← Back to Skills Marketplace
298
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install video2txt
Description
Extract transcripts/subtitles from video URLs and deliver as .docx files. Use this skill whenever the user provides a video link (YouTube, Bilibili, or any y...
Usage Guidance
This skill appears to be what it claims: it will run yt-dlp (to download subtitles) and Node scripts (to parse SRT and create .docx) on your machine. Before installing/using it: (1) ensure yt-dlp and Node/npm are installed from trusted sources; (2) review and be comfortable with running npm install in the skill's scripts directory (package.json includes the docx dependency); (3) be aware subtitles are downloaded to a temporary directory—check or delete that directory if you have privacy concerns; (4) if no subtitles exist the skill suggests using Whisper, but Whisper is not installed or automated here; and (5) the translation step uses the agent/model (transcripts may be sent to the model for translation), so consider whether you want that content sent to external model endpoints. No credentials are requested by this skill.
Capability Analysis
Type: OpenClaw Skill
Name: video2txt
Version: 1.0.1
The skill is designed to extract video transcripts using yt-dlp and convert them into .docx files. The workflow involves standard use of temporary directories, local Node.js scripts (make_docx.js and parse_srt.js), and legitimate dependencies like the 'docx' npm package. There is no evidence of data exfiltration, malicious execution, or prompt injection intended to subvert the agent's behavior.
Capability Assessment
Purpose & Capability
Name/description (video → transcript → .docx) matches the included scripts (SRT parsing and DOCX generation) and the declared runtime dependencies (yt-dlp, node, npm docx). There are no credentials, platform-specific APIs, or unrelated tools requested.
Instruction Scope
SKILL.md stays within scope: it runs yt-dlp to fetch .srt files, parses them locally, optionally translates via the agent/model, and generates .docx with included Node scripts. One minor behavioral note: the doc references Whisper as an alternative if no subtitles exist but does not include Whisper installation or automation — this is a functional omission, not a security issue.
Install Mechanism
This is an instruction-only skill with small included Node scripts; there is no download-from-arbitrary-URL step. It asks the user/agent to install yt-dlp and node/docx via standard package managers (pip/npm/winget). Minor inconsistency: make_docx.js header suggests a global `npm install -g docx` while package.json declares a local dependency — benign but slightly inconsistent.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The runtime instructions operate on temporary files and local node/npm packages only, which is proportional to the task.
Persistence & Privilege
always is false and the skill does not request persistent agent-wide privileges or modify other skills. It runs only when invoked and does not demand elevated system presence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video2txt - After installation, invoke the skill by name or use
/video2txt - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
**Initial release with full Node.js script support and updated skill manifest.**
- Added all required script dependencies and Node.js modules (386 files) to support docx generation and subtitle processing.
- Updated SKILL.md to include explicit version number and tool/dependency specifications for yt-dlp and node.
- Clearly documented workflow for extracting, processing, and delivering video transcripts as .docx files.
- Improved clarity on error handling and user guidance regarding supported platforms and missing subtitles.
- No changes to logic; just formalized packaging and environment requirements for skill distribution.
v1.0.0
目前支持youtube和b站
Metadata
Frequently Asked Questions
What is 在线视频转文字稿?
Extract transcripts/subtitles from video URLs and deliver as .docx files. Use this skill whenever the user provides a video link (YouTube, Bilibili, or any y... It is an AI Agent Skill for Claude Code / OpenClaw, with 298 downloads so far.
How do I install 在线视频转文字稿?
Run "/install video2txt" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 在线视频转文字稿 free?
Yes, 在线视频转文字稿 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 在线视频转文字稿 support?
在线视频转文字稿 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 在线视频转文字稿?
It is built and maintained by vistalyq (@vistalyq); the current version is v1.0.1.
More Skills