According to AlphaMoat, as of 2026-09, Video-Watch has 4,352 downloads and 8 stars — ranked #2,255 of 5,078 AI skills overall, and #221 of 512 in Design & Media.

Installs

152

Downloads

4.4K

Stars

Overall Rank

#2,255

Top 45% overall · Top 44% in Design & Media

Platform	Installs	Downloads	Stars	Comments
ClawHub ↗	141	4.2K	6	-
SkillHub ↗	152	4.4K	8	—

Platforms count differently and update at different times.

What this skill does

The script exports numbered images at a chosen frame rate and reports metadata such as duration, resolution, and frame count. A separate image-reading tool can then inspect key frames. ffmpeg must be installed locally. Confirm the video and output path before processing. The source reports unsafe argument and output handling. Use trusted video paths, a reviewed numeric fps and a private non-shared output directory; inspect existing files and overwrite behavior before execution. Do not process attacker-controlled inputs until handling is fixed.

Profile published 2026-10-27

What you can do with it

Create reviewable frames from a video that cannot be played directly
Sample scene changes, captions, or visible UI elements
Inspect metadata such as video duration, resolution, and frame count

When to use it

When you need to inspect a video visually frame by frame or by sampling
When ffmpeg is installed and the output directory is confirmed

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Extract key frames from this video and summarize only what is visibly present in them; do not infer audio or unseen events.

Monthly Trend

Downloads4.4K

Stars8

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

Month	Downloads	MoM	Stars
2026-09	4.4K	—	8
2026-08	4.1K	+4.6%	8
2026-07	3.9K	+8.8%	8
2026-06	3.6K	+5.0%	6
2026-05	3.4K	—	7
2026-03	2.7K	—	6

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

1.9 KB · ClawHub v1.0.0

---
name: video-analyzer
description: Analyze video content by extracting frames at regular intervals. Use when you need to understand what's in a video file, review video content, analyze scenes, or describe video without being able to play it directly. Supports MP4, MOV, AVI, MKV, and other common video formats.
---

# Video Analyzer

Analyze video files by extracting frames at 1-second intervals using ffmpeg, then examining the frames to understand the video content.

## Prerequisites

Show all (59 lines)


Requires `ffmpeg` installed on the system. Install if missing:

```bash
# Ubuntu/Debian
sudo apt-get install -y ffmpeg

# macOS
brew install ffmpeg
```

## Usage

### Extract frames from video

```bash
scripts/extract_frames.sh <video_path> [output_dir] [fps]
```

**Arguments:**
- `video_path` (required): Path to the video file
- `output_dir` (optional): Directory for extracted frames. Default: creates `frames_<video_name>` in current directory
- `fps` (optional): Frames per second to extract. Default: 1 (one frame per second)

**Example:**
```bash
scripts/extract_frames.sh /path/to/video.mp4
scripts/extract_frames.sh /path/to/video.mp4 ./my_frames
scripts/extract_frames.sh /path/to/video.mp4 ./my_frames 2  # 2 frames per second
```

**Output:**
- Creates numbered frame images: `frame_001.jpg`, `frame_002.jpg`, etc.
- Prints video metadata (duration, resolution, frame count)

## Workflow

1. Run `extract_frames.sh` on the video file
2. Read key frames using the `read` tool to view images
3. For comprehensive analysis, sample frames at regular intervals (e.g., every 5th frame)
4. Describe what you see in each frame to build understanding of the video

## Tips

- For short videos (<1 min): Review all frames
- For medium videos (1-5 min): Sample every 3-5 frames
- For long videos (>5 min): Sample every 10+ frames, focus on scene changes
- Look for: scene transitions, text/titles, UI elements, actions, characters