← Back to Skills Marketplace
724
Downloads
3
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install douyin-downloader-nodejs
Description
抖音无水印视频下载和文案提取工具
README (SKILL.md)
douyin-downloader Skill
抖音无水印视频下载和文案提取工具的 Node.js 版本。
功能
- 🎬 获取无水印视频下载链接
- 📥 下载抖音视频
- 🎙️ 从视频中提取语音文案(需要 API Key)
环境变量
DOUYIN_API_KEY或API_KEY- 硅基流动 API 密钥(用于语音转文字)
获取 API Key: https://cloud.siliconflow.cn/
使用方法
获取视频信息(无需 API Key)
node /root/.openclaw/workspace/skills/douyin-downloader/douyin.js info "抖音分享链接"
下载视频
node /root/.openclaw/workspace/skills/douyin-downloader/douyin.js download "抖音链接" -o ./videos
提取文案(需要 API Key)
export DOUYIN_API_KEY="your-api-key"
node /root/.openclaw/workspace/skills/douyin-downloader/douyin.js extract "抖音链接" -o ./output
在 OpenClaw 中调用
通过 exec 工具调用:
node /root/.openclaw/workspace/skills/douyin-downloader/douyin.js info \x3C抖音链接>
Usage Guidance
This skill appears to implement Douyin downloading and transcription, but check the following before installing:
- Be aware audio is uploaded to https://api.siliconflow.cn for transcription. Do not use the skill on sensitive audio unless you trust that service and its privacy policy.
- SKILL.md and the code require an API key (DOUYIN_API_KEY or API_KEY) but the registry metadata does not declare it — expect to provide that secret manually. Limit the key's scope if possible.
- The code spawns both ffmpeg and ffprobe; ensure those binaries are available (ffprobe may be part of ffmpeg on some systems). The metadata only listed ffmpeg — consider this a small mismatch.
- The skill writes video/audio/transcript files to the output folder you choose; run it in a sandboxed or disposable workspace if unsure.
- The repository/homepage is listed (https://github.com/yzfly/douyin-mcp-server). If you plan to use it, review the full source there and the remainder of douyin.js (the provided file was truncated in the package) so you can confirm no unexpected behavior exists.
If you want higher assurance, ask the publisher to update the metadata to declare the required env vars and to provide a full audit of network endpoints and any additional code paths not visible in the truncated file.
Capability Analysis
Type: OpenClaw Skill
Name: douyin-downloader-nodejs
Version: 1.0.0
The skill is designed for legitimate video downloading and transcription. However, it is classified as suspicious due to significant vulnerabilities. The `douyin.js` script uses `child_process.spawn` to execute `ffmpeg` and `ffprobe` with file paths constructed from user-controlled input (`outputDir` and derived `video_id`). This poses a shell injection risk if these inputs contain malicious metacharacters. Additionally, the `outputDir` is directly used in `path.join` for file writing, creating a path traversal vulnerability that could allow writing files to arbitrary locations on the filesystem. There is no evidence of intentional malicious behavior like data exfiltration or backdoors.
Capability Assessment
Purpose & Capability
The name/description (Douyin downloader + transcription) align with the code: it parses Douyin links, downloads videos, extracts audio, and posts audio to a transcription API. Minor mismatch: the registry metadata lists no required environment variables, but SKILL.md and the code expect an API key (DOUYIN_API_KEY or API_KEY) for transcription.
Instruction Scope
SKILL.md instructs running the included Node script and the code follows that. The code performs network requests to douyin.com (to resolve video info) and to https://api.siliconflow.cn/v1/audio/transcriptions to upload audio for transcription — this is expected for the stated feature but is important to note because it sends user audio to a third party. The SKILL.md examples reference an absolute skill workspace path; otherwise the instructions do not request unrelated system data.
Install Mechanism
This is an instruction-only skill with no install spec; nothing is downloaded or extracted by an installer, which is the lowest-risk install model.
Credentials
The skill requires an API key for transcription (DOUYIN_API_KEY or API_KEY) according to SKILL.md and the code, but the registry metadata reports no required environment variables or primary credential — that inconsistency is concerning because users may not realize they must provide a key. Otherwise, no unrelated credentials or high-privilege env vars are requested.
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges. It creates files in the specified output directories and invokes ffmpeg/ffprobe locally, which is appropriate for its purpose.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install douyin-downloader-nodejs - After installation, invoke the skill by name or use
/douyin-downloader-nodejs - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of douyin-downloader Node.js version:
- 支持抖音无水印视频下载
- 支持获取视频下载链接及提取语音文案(需 API Key)
- 命令行工具,包含信息获取、视频下载与文案提取功能
- 依赖 ffmpeg,部分功能需硅基流动 API 密钥
Metadata
Frequently Asked Questions
What is 抖音下载器(Node.js)?
抖音无水印视频下载和文案提取工具. It is an AI Agent Skill for Claude Code / OpenClaw, with 724 downloads so far.
How do I install 抖音下载器(Node.js)?
Run "/install douyin-downloader-nodejs" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 抖音下载器(Node.js) free?
Yes, 抖音下载器(Node.js) is completely free (open-source). You can download, install and use it at no cost.
Which platforms does 抖音下载器(Node.js) support?
抖音下载器(Node.js) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 抖音下载器(Node.js)?
It is built and maintained by whille (@whille); the current version is v1.0.0.
More Skills