video-highlights SKILL.md skillA

video-highlights from zju-real/easel is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add zju-real/easel/video-highlights@git:20261012.0d53744

Pins git:20261012.0d53744 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
zju-real/easel
Path
skills/builtin/video-highlights/SKILL.md
Versions recorded
1
Latest version
git:20261012.0d53744, committed Oct 12, 2026
Size
4,061 bytes
Repository stars
4,469
License
Apache-2.0

长视频 / 直播录像高光切片:从一条长视频里找出高光片段,切成多条独立短视频,可选转竖版 9:16 + 加字幕。找点两种方式——音频能量峰值(情绪高涨/欢呼/大声处)或转录后由内容判断挑金句段。当用户说 直播切片、高光切片、长视频切短、录像剪精华、切片、高光时刻、把直播剪成短视频、提取精彩片段、长视频找亮点 时使用。基于 shared/scripts/highlight_cut.py(librosa 能量分析)。与 clipify 区别:clipify 专做英文口播找笑点+动态人脸pan,本 SKILL 更通用(中文/直播皆可)、静态转竖版更稳。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 长视频 / 直播录像高光切片

> 从长视频里找高光段 → 切成多条短视频(可转竖版 + 加字幕)。切片执行走
> `skills/shared/scripts/highlight_cut.py`,**不要手拼裁切命令**——脚本已处理精确裁切、
> 前后留白、批量输出、转竖版、清单生成。

> 英文口播找笑点 + 逐段动态人脸 pan 见 **clipify**;只转画幅见 **video-reframe**;
> 字幕翻译见 **subtitle-translate**。

## 输入

| 字段 | 必填 | 说明 |
|------|------|------|
| 长视频 | 是 | 直播录像 / 长视频(没给就问) |
| 找点方式 | 否 | `能量`(默认,情绪高涨处)/ `内容`(转录后按金句/爆点挑) |
| 片段数 | 否 | 切几条(默认 5) |
| 每段时长 | 否 | 每条大约多长(默认 20s) |
| 转竖版 | 否 | 是否转 9:16 发抖音/小红书 |

## 输出(`outputs/主题名/`)

- 多条切片(`highlight_01.mp4` …)+ 清单 `highlights.json`

## 执行步骤

脚本路径(相对项目根):`skills/shared/scripts/highlight_cut.py`(`energy -h` / `cut -h`)。

### 方式 A:音频能量找点(快,适合有欢呼/情绪起伏的直播)
```bash
# 1) 找候选段
python skills/shared/scripts/highlight_cut.py energy -i <长视频> \
  --top 5 --clip-len 20 -o /tmp/hl_cand.json
# 2) 切片(可同时转竖版)
python skills/shared/scripts/highlight_cut.py cut -i <长视频> \
  --segments /tmp/hl_cand.json -o outputs/video-highlights \
  --reframe 9:16 --reframe-mode blur
```

### 方式 B:内容找点(准,适合口播/知识/带货,挑金句爆点)
1. 先转录(复用 auto-subtitle 的 `asr.py`,带时间轴):
   ```bash
   python skills/shared/scripts/asr.py transcribe -i <长视频> --format json -o /tmp/hl.json
   ```
2. **你**读转录,挑出 3-5 个最有价值/最抓人的片段(完整语义段,别切半句),
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add zju-real/easel/video-highlights@sha256:89f3837adb405c12

The line at the top of this page pins the label git:20261012.0d53744, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6c73e5fe4mvdcw7k.svg)](https://markdownregistry.com/a/art_6c73e5fe4mvdcw7k)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 12, 2026.

versioncommittedcommitsizeaudit
git:20261012.0d53744 latest2026-10-12 0d53744 4,061 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4061 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

zju-real/easel · 4,469 stars · license Apache-2.0 · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6c73e5fe4mvdcw7k
GET https://markdownregistry.com/api/v1/resolve?ref=zju-real/easel/video-highlights
GET https://markdownregistry.com/api/v1/blob/89f3837adb405c120c0f74acb9553a0c8f1704a2c930bd4bf169312e2d6dfca7

