← Back to Skills Marketplace
hanxueda

Douyin Dedup

by 三昧 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
173
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install douyin-dedup
Description
抖音视频下载、去水印、深度混剪去重、去除音频的全自动处理工具。当用户发送抖音链接(v.douyin.com 或 douyin.com 格式)并要求处理、去重、下载或类似意图时,自动触发此技能。
README (SKILL.md)

抖音去重工具

功能

给定抖音URL,自动完成:下载 → 去水印 → 深度混剪去重 → 去除音频 → 输出文件

使用方法

执行命令

cd ~/.openclaw/skills/douyin-dedup/scripts && python3 dedup.py "\x3C抖音URL>"

输出位置

~/video-dedup/output/dedup_\x3C随机ID>.mp4

去重效果包含

  • 随机截取 3-6 个片段打乱顺序
  • 画面随机裁剪缩放(80%-95%)
  • 随机镜像翻转(30%概率)
  • 随机亮度调整(±5% Gamma校正)
  • 随机噪点叠加(20%概率)
  • 随机播放速度(0.9x-1.1x)
  • 去除原始音频

依赖

  • ffmpeg
  • yt-dlp
  • Python 3

故障排除

  • 如遇下载失败,可能是抖音链接重定向问题,检查视频ID是否正确提取
  • 如遇 ffmpeg 滤镜错误,检查 noise 滤镜参数格式
Usage Guidance
This skill appears to do what it says: it downloads Douyin videos (via Douyin/iesdouyin/aweme endpoints or yt-dlp), removes audio/watermark and runs ffmpeg transforms, then saves files under ~/video-dedup. Before installing or running: 1) Ensure you have trusted ffmpeg, ffprobe and yt-dlp binaries installed (the registry metadata did not declare these, but the script needs them). 2) Be aware it will download media from the internet and write files to your home directory — run in a sandbox/container if you want isolation. 3) This tool can be used to repurpose others' content (legal/terms-of-service risk); verify you have rights to process videos. 4) If you need higher assurance, review the full script (dedup.py) locally and run it manually once rather than granting broad automation. No credentials are requested and I found no hidden remote endpoints or exfiltration logic.
Capability Analysis
Type: OpenClaw Skill Name: douyin-dedup Version: 1.0.0 The skill is a specialized utility for downloading Douyin videos and applying FFmpeg filters to modify the visual content (deduplication). The code in `scripts/dedup.py` implements the stated functionality using standard libraries and external tools like `ffmpeg` and `yt-dlp`, communicating only with legitimate Douyin/ByteDance domains (e.g., iesdouyin.com, snssdk.com) to retrieve video data. No indicators of data exfiltration, persistence, or malicious command execution were found.
Capability Assessment
Purpose & Capability
The skill name/description (Douyin download + dedup) matches the included script behavior: network download from Douyin/iesdouyin/aweme endpoints, use of yt-dlp fallback, and ffmpeg-based processing. Minor inconsistency: registry metadata lists no required binaries, but the SKILL.md and script clearly require ffmpeg, ffprobe, yt-dlp and Python3.
Instruction Scope
SKILL.md instructs the agent to run the included script from the skill's scripts directory. The script only reads the provided Douyin URL, fetches video content from Douyin-related hosts, runs ffmpeg/ffprobe/yt-dlp, and writes files under ~/video-dedup; it does not attempt to read other system files, environment secrets, or send data to third‑party endpoints beyond video hosts.
Install Mechanism
No install spec is present and the skill is instruction+script only. That is low-risk as nothing is downloaded during install. The script invokes system binaries (ffmpeg, yt-dlp), so those must be installed separately by the user.
Credentials
The skill requests no environment variables or credentials. Its network access is limited to fetching video pages and media URLs derived from the provided Douyin link; no secrets or unrelated service tokens are requested.
Persistence & Privilege
always:false and user-invocable:true (normal). The skill writes output to its own workspace/output directories in the user's home and does not modify other skills or system-wide agent settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install douyin-dedup
  3. After installation, invoke the skill by name or use /douyin-dedup
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of douyin-dedup. - Supports automatic download, watermark removal, deep deduplication (remix), and audio removal for Douyin videos via URL. - Processes include segment shuffling, crop/scale, mirroring, brightness adjustment, noise, and speed changes. - Outputs deduplicated video file ready for use. - Simple command-line usage and troubleshooting guidance included. - Requires ffmpeg, yt-dlp, and Python 3.
Metadata
Slug douyin-dedup
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Douyin Dedup?

抖音视频下载、去水印、深度混剪去重、去除音频的全自动处理工具。当用户发送抖音链接(v.douyin.com 或 douyin.com 格式)并要求处理、去重、下载或类似意图时,自动触发此技能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 173 downloads so far.

How do I install Douyin Dedup?

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

Is Douyin Dedup free?

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

Which platforms does Douyin Dedup support?

Douyin Dedup is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Douyin Dedup?

It is built and maintained by 三昧 (@hanxueda); the current version is v1.0.0.

💬 Comments