letmewatch — Claude Code plugin: video analysis and install
letmewatch samples video at scene changes and gives Claude timestamped frames to inspect. Use it to trace a bug in a screen recording or review an app flow.
MIT ★ 9 updated 2026-06-13
/plugin marketplace add anthropics/claude-plugins-community
/plugin install letmewatch@claude-communityWhat letmewatch does
The plugin runs ffmpeg scene detection to select frames where the picture changes, then sends them to Claude in batches. Timestamped frames help Claude describe when an error appears and what happened beforehand. If the clip contains very few scene changes, letmewatch switches to sampling at regular intervals.
ffmpeg must be installed for frame extraction to work. Audio transcription is available when whisper or mlx-whisper is installed; otherwise, Claude can still inspect the images. The commands analyze a given video, process the latest video in a configured folder, or change that folder.
What it helps with
- locate an error in a screen recording
- trace user actions before a bug appears
- review the sequence of screens in an app flow
- turn a video tutorial into a written summary
Example prompts for the agent
- Inspect
~/Desktop/bug-recording.movand identify when the error appears:/letmewatch:video ~/Desktop/bug-recording.mov. - Analyze the latest video in the configured folder:
/letmewatch:video-last. - Set the video folder to
~/Videos:/letmewatch:video-dir ~/Videos.
How to install letmewatch
Plugin marketplace
/plugin marketplace add anthropics/claude-plugins-community/plugin install letmewatch@claude-communityStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about letmewatch
How do I install letmewatch in Claude Code?
Add the marketplace with /plugin marketplace add anthropics/claude-plugins-community, then install the plugin with /plugin install letmewatch@claude-community. Install ffmpeg first so the plugin can extract frames.
What does letmewatch do?
It selects frames around visual scene changes, timestamps them, and sends them to Claude for analysis. With whisper or mlx-whisper installed, it can transcribe the video's audio too.
Does letmewatch need Whisper?
No. ffmpeg is required for frame extraction; whisper and mlx-whisper are optional and enable audio transcription.
Source text
SKILL.md · MIT
<div align="center">
<br>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://img.shields.io/badge/Claude_Code_Plugin-8B5CF6?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJub25lIiBzdHJva2U9IndoaXRlIiBzdHJva2Utd2lkdGg9IjIiIHN0cm9rZS1saW5lY2FwPSJyb3VuZCIgc3Ryb2tlLWxpbmVqb2luPSJyb3VuZCI+PHBvbHlnb24gcG9pbnRzPSIyMyA3IDEyIDIgMSA3IDEgMTcgMTIgMjIgMjMgMTciLz48cG9seWxpbmUgcG9pbnRzPSIxIDcgMTIgMTIgMjMgNyIvPjxsaW5lIHgxPSIxMiIgeTE9IjIyIiB4Mj0iMTIiIHkyPSIxMiIvPjwvc3ZnPg==">
<img alt="Claude Code Plugin" src="https://img.shields.io/badge/Claude_Code_Plugin-8B5CF6?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJub25lIiBzdHJva2U9IndoaXRlIiBzdHJva2Utd2lkdGg9IjIiIHN0cm9rZS1saW5lY2FwPSJyb3VuZCIgc3Ryb2tlLWxpbmVqb2luPSJyb3VuZCI+PHBvbHlnb24gcG9pbnRzPSIyMyA3IDEyIDIgMSA3IDEgMTcgMTIgMjIgMjMgMTciLz48cG9seWxpbmUgcG9pbnRzPSIxIDcgMTIgMTIgMjMgNyIvPjxsaW5lIHgxPSIxMiIgeTE9IjIyIiB4Mj0iMTIiIHkyPSIxMiIvPjwvc3ZnPg==">
</picture>
# letmewatch
### Give Claude eyes for video.
[](https://readme.cash/c/4y5sxs7pbj)
Extract key frames with scene detection.<br>
Claude sees every meaningful moment — and skips the rest.