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from zju-real/easel

AGENTS.md@agents/workspace AGENTS.md file
zju-real/easel · agents/workspace/AGENTS.md
git:20261023.a097ddf · audit B · 4,469 stars
ai-image-gen SKILL.md skill
zju-real/easel · skills/builtin/ai-image-gen/SKILL.md · 通用 AI 生图:文生图 / 图生图 / 图像变体。当用户说 AI 生图、AI 画图、文生图、图生图、生成图片、生成配图、图像生成、AI 出图、AI 作图、换图、改图、图像编辑、给我画一张、生成一张图 时使用。支持 OpenAI 兼容…
git:20261012.0d53744 · audit A · 4,469 stars
ai-music SKILL.md skill
zju-real/easel · skills/builtin/ai-music/SKILL.md · AI 音乐 / BGM 生成:给短视频、社媒内容生成原创背景音乐 / 配乐 / 纯音乐。通过可插拔 provider(阿里 DashScope / Suno 类第三方…
git:20261018.8d08b21 · audit A · 4,469 stars
ai-video-gen SKILL.md skill
zju-real/easel · skills/builtin/ai-video-gen/SKILL.md · AI 视频生成:文生视频 / 图生视频 / 数字人首帧驱动。通过可插拔 provider(通义万相 Wan / 火山 Seedance / 快手可灵 / OpenAI 兼容)异步生成视频,用户自备 API key。当用户说 AI…
git:20261012.0d53744 · audit A · 4,469 stars
asset-manager SKILL.md skill
zju-real/easel · skills/builtin/asset-manager/SKILL.md · outputs/ 目录下的产物管理:按日期/平台/类型归档、打标签、搜索历史内容、生成素材清单。 当用户说"整理素材"、"归档"、"找之前的内容"、"搜索历史"、"素材管理"、 "outputs 整理"、"之前做的"时使用。 与其他…
git:20261012.0d53744 · audit A · 4,469 stars
audio-denoise SKILL.md skill
zju-real/easel · skills/builtin/audio-denoise/SKILL.md · 音频降噪:去除录音中的背景噪声、电流声、风噪、嗡嗡声,基于 ffmpeg 滤镜链(afftdn/highpass/lowpass)。 当用户说"降噪""去噪""去杂音""消除背景噪声""电流声""风噪""录音有杂音""音频降噪"时使用。…
git:20261012.0d53744 · audit A · 4,469 stars
audio-editing SKILL.md skill
zju-real/easel · skills/builtin/audio-editing/SKILL.md · 通用音频处理:音频剪辑/裁剪、格式转码(mp3/wav/m4a/aac)、音量归一化、从视频提取音轨、多段拼接、淡入淡出、变速(保音高)。当用户说“剪音频”“裁一段”“转成…
git:20261012.0d53744 · audit A · 4,469 stars
audio-mix SKILL.md skill
zju-real/easel · skills/builtin/audio-mix/SKILL.md · 音频混合 / 混音:把旁白口播 + 背景音乐 + 音效混成一轨,BGM 自动循环补足并可闪避(旁白说话时自动压低 BGM 保证人声清晰)。当用户说 混音、音频混合、旁白加背景音乐、配音加BGM、人声和音乐混一起、加音效、音频叠加、BGM…
git:20261025.5a597e5 · audit A · 4,469 stars
audio-visualizer SKILL.md skill
zju-real/easel · skills/builtin/audio-visualizer/SKILL.md · 音频可视化视频:把纯音频(播客片段、音乐、口播金句、电台)渲染成带动态波形/频谱的视频,配封面和标题,好发到抖音/B站/视频号等只收视频的平台。当用户说…
git:20261012.0d53744 · audit A · 4,469 stars
auto-short-video SKILL.md skill
zju-real/easel · skills/builtin/auto-short-video/SKILL.md · 一句话主题 → 成品短视频:自动串联 文案→配图/AI视频→配音→字幕→BGM→合成,把 Easel 制作层零件编排成一条'一键出片'流水线。**单条视频、口播/资讯向,画面默认逐句配图 + Ken Burns…
git:20261025.5a597e5 · audit A · 4,469 stars
auto-subtitle SKILL.md skill
zju-real/easel · skills/builtin/auto-subtitle/SKILL.md · 自动字幕 / 语音转字幕:把音频或视频里的语音识别成字幕文件(SRT/ASS/TXT/JSON),可选把字幕烧录进视频。当用户说自动字幕、语音转字幕、视频加字幕、上字幕、转录、听写、字幕文件、生成字幕、烧字幕时使用。
git:20261012.0d53744 · audit A · 4,469 stars
batch-process SKILL.md skill
zju-real/easel · skills/builtin/batch-process/SKILL.md · 批量处理:对一个目录里的一批图片/视频/音频统一套用同一操作——批量压缩、加水印、转格式、缩放、转比例、音量归一化等。当用户说 批量处理、批量压缩、批量加水印、批量转格式、一批图片/视频、给这个文件夹、全部转成、批量缩放、批量转竖版、整个目…
git:20261012.0d53744 · audit A · 4,469 stars

Every file in zju-real/easel

Browse by kind, by grade A, or by owner.