Agent skill

Video Highlights

by ZJU-REAL in ZJU-REAL/Easel

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…

Apache-2.0Auto-check passed

Install Video Highlights

skills CLI
$ npx skills add ZJU-REAL/Easel --skill video-highlights -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZJU-REAL/Easel video-highlights --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw/video-highlights .claude/skills/video-highlights && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
video-highlights
GitHub stars
3.4k
Token cost
~588 tokens
SKILL.md length
113 words
Files
1
Skills in repo
114
Repo updated
First seen
Licence
Apache-2.0

At a glance

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…

  • Works in 3 steps: 先转录(复用 auto-subtitle 的 asr.py,带时间轴) → 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), → 切片
  • SKILL.md covers 输入, 输出(outputs/主题名/), 执行步骤 and Profile 感知, plus 2 more sections
  • Calls python

What it does

Video Highlights is an agent skill from ZJU-REAL/Easel. 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/highlightcut.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。

Its SKILL.md is about 590 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的… The licence is Apache-2.0.

Example prompts

  • “/video-highlights”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. 先转录(复用 auto-subtitle 的 asr.py,带时间轴)
  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),
  3. 切片

What it can do on your machine

Read from SKILL.md and the folder at commit 278f420. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Video Highlights loads about 588 tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 113 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~588

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ZJU-REAL/Easel at commit 278f420, republished under its Apache-2.0 licence (© ZJU-REAL). 113 words, ~588 tokens.

Download SKILL.mdSave it as .claude/skills/video-highlights/SKILL.md (or your agent's skills folder).
name
video-highlights
description
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。
layer
produce

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), 写成切片清单 /tmp/hl_segs.json:
    json
    {"segments": [{"start": 73.2, "end": 95.0, "label": "金句:xxx"}, ...]}
  3. 切片:
    bash
    python skills/shared/scripts/highlight_cut.py cut -i <长视频> \
      --segments /tmp/hl_segs.json -o outputs/video-highlights --reframe 9:16

--pad 0.3 每段前后留白避免切太紧;不转竖版就去掉 --reframe。

Profile 感知

  • 有 Profile:转竖版比例按 platforms.md 主平台;找点侧重贴合账号定位(带货看爆点、 知识看金句、娱乐看情绪高潮);切片时长贴合平台(抖音 15-30s,视频号 30-60s)。
  • 无 Profile:默认能量找点 top5、每段 20s,询问是否转竖版。

规则

  1. 内容找点务必切完整语义段,不要从半句话切进/切出。
  2. 能量找点适合有明显情绪起伏的素材;平淡口播优先用内容找点(方式 B)。
  3. 切片默认前后各留 0.3s 白,避免开头/结尾被切掉。
  4. 转竖版口播类建议 --reframe-mode smart(人脸居中),其它用 blur(不丢画面)。
  5. 产物统一进 outputs/主题名/,附 highlights.json 清单。

参考来源

音频能量选段用 librosa RMS 峰值(贪心去重保证峰间隔);内容选段沿用 opus-clip 式"转录→挑金句" 思路但交给 LLM 判断。切片/转竖版复用确定性脚本,保证时间轴与画幅不出错。

© ZJU-REAL, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/openclaw/video-highlights of ZJU-REAL/Easel.

Open the folder on GitHubat commit 278f420

Compare with similar skills

Video Highlights next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Video Highlights compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Video Highlights this skillZJU-REAL/Easel3.4k—~588Automated safety check: PassApache-2.0
Pierre Highlightspierrecomputer/pierre6.3k—~409Automated safety check: PassApache-2.0
Highlightxenodium/emacs-skills143—~395Automated safety check: PassNone
Molcell Highlightsbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.4kAutomated safety check: PassMIT
Sports Highlight EditorLeoYeAI/openclaw-master-skills2.2k—~4.1kAutomated safety check: PassMIT
Academic Highlight Generatoraipoch/medical-research-skills1.9k—~1.5kAutomated safety check: PassMIT

Similar skills

  • Pierre Highlights

    pierrecomputer/pierre

    Shows how to use @pierre/highlights for syntax-highlighted HTML or tokens, streaming and incremental tokenizing, and Zed-compatible themes with CSS variables.

    6.3k GitHub stars~409 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Highlight

    xenodium/emacs-skills

    This skill should be used when the user invokes "/highlight" to highlight relevant regions in one or more files in Emacs via emacsclient.

