How do I install the Vertex Video Reader skill?

Run npx skillmds@latest add hwj123hwj/vertex-video-reader in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Vertex Video Reader safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Vertex Video Reader?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Vertex Video Reader free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Vertex Video Reader?

hwj123hwj (@hwj123hwj) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Vertex Video Reader by hwj123hwj — Agent Skill

Name: Vertex Video Reader
Author: hwj123hwj

Vertex Video Reader

Use this skill to read, analyze, and understand video files using Google Cloud Vertex AI's lightweight video model (gemini-3.1-flash-lite-preview). Use it whenever the user asks to summarize a video, extract text/actions from a video, describe what happens in an mp4/mov file, or ask questions about a specific video clip.

hwj123hwj ea207ff 4 files · 8.8 KB Updated Sep 17, 2026

File contents

Vertex AI Video Reader Skill

This skill allows you to analyze and understand video contents using the fast and cost-effective gemini-3.1-flash-lite-preview model via Google Vertex AI.

Usage

To analyze a video, use the run_shell_command tool to execute the provided Python script:

python .claude/skills/vertex-video-reader/scripts/analyze_video.py "/path/to/video.mp4" -p "具体的提问或提示词"

Parameters

video_path (Required): The absolute or relative path to the video file (.mp4, .mov, .webm).
-p, --prompt (Optional): Instructions for what to extract or analyze. Default is "请详细描述一下这个视频的内容。" (Please describe the contents of this video in detail).
-m, --model (Optional): Model to use. Default is gemini-3.1-flash-lite-preview (cheaper/faster). You can switch to gemini-3.1-flash for tasks requiring deeper reasoning, complex extraction, or longer context.

Important Constraints

File Size Limit: This script uses inlineData (Base64 encoding) to send the video directly in the JSON payload. Vertex AI usually restricts inline video payloads to around 20MB. It works best for small to medium video clips (e.g., short drama clips, Tiktok/Reels videos).
Supported Formats: mp4, mov, webm, mkv.
API Key: The script automatically looks for VERTEX_API_KEY in the skill's .env file or the project root .env.

Examples

Example 1: General Video Summary

python .claude/skills/vertex-video-reader/scripts/analyze_video.py "./downloads/clip1.mp4"

Example 2: Specific Question/Extraction

python .claude/skills/vertex-video-reader/scripts/analyze_video.py "./assets/tutorial.mov" -p "提取出视频中屏幕上出现的所有中文字幕和关键步骤"

---name: vertex-video-readerdescription: Use this skill to read, analyze, and understand video files using Google Cloud Vertex AI's lightweight video model (gemini-3.1-flash-lite-preview). Use it whenever the user asks to summarize a video, extract text/actions from a video, describe what happens in an mp4/mov file, or ask questions about a specific video clip.---# Vertex AI Video Reader SkillThis skill allows you to analyze and understand video contents using the fast and cost-effective `gemini-3.1-flash-lite-preview` model via Google Vertex AI.## UsageTo analyze a video, use the `run_shell_command` tool to execute the provided Python script:```bashpython .claude/skills/vertex-video-reader/scripts/analyze_video.py "/path/to/video.mp4" -p "具体的提问或提示词"```### Parameters- **video_path** (Required): The absolute or relative path to the video file (`.mp4`, `.mov`, `.webm`).- **-p, --prompt** (Optional): Instructions for what to extract or analyze. Default is "请详细描述一下这个视频的内容。" (Please describe the contents of this video in detail).- **-m, --model** (Optional): Model to use. Default is `gemini-3.1-flash-lite-preview` (cheaper/faster). You can switch to `gemini-3.1-flash` for tasks requiring deeper reasoning, complex extraction, or longer context.## Important Constraints- **File Size Limit**: This script uses `inlineData` (Base64 encoding) to send the video directly in the JSON payload. Vertex AI usually restricts inline video payloads to around `20MB`. It works best for small to medium video clips (e.g., short drama clips, Tiktok/Reels videos).- **Supported Formats**: `mp4`, `mov`, `webm`, `mkv`.- **API Key**: The script automatically looks for `VERTEX_API_KEY` in the skill's `.env` file or the project root `.env`.## Examples**Example 1: General Video Summary**```bashpython .claude/skills/vertex-video-reader/scripts/analyze_video.py "./downloads/clip1.mp4"```**Example 2: Specific Question/Extraction**```bashpython .claude/skills/vertex-video-reader/scripts/analyze_video.py "./assets/tutorial.mov" -p "提取出视频中屏幕上出现的所有中文字幕和关键步骤"```

Frequently asked questions