Updated 1mo ago
by xinhailaopo
video-watch-plus
让 Agent 既看得见视频也听得见声音的 DSH 技能:声学侦察判定有无人声、ASR 幻觉证伪、三路互校,含 Windows 一键环境与上游兼容性修补。
21 GitHub stars (21)
+9 in 18 days
| Period | New stars |
|---|---|
| Oct 27 | +4 |
| Oct 28 | 0 |
| Oct 29 | 0 |
| Oct 30 | +1 |
| Oct 31 | 0 |
| Nov 1 | 0 |
| Nov 2 | 0 |
| Nov 3 | +1 |
| Nov 4 | +1 |
| Nov 5 | 0 |
| Nov 6 | 0 |
| Nov 7 | 0 |
| Nov 8 | 0 |
| Nov 9 | 0 |
| Nov 10 | 0 |
| Nov 11 | 0 |
| Nov 12 | +1 |
| Nov 13 | +1 |
- 1 skill (1 skills found in its SKILL.md files)
- 0 forks (0 forks)
- 1mo ago last update (Last updated 1mo ago)
Install
Skills CLI
npx skills add xinhailaopo/video-watch-plus
Asks which agents to install it for. Add -g to install it for every project.
Claude Code
git clone https://github.com/xinhailaopo/video-watch-pluscp -r "video-watch-plus" ~/.claude/skills/video-watch-plus
Copies the video-watch-plus skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project).
Plugin
/plugin marketplace add xinhailaopo/video-watch-plus
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
video-watch-plus
看视频与听声音:把视频/GIF/录屏同时翻译成「可核算的图版序列」与「可信度经过检验的音轨结论」,产出带时间戳的观看交付。视觉侧 ffmpeg 逐帧量测(切点/冻结/运动/像素突变/静音)→ 骨架优先采样 → 图版与位置映射 → 画面文字裁切放大读取;听觉侧先做声学侦察判定有无语音,再做 ASR 转写并做幻觉证伪;最后三路证据互校。含 Windows 一键环境安装与上游 vw.py 的两处 Windows 缺陷修补。Invoke when 用户要求看视频/看动图/分析录屏/GIF 拆帧/视频里发生了什么/某时刻画面是什么/把视频里的文字或语音转写出来/这条音轨里有没有人说话。
SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.