← Back to Skills Marketplace
wangminrui2022

link-resolver-engine

by 顶尖王牌程序员 · GitHub ↗ · v1.0.6 · MIT-0
cross-platform ⚠ suspicious
174
Downloads
0
Stars
0
Active Installs
7
Versions
Install in OpenClaw
/install link-resolver-engine
Description
当用户想要**下载抖音视频**、**下载B站视频**、**解析无水印直链**、**提取最高画质视频**、**把视频下下来**、**保存抖音/B站视频**时自动触发。 专门处理哔哩哔哩(Bilibili/B站)和抖音(Douyin)的任意视频链接(包括短链 b23.tv、douyin.com、bilibili.co...
README (SKILL.md)

\r \r

link-resolver-engine\r

\r 功能:高性能、智能、双平台视频链接解析与下载引擎。专为 OpenClaw Skill 生态设计,支持 B站(Bilibili)抖音(Douyin) 视频链接的自动识别、智能解析与无水印下载。\r \r

触发时机(Triggers)\r

  • 用户直接发抖音或B站视频链接,并带有“下载”“解析”“直链”“无水印”“最高画质”“下下来”“保存”等关键词。\r
  • 用户说“帮我处理这个视频链接”“给我这个视频的最高画质版本”等口语指令。\r
  • 支持批量处理:一次发多个链接也行。\r
  • 自动检测短链并跳转。\r \r

核心优势\r

  • 完全离线运行(仅在需要时使用网络下载视频)。\r
  • 采用“主方案 + 备用方案”双保险机制,确保最高成功率。\r
  • 自动检测平台(支持短链自动跳转)。\r
  • 下载完成后按指定目录保存 .mp4 文件。\r \r

参数提取指南\r

当决定调用此技能时,请从用户上下文中提取以下参数:\r \r

  1. \x3C视频链接> (必填): 用户提供的完整链接或短链(如 b23.tvv.douyin.com 等)。\r
  2. \x3C文件名前缀> (选填): 用户如果明确指定了保存的文件名。\r
  3. \x3C下载目录> (选填): 用户如果明确指定了保存路径。若未指定,无需添加此参数(默认 ./downloads)。\r
  4. \x3C格式代码> (选填): 用户如果明确提出了特定的画质或格式要求。\r \r

B站下载方案\r

  1. 第一优先 → 使用 yt-dlp(最稳定、最快,支持最高画质)\r
  2. 第二备用 → 自动展开 b23.tv 短链接 → 获取无水印直链 → requests + ffmpeg 合并\r
  3. 第三兜底 → 两步都失败时给出清晰错误提示\r \r

抖音下载方案\r

  1. 第一优先 → 短链展开 → PC 端最高画质无水印直链下载\r
  2. 第二备用 → 移动端轻量模式下载(兼容性极强)\r
  3. 第三兜底 → 优先保证画质,失败后自动降级\r \r

执行步骤\r

  1. 解析链接:识别用户的源链接(支持单个或批量 B站/抖音视频链接或短链,自动判断平台)。\r
  2. 默认目标:若未指定下载目录,默认保存在 ./downloads 文件夹(支持 --filename-prefix 或自动生成带时间戳的文件名)。\r
  3. 调用命令:使用以下兼容性命令启动脚本(优先 python3,失败则 python)。脚本会自动创建虚拟环境、检查依赖并初始化。\r \r
    (python3 scripts/video_snapper.py -u "\x3C视频链接>" [-p "\x3C文件名前缀>"] [-d "\x3C下载目录>"] [-f "\x3C格式代码>"]) || (python scripts/video_snapper.py -u "\x3C视频链接>" [-p "\x3C文件名前缀>"] [-d "\x3C下载目录>"] [-f "\x3C格式代码>"])
    
