← 返回 Skills 市场
286
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install torrent-downloader
功能描述
Search magnet links for movies/TV shows and download via qBittorrent. Automatically scores and ranks results by subtitle availability and resolution. Trigger...
安全使用建议
This skill behaves as advertised: it searches a public torrent index and sends magnet links to a qBittorrent Web UI. Before installing, confirm you intend to let the agent autonomously start downloads (the skill is configured to auto-pick the top result). Change the default QBT_USER/QBT_PASS and ensure QBT_URL points to a local or trusted qBittorrent instance (avoid exposing a remote Web UI with weak credentials). If you want stricter control, run the included scripts manually first or require the agent to show search results and ask for confirmation before adding a torrent. Be aware of legal implications of downloading copyrighted material.
功能分析
Type: OpenClaw Skill
Name: torrent-downloader
Version: 1.0.0
The skill bundle is a functional tool for searching and downloading torrents via qBittorrent. It uses standard Python libraries to interact with the SolidTorrents API and a local qBittorrent Web UI. While the instructions in SKILL.md direct the agent to automatically initiate downloads without showing a selection list to the user, this behavior aligns with the stated purpose of the tool and does not exhibit signs of data exfiltration, unauthorized access, or malicious intent.
能力评估
Purpose & Capability
Name/description, SKILL.md, and the two scripts are consistent: search_magnet.py queries a public torrent search API (SolidTorrents) and qbt_download.py talks to a qBittorrent Web UI. Required binary (python3) and optional environment variables (QBT_URL, QBT_USER, QBT_PASS) are appropriate for this purpose.
Instruction Scope
The runtime instructions and Agent Behavior Rules instruct the agent to automatically pick the highest-scored result and start the download without showing the search list to the user. Functionally this is within the skill's download purpose, but it grants the agent autonomous decision-making about which magnet to add. The scripts themselves only perform expected network calls (SolidTorrents and the configured qBittorrent URL) and do not read unrelated files or environment variables.
Install Mechanism
No install spec (instruction-only plus shipped scripts). This is low-risk: nothing is downloaded or written to disk by an installer beyond the code bundle you already have.
Credentials
No unrelated credentials requested. The skill documents QBT_URL, QBT_USER, and QBT_PASS (used by qbt_download.py) which are proportionate to controlling a qBittorrent Web UI. Note: defaults (http://localhost:8080, admin/adminadmin) are insecure placeholders—users should supply correct credentials and avoid exposing a remote qBittorrent instance.
Persistence & Privilege
always is false and there is no installation step that modifies other skills or system settings. However, the skill's declared agent behavior (auto-select & start downloads without prompting) combined with normal autonomous invocation means an agent could add downloads without per-download confirmation — consider requiring explicit user confirmation if you don't want that behavior.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install torrent-downloader - 安装完成后，直接呼叫该 Skill 的名称或使用
/torrent-downloader触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release: search magnet links for movies/TV shows and download via qBittorrent
元数据
常见问题
Torrent Downloader 是什么？
Search magnet links for movies/TV shows and download via qBittorrent. Automatically scores and ranks results by subtitle availability and resolution. Trigger... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 286 次。
如何安装 Torrent Downloader？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install torrent-downloader」即可一键安装，无需额外配置。
Torrent Downloader 是免费的吗？
是的，Torrent Downloader 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Torrent Downloader 支持哪些平台？
Torrent Downloader 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Torrent Downloader？
由 d19310（@d19310）开发并维护，当前版本 v1.0.0。
推荐 Skills