    143 GitHub stars~395 tokensUpdated 2 mo ago
    Auto-check passed
  • Molcell Highlights

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses to produce the three signature Cell Press front-matter artifacts for Molecular Cell — Highlights (3–4 bullets, each ≤85 characters), the eTOC/In Brief blurb (~50 words…

    1.2k GitHub stars~1.4k tokensUpdated 14 days ago
    Media & CreativeAuto-check passed
  • Sports Highlight Editor

    LeoYeAI/openclaw-master-skills

    The sports-highlight-editor skill analyzes raw game footage and automatically identifies peak moments — goals, dunks, sprints, saves, and crowd reactions — then assembles them into a polished…

    2.2k GitHub stars~4.1k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed
  • Academic Highlight Generator

    aipoch/medical-research-skills

    Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content.

    1.9k GitHub stars~1.5k tokensUpdated 24 days ago
    Documents & OfficeAuto-check passed
  • Highlight Images

    rweekly/rweekly.org

    Find, download, resize, and embed images for the three Highlight links in draft.md.

    826 GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check: notes

More from ZJU-REAL/Easel

All 114 skills in this repo
  • Gzh Design

    ZJU-REAL/Easel

    微信公众号文章排版引擎:把 Markdown / Word(.docx) / PDF / 纯文本转成可直接粘贴进公众号编辑器的 HTML,自动章节编号、关键词标记、引言卡、目录、代码块、图片/GIF、作者签名;主题从 references/theme-index.md…

    3.4k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • 微信公众号文章自动创作与发布工具。给定参考文章、文字或文档,自动搜索整理全网相关信息、生成图文并茂的公众号文章,并发布到微信公众号草稿箱。特别强调反 AI 检测写作。

    3.4k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Card Design

    ZJU-REAL/Easel

    社媒卡片视觉设计系统:提供配色、中文字体层级、满画幅布局、品类骨架和死空白/密度质检,避免模板化 PPT 与廉价 AI 感。

    3.4k GitHub stars~657 tokensUpdated today
    Auto-check passed
  • Ecom Details Image

    ZJU-REAL/Easel

    生成电商商品视觉方案:主图概念、场景图、详情页视觉方向和 AI 生图 Prompt. An agent skill from ZJU-REAL/Easel.

    3.4k GitHub stars~1.1k tokensUpdated today
    Auto-check: notes
  • Infographic

    ZJU-REAL/Easel

    将数据或文字内容转化为可视化信息图,支持静态(AntV)和动画 GIF 两种模式。当用户需要制作信息图、数据可视化、流程图、对比图、动画图表、GIF 图表、思维导图、SWOT 分析图时调用。本地渲染信息图/GIF 动画;要单张静态图片 URL 用 chart-visualization,要 CSV/JSON→整页报告用 data-report

    3.4k GitHub stars~643 tokensUpdated today
    Auto-check passed
  • Novel Writer

    ZJU-REAL/Easel

    长篇小说/网文连载创作:从世界观、人设和三级大纲写到逐章正文,并用文件化状态维护伏笔、前情和跨章一致性. An agent skill from ZJU-REAL/Easel.

    3.4k GitHub stars~1k tokensUpdated today
    Auto-check passed

Questions about Video Highlights

What does Video Highlights do?

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…. Video Highlights is an agent skill from ZJU-REAL/Easel.

How do I install Video Highlights in Claude Code?

Run `npx skills add ZJU-REAL/Easel --skill video-highlights -a claude-code`. Or copy the skill folder (skills/openclaw/video-highlights in ZJU-REAL/Easel) into .claude/skills/video-highlights in your project. Claude Code loads it when a task matches its description.

How do I install Video Highlights in Codex?

Run `npx skills add ZJU-REAL/Easel --skill video-highlights -a codex`. Or copy the skill folder (skills/openclaw/video-highlights in ZJU-REAL/Easel) into .agents/skills/video-highlights in your project. Codex loads it when a task matches its description.

Can I use Video Highlights in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZJU-REAL/Easel --skill video-highlights -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-highlights, .gemini/skills/video-highlights, .github/skills/video-highlights and .opencode/skills/video-highlights in your project.

What does Video Highlights need to run?

Going by SKILL.md and its folder, Video Highlights needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Video Highlights access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Video Highlights safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Video Highlights use?

Video Highlights is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Video Highlights use?

About 588 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Video Highlights?

Skills that share tags, products or a category with Video Highlights: Pierre Highlights (pierrecomputer/pierre, 6.3k stars), Highlight (xenodium/emacs-skills, 143 stars), Molcell Highlights (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars) and Sports Highlight Editor (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Video Highlights?

ZJU-REAL (a GitHub organization) maintains it in ZJU-REAL/Easel, which has 3,376 GitHub stars. The repository holds 114 skills in this directory. The repository was last updated on October 9, 2026.

Source: ZJU-REAL/Easel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.