watching-videos

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Watching videos

视频解析操作

You don't have a video input; this skill gives you one. Anything a user hands you — a YouTube link, a TikTok, a lecture, a meeting recording, a screen capture, an .mp4 on disk — goes through the same pipeline: frames (scene-aware, deduplicated), OCR, transcript (captions first, local Whisper offline fallback), all persisted into one index.

你没有视频输入渠道；本skill为你提供了这个能力。用户交给你的任何内容——YouTube链接、TikTok视频、讲座录像、会议录制文件、屏幕捕获视频或本地.mp4文件——都会经过同一处理流程：提取场景感知且去重的帧、OCR识别、转录（优先使用字幕，离线Whisper作为备用方案），所有数据都会存储到一个索引中。

Before watching: check the index

解析前：检查索引

bash

watch-skill list

If the video was already analyzed — this session or any earlier one — do NOT watch it again. Ask it directly (see the

asking-with-evidence

skill):

bash

watch-skill ask <video_id> "<question>"

bash

watch-skill list

如果该视频已被分析过——无论是本次会话还是之前的会话——请勿再次解析。直接通过索引查询（参考

asking-with-evidence

skill）：

bash

watch-skill ask <video_id> "<question>"

One video

单个视频处理

bash

watch-skill watch "<url-or-path>" [--start T --end T] [--max-frames N] [--transcript-only]

Works on any yt-dlp-supported site (1800+), direct media URLs, HLS/DASH manifests (
```
--duration 60
```
bounds live streams), and local files.
Video over ~10 minutes and the user cares about one part → use
```
--start
```
/
```
--end
```
for dense sampling of that window.
User only needs what was said →
```
--transcript-only
```
(fastest, often no video download at all).

The report prints

Indexed: <video_id>

, frames with

t=MM:SS

timestamps, OCR text, and the transcript. Read every frame path listed — in a single message, parallel Read calls — then answer from frames + OCR

transcript, citing timestamps.

bash

watch-skill watch "<url-or-path>" [--start T --end T] [--max-frames N] [--transcript-only]

支持所有yt-dlp兼容的网站（1800+个）、直接媒体URL、HLS/DASH清单（
```
--duration 60
```
可限制直播流时长）以及本地文件。
若视频时长超过约10分钟且用户仅关注其中某一部分→使用
```
--start
```
/
```
--end
```
参数对该时间段进行密集采样。
若用户仅需要视频中的语音内容→使用
```
--transcript-only
```
（速度最快，通常无需下载视频）。

处理报告将显示

Indexed: <video_id>

、带

t=MM:SS

时间戳的帧、OCR文本以及转录内容。读取所有列出的帧路径——在一条消息中并行读取——然后结合帧、OCR文本和转录内容回答问题，并标注时间戳。

Many videos (playlist, channel, folder)

批量处理多个视频（播放列表、频道、文件夹）

bash

watch-skill batch "<playlist-url-or-folder>" [--limit N]

Everything lands in the same index; one broken video never stops the rest. Afterwards a single

watch-skill search "<phrase>"

spans the whole batch.

bash

watch-skill batch "<playlist-url-or-folder>" [--limit N]

所有内容都会存入同一个索引；单个视频处理失败不会影响其他视频。处理完成后，可通过

watch-skill search "<phrase>"

在整个批量处理的内容中进行搜索。

First run on a machine

首次在设备上运行

If any command fails with a dependency error, run

watch-skill doctor

once — it installs missing ffmpeg/yt-dlp itself. No API key is required for any of this; transcription is local by default and the video file never leaves the machine.

如果任何命令因依赖项错误失败，只需运行一次

watch-skill doctor