Usage Guidance
This skill appears to implement video downloading for Bilibili and Douyin as stated, but it makes significant environment changes at runtime: it will auto-run pip installs (and may modify setuptools), download Playwright chromium and ffmpeg, create a virtualenv in a directory outside the skill folder, and restart in that venv. Those actions can modify your Python environment, write files to disk, and perform network downloads. Before installing or running it consider: - Do not run in a production or sensitive host. Prefer an isolated sandbox/container or disposable VM. - Review the code (ensure_package, env_manager, and top-level imports) line-by-line; note that many installs happen at module import time. - If you must use it on a persistent host, change VENV_DIR to a skill-local path, remove or disable automatic setuptools downgrades, and avoid top-level pip/playwright installs (move them to an explicit, user-approved setup step). - Expect downloads (chromium, ffmpeg, pip packages) and filesystem writes (logs, downloads, venv). - The unicode-control-chars finding in SKILL.md is a prompt-injection warning — be cautious with automatic enabling or trusting external documentation. If you want help producing a safer checklist or a sanitized version of this skill that only runs in a local ephemeral environment, I can suggest concrete code edits (e.g., remove top-level installs, use a local venv path, require explicit user consent before downloads).
Capability Analysis
Type: OpenClaw Skill Name: link-resolver-engine Version: 1.0.6 The skill bundle is a functional video downloader for Bilibili and Douyin. It features a robust environment setup process, including automated virtual environment creation, dependency management via pip (using the Tsinghua mirror), and the automatic installation of FFmpeg and Chromium. The core logic uses Playwright for dynamic content scraping and the Bilibili/Douyin APIs to retrieve high-quality, watermark-free video streams. All high-risk operations, such as subprocess execution for video merging and network requests for media downloading, are strictly aligned with the stated purpose. No evidence of data exfiltration, malicious persistence, or prompt injection was found across the analyzed files (video_snapper.py, bilibili_video.py, douyin_video.py, etc.).
Capability Assessment
Purpose & Capability
Name and description match the code: it targets B站 and 抖音 and uses yt-dlp/Playwright/ffmpeg to fetch highest-quality, no-watermark streams. However the code also downgrades setuptools, supports installing large ML stacks (PyTorch paths present), and creates a virtualenv outside the skill directory (VENV_DIR set to a parent-level path). Those environment/control actions are not necessary for a simple download helper and are disproportionate to the stated purpose.
Instruction Scope
SKILL.md instructs running the provided script and mentions yt-dlp/ffmpeg/Playwright, which is expected. The actual code goes further: at import it auto-installs Python packages, runs 'playwright install chromium', forces setuptools changes, may auto-download ffmpeg, and restarts into a new venv. These side effects are not documented in SKILL.md and expand scope to system modification and network downloads.
Install Mechanism
There is no formal install spec, but the code performs runtime installation: ensure_package.pip calls pip, attempts to downgrade setuptools, ensure_package supports git+/zip installs and fallback behavior, scripts invoke 'playwright install chromium' and ffmpeg-downloader, and video_snapper will download binaries. Runtime downloads from remote sources and extraction/install behavior are present and executed at module import — a high-risk install pattern.
Credentials
The skill requests no credentials, but it writes persistent artifacts: creates a virtualenv at VENV_DIR which resolves outside the skill root (parent of repo root), writes logs and downloads, modifies the Python environment (pip installs, setuptools downgrade), and may install large optional packages (PyTorch-related logic). These are excessive for a chat-level video resolver and can affect the host environment.
Persistence & Privilege
always:false, but the skill persists by creating venvs, downloading browsers and ffmpeg, and installing packages into the current Python environment. It runs subprocesses and can restart the process in a newly created venv. This gives it a durable footprint and system-level side effects beyond the life of a single invocation.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install link-resolver-engine
  3. After installation, invoke the skill by name or use /link-resolver-engine
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.6
Version 1.0.6 of link-resolver-engine - No file changes detected in this release. - No visible feature, bug, or documentation changes from the previous version.
v1.0.5
- 移除了部分常见触发口语,简化描述。 - 其余功能与参数指南保持不变。
v1.0.4
- Expanded and clarified the skill description to better specify supported platforms and use cases. - Added a comprehensive list of natural language trigger phrases for improved automatic invocation. - Updated instructions for parameter extraction and triggering conditions based on user context. - Improved documentation for supported link types (short and full links) and typical user queries. - Emphasized strict limitation to Bilibili and Douyin links, ignoring all others.
v1.0.3
- No changes detected in this version; version bump only. - Functionality, description, and requirements remain unchanged.
v1.0.2
- No code changes; this release maintains all previous features and behavior. - SKILL.md updated without any functional modifications.
v1.0.1
- Slightly shortened the plugin description for clarity. - No functional or technical changes; documentation content remains consistent.
v1.0.0
link-resolver-engine 1.0.0 - Initial release: Provides offline, high-quality download and link resolution for Bilibili and Douyin videos. - Supports automatic platform detection and short-link expansion for both sites. - Downloads videos in the highest available quality and merges audio/video when needed. - Batch processing and fallback mechanisms increase reliability. - Default saving to ./downloads directory with automatic filename generation.
Metadata
Slug link-resolver-engine
Version 1.0.6
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 7
Frequently Asked Questions

What is link-resolver-engine?

当用户想要**下载抖音视频**、**下载B站视频**、**解析无水印直链**、**提取最高画质视频**、**把视频下下来**、**保存抖音/B站视频**时自动触发。 专门处理哔哩哔哩(Bilibili/B站)和抖音(Douyin)的任意视频链接(包括短链 b23.tv、douyin.com、bilibili.co... It is an AI Agent Skill for Claude Code / OpenClaw, with 174 downloads so far.

How do I install link-resolver-engine?

Run "/install link-resolver-engine" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is link-resolver-engine free?

Yes, link-resolver-engine is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does link-resolver-engine support?

link-resolver-engine is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created link-resolver-engine?

It is built and maintained by 顶尖王牌程序员 (@wangminrui2022); the current version is v1.0.6.

💬 Comments