<br>
<table>
<tr>
<td align="center"><strong>1</strong><br><sub>Skill</sub></td>
<td align="center"><strong>3</strong><br><sub>Commands</sub></td>
<td align="center"><strong>Scene<br>Detection</strong><br><sub>via ffmpeg</sub></td>
<td align="center"><strong>Audio</strong><br><sub>via whisper</sub></td>
</tr>
</table>
<br>
```
/plugin marketplace add BinyaminEden/letmewatch
```
<br>
[View on GitHub](https://github.com/BinyaminEden/letmewatch) · [Report Issue](https://github.com/BinyaminEden/letmewatch/issues)
</div>
---
## What it does
You send Claude a video. Claude **watches** it.
```
You: /letmewatch:video ~/Desktop/bug-recording.mov
Claude: Extracting frames... 15 scene changes detected.
At 00m00s: The app loads with the dashboard view.
At 00m12s: User clicks "Submit".
At 00m13s: Loading spinner appears.
At 00m18s: Error toast — "Failed to save" (500).
At 00m23s: Form resets, user input is lost.
The bug: API returns 500 on submit, and the form
clears input instead of preserving it.
```
Instead of processing video natively, letmewatch uses **ffmpeg scene detection** — it only captures frames where the visuals actually change. No idle screens, no wasted frames.
- A 2-minute screen recording → ~15-20 frames
- Static moments → skipped entirely
- Every frame → timestamped (`frame_01m23s.jpg`)
- Audio → transcribed if whisper is installed
## Install
### 1. Install ffmpeg (required)
```bash
# macOS
brew install ffmpeg
# Ubuntu/Debian
sudo apt install ffmpeg
# Windows
winget install ffmpeg
# or: choco install ffmpeg
```
### 2. Install the plugin
**Via marketplace** (recommended):
```
/plugin marketplace add BinyaminEden/letmewatch
/plugin install letmewatch@letmewatch
```
**Via local clone:**
```bash
git clone https://github.com/BinyaminEden/letmewatch.git ~/letmewatch
# Then in Claude Code:
/plugin install --path ~/letmewatch
```
### 3. Optional: Audio transcription
```bash
# Standard
pip install openai-whisper
# Apple Silicon (faster)
pip install mlx-whisper
```
## Commands
| Command | What it does |
|---|---|
| `/letmewatch:video <path>` | Analyze a specific video file |
| `/letmewatch:video-last` | Analyze the most recent video in your configured folder |
| `/letmewatch:video-dir <path>` | Set/change where `video-last` looks for videos |
## How it works
### Scene detection
The plugin uses ffmpeg's scene detection filter to find frames where visuals change:
```
ffmpeg -vf "select='gt(scene,0.1)'" ...
```
This captures page navigations, modal dialogs, form submissions, error states, tab switches — any meaningful UI change. Static moments produce zero frames.
### Smart fallbacks
If scene detection finds fewer than 3 changes (e.g., a very static video or gradual scrolling), it automatically falls back to extracting frames at regular intervals:
| Video length | Interval |
|---|---|
| < 30 seconds | Every 2s |
| 30s – 3 min | Every 5s |
| > 3 min | Every 10s |
### Frame processing
- Resized to **720p JPEG** (~50-80KB each)
- Capped at **40 frames** per video
- Viewed in **batches of 8** to stay within context limits
- **Timestamped** in filenames for easy reference
### Audio transcription
If [whisper](https://github.com/openai/whisper) or [mlx-whisper](https://github.com/ml-explore/mlx-examples/tree/main/whisper) is installed, the plugin extracts and transcribes audio automatically. Claude sees both the visual frames and the spoken content.
## Configuration
**Video directory:** The first time you run `video-last`, it asks where your videos live and saves it to `~/.claude/video.conf`. Change it anytime with `video-dir`.
**Scene threshold:** Default is `0.1` (10% pixel change). Lower = more sensitive, higher = fewer frames.
## Use cases
- **Bug reports** — Record the bug, share the video, get a diagnosis with timestamps
- **UI review** — Show Claude your app flow, get design feedback
- **Code walkthroughs** — Record a tutorial, get a written summary
- **Screen recordings** — Anything you'd screenshot, but as a video
## License
MIT — [Binyamin Eden](https://github.com/BinyaminEden)
© BinyaminEden · MIT · BinyaminEden/letmewatch