video-highlights

video-highlights is a skill for Claude Code, Codex from ZJU-REAL/Easel. It costs 195 tokens per session (1,290 once invoked), scanned A, original, Apache-2.0.

A long-video highlight tool that finds promising moments in a recording and cuts them into separate short videos. It can choose moments from loud or energetic audio, or from transcribed content.

In plain words
What is it for?
Use it to turn livestreams, talks, knowledge videos, or sales recordings into several short clips, optionally formatted vertically for social platforms.
Why use it?
It reduces the work of searching through a livestream or long recording for clips worth publishing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python skills/shared/scripts/highlight_cut.py energy -i <长视频> \.

Good fit Use it to turn livestreams, talks, knowledge videos, or sales recordings into several short clips, optionally formatted vertically for social platforms.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ZJU-REAL/Easel
agentmods
npx agentmods add skills/zju-real/easel/video-highlights

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for video-highlights

README.md
[![agentmods](https://agentmods.dev/badge/skills/zju-real/easel/video-highlights/github.svg)](https://agentmods.dev/skills/zju-real/easel/video-highlights)
Your own site
<a href="https://agentmods.dev/skills/zju-real/easel/video-highlights"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-highlights/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for video-highlights

Your own site · 80×15
<a href="https://agentmods.dev/skills/zju-real/easel/video-highlights"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-highlights.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,290 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00195 $0.01290
Opus 5 $0.00097 $0.00645
Sonnet 5 $0.00039 $0.00258
Haiku 4.5 $0.00019 $0.00129

Measured 8d ago against content hash 89f3837adb40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

video-highlights scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/openclaw/video-highlights/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 直播录像 / 长视频(没给就问)
找点方式 能量(默认,情绪高涨处)/ 内容(转录后按金句/爆点挑)
片段数 切几条(默认 5)
每段时长 每条大约多长(默认 20s)
转竖版 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.pyenergy -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)

# 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):
    python skills/shared/scripts/asr.py transcribe -i <长视频> --format json -o /tmp/hl.json
    
  2. 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
    {"segments": [{"start": 73.2, "end": 95.0, "label": "金句:xxx"}, ...]}
    
  3. 切片:
    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。

Read the full file on GitHub · 81 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 81 lines · 195 tokens per session scan A 89f3837adb40

Subscribe to this mod's changes

video-highlights is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed today), licensed Apache-2.0. It adds 195 tokens to every session and 1,290 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

ppt-generation

Generate PPTX presentations from slide plan + content.

HezaoHezao/poirot · 13 tokens

chart-visualization

Generate charts: select type, extract data, render image.

HezaoHezao/poirot · 17 tokens

jacky-motion2-0-srt

A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.

Jackywxsz/Jacky-motion · 127 tokens

video-podcast-maker

Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…

Agents365-ai/video-podcast-maker · 214 tokens

video-podcast-maker-lite

Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…

Agents365-ai/video-podcast-maker · 96 tokens

video-podcast-maker-nano

Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…

Agents365-ai/video-podcast-maker · 163 tokens