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.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/video-highlightsWrote 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.
[](https://agentmods.dev/skills/zju-real/easel/video-highlights)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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 | 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)
# 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)
- 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 - 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:{"segments": [{"start": 73.2, "end": 95.0, "label": "金句:xxx"}, ...]} - 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
- 内容找点务必切完整语义段,不要从半句话切进/切出。
- 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)。
- 切片默认前后各留 0.3s 白,避免开头/结尾被切掉。
- 转竖版口播类建议
--reframe-mode smart(人脸居中),其它用blur(不丢画面)。 - 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。
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.
- 8d ago First seen · 81 lines · 195 tokens per session scan A 89f3837adb40
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.
Other skills, from other repositories
ppt-generation
Generate PPTX presentations from slide plan + content.
chart-visualization
Generate charts: select type, extract data, render image.
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.
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…
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…
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…