VidIQ - Video Intelligence

通过 shell 脚本调用 ffmpeg 与 yt-dlp，对 YouTube、TikTok、Instagram、X 或本地视频执行元信息查询、均匀抽帧、指定时间点抽帧、片段裁剪、GIF 生成、音频提取、场景变化检测与拼图；下载与抽帧结果缓存到临时目录，并建议将提取的帧交给视觉模型做内容理解。

cassh100k

热度 59.55

最近更新 2026-05-17 13:45:53

分类：创作依赖：代码执行 / 读写文件 / 第三方 API应用场景：视频编辑 / 图像生成 / 数据处理 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add vidiq

Metadata

name: vidiq
description: AI-powered video intelligence - download, analyze, clip, GIF from any URL. Supports YouTube, TikTok, Instagram, X. Uses ffmpeg + yt-dlp.
metadata: {"openclaw":{"emoji":"🎬","requires":{"bins":["ffmpeg","yt-dlp"]}}}

VidIQ - Video Intelligence & Query Tool

Download, understand, and manipulate any video from a URL.

Commands

# Video info (duration, resolution, codecs)
{baseDir}/scripts/vidiq.sh <url_or_path> info

# Extract N frames evenly spaced
{baseDir}/scripts/vidiq.sh <url_or_path> frames 10

# Single frame at timestamp
{baseDir}/scripts/vidiq.sh <url_or_path> frame 01:30:00

# Clip between timestamps
{baseDir}/scripts/vidiq.sh <url_or_path> clip 01:01:01 01:20:01 output.mp4

# Create GIF (start time, duration in seconds)
{baseDir}/scripts/vidiq.sh <url_or_path> gif 00:45:00 5

# Extract audio as MP3
{baseDir}/scripts/vidiq.sh <url_or_path> audio

# Detect scene changes
{baseDir}/scripts/vidiq.sh <url_or_path> scenes 0.3

# Visual mosaic (columns, total frames)
{baseDir}/scripts/vidiq.sh <url_or_path> mosaic 4 16

AI Analysis Workflow

Extract frames: vidiq.sh <url> frames 10
Feed frames to vision model for content understanding
Answer questions about the video based on frame analysis

Supported Platforms

YouTube, TikTok, Instagram, X/Twitter, any direct video URL, local files.

Notes

Downloaded videos are cached in /tmp/vidiq/ for reuse
Frames output to /tmp/vidiq/frames_*/
For long videos, extract more frames for better coverage
GIFs are optimized with palette generation for small file size