← Back to Skills Marketplace
6216
Downloads
9
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install douyin-video-analyst
Description
抖音账号视频批量采集与文案分析工作流。当用户提供抖音账号主页链接、要求抓取最新 N 条视频链接、提取视频文案（语音转文字）、或对视频内容进行总结归纳时，激活此 skill。依赖 browser 工具（抓取视频列表）和 mcporter + douyin-mcp（文案提取）。
Usage Guidance
Install only if you are comfortable with a skill that uses a browser profile, local MCP configuration, and API-backed transcription. Do not run the troubleshooting config-dump command with real credentials unless it is redacted first, avoid pasting API keys into shell commands or support chats, and prefer pinned, reviewed versions of mcporter and douyin-mcp-server.
Capability Assessment
Credentials
Use of browser and mcporter is coherent for Douyin collection and transcription, but local config inspection and credential-bearing command examples are broader than necessary and can leak secrets into logs or transcripts.
Install Mechanism
Setup uses npm install -g mcporter and an unpinned uvx douyin-mcp-server path for the latest version, creating ordinary supply-chain risk for a local tool that receives API credentials.
Instruction Scope
The skill directs agents to inspect ~/.cursor/mcp.json and ~/.claude.json without an explicit consent boundary; the main skill prints only args and env key names, but troubleshooting prints the full config object.
Persistence & Privilege
No backdoor, scheduled task, memory write, or privilege escalation is present; the persistent elements are user MCP configuration and optional global CLI installation.
Purpose & Capability
The main browser and douyin-mcp workflow is purpose-aligned, but troubleshooting prints the full douyin-mcp configuration, which can include plaintext API keys and is not needed for video analysis.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install douyin-video-analyst - After installation, invoke the skill by name or use
/douyin-video-analyst - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
支持 v1.1.0（硅基流动）和 v1.2.0+（阿里云百炼）双版本；说明 mcporter 加载 ~/.cursor/mcp.json 和 ~/.claude.json；输出改为去口语化的精简原始文案
v1.0.0
抖音账号视频采集 + 文案提取工作流：browser 抓取视频列表 + douyin-mcp 语音转文字 + 内容总结
Metadata
Frequently Asked Questions
What is Douyin Video Analyst?
抖音账号视频批量采集与文案分析工作流。当用户提供抖音账号主页链接、要求抓取最新 N 条视频链接、提取视频文案（语音转文字）、或对视频内容进行总结归纳时，激活此 skill。依赖 browser 工具（抓取视频列表）和 mcporter + douyin-mcp（文案提取）。 It is an AI Agent Skill for Claude Code / OpenClaw, with 6216 downloads so far.
How do I install Douyin Video Analyst?
Run "/install douyin-video-analyst" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Douyin Video Analyst free?
Yes, Douyin Video Analyst is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Douyin Video Analyst support?
Douyin Video Analyst is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Douyin Video Analyst?
It is built and maintained by fishisnow (@fishisnow); the current version is v1.0.1.
More Skills