
python3 qbt.py tags                              # list all tags with counts

Categories

bash
python3 qbt.py category ubuntu --cat Linux
python3 qbt.py categories                        # list all categories

Rename / Move

bash
python3 qbt.py rename ubuntu --name "Ubuntu 24.04 LTS"
python3 qbt.py move ubuntu --path /data/iso

Top N

bash
python3 qbt.py top --n 10 --sort size    # largest tasks
python3 qbt.py top --n 5 --sort dl       # fastest downloads
python3 qbt.py top --n 5 --sort ratio    # highest ratio seeders

Sort choices: size dl ul ratio progress added

RSS

bash
python3 qbt.py rss list
python3 qbt.py rss add --url "https://example.com/feed.rss"
python3 qbt.py rss remove --path "FeedName"
python3 qbt.py rss addrule --name "4K Shows" --pattern "2160p" --category TV
python3 qbt.py rss removerule --name "4K Shows"

Workflow: Search the web and add a torrent

  1. Search for the torrent on sites like torrentkitty.net or thepiratebay.org using browser_use
  2. Extract the magnet link from the page
  3. Run python3 qbt.py add "<magnet>" --savepath /path --tags "tag1,tag2"

Common patterns

bash
# Check what's currently downloading
python3 qbt.py list --filter downloading

# Find and delete a large task including its files
python3 qbt.py top --n 10 --sort size
python3 qbt.py delete "keyword" --files

# Tag all completed tasks
python3 qbt.py list --filter completed   # find keyword
python3 qbt.py tag "keyword" --tags "done"

# Slow down a task to save bandwidth
python3 qbt.py limit "keyword" --dl 200 --ul 50

Notes

  • keyword matching is case-insensitive fuzzy match on task name
  • Use all as keyword to target every task (e.g. resume all, pause all)
  • delete always prompts for confirmation before executing
  • rename requires an exact single match; use a more specific keyword if multiple tasks match
  • qBittorrent instance: http://qbt.wsen.me (internal network, v5.0.2)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Qbt Hub AI skill do?

Manage qBittorrent downloads via WebUI API (v5.0+). Use this skill whenever the user asks to add a torrent or magnet link, check download progress, search/filter tasks, delete tasks, set speed limits, manage tags/categories, or do anything related to qBittorrent. Trigger keywords: qBittorrent, qbt, torrent, magnet, download task, seeding, add torrent, qbt-hub.

Why use Qbt Hub on TypingMind?

Because you install it once and use it with any model. Qbt Hub is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Qbt Hub in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/OpenMinis/MinisSkills/tree/main/qbt-hub. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Qbt Hub?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Qbt Hub?

As many as you like. As long as a model supports skills, you can use Qbt Hub with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Qbt Hub AI skill free?

Yes. It is published on GitHub by OpenMinis under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