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-chaptersWrote 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-chapters)<a href="https://agentmods.dev/skills/zju-real/easel/video-chapters"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-chapters/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-chapters"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-chapters.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 | $0.00158 | $0.01090 |
| Opus 5 | $0.00079 | $0.00545 |
| Sonnet 5 | $0.00032 | $0.00218 |
| Haiku 4.5 | $0.00016 | $0.00109 |
Grade A, and why
video-chapters 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.
What it actually says
视频章节 / 时间戳目录
给中长视频生成章节时间戳目录(B站/YouTube 描述区可用)。带时间轴转录走
asr.py, 章节切分与命名由你(LLM)完成。
出成篇图文见 video-to-article;出字幕见 auto-subtitle;切成短视频见 video-highlights。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 视频文件 | 是 | 中长视频(教程/评测/讲座/直播回放;没给就问) |
| 目标平台 | 否 | B站 / YouTube / 通用(影响格式与措辞) |
| 章节数 | 否 | 期望章节数(默认按内容自然划分,通常 5-12 段) |
输出(outputs/主题名/)
chapters.txt— 时间戳目录(每行mm:ss 章节名,可直接贴描述区)chapters.json— 结构化(start 秒 + 标题),供程序化使用transcript.txt— 转录原文(备查)
执行步骤
脚本路径(相对项目根):skills/shared/scripts/asr.py。
1. 带时间轴转录
python skills/shared/scripts/asr.py transcribe -i <视频> --format json \
-o outputs/主题名/transcript.json
(首次跑 ASR 需外网代理下模型,见 auto-subtitle 前置说明。)
2. 划分章节(你来做)
读 transcript.json(每段带 start/end),按话题转折划分章节:
- 找主题切换点作为章节边界(不是均匀切时间,而是按内容)。
- 第一章从 00:00 开始(平台要求,否则章节功能不生效)。
- 每章名 6-16 字,动词开头或点明看点(如"实测续航翻车了""3 分钟教你上手"),不写"第一部分"。
- 章节数适中(太碎观众烦,太粗没用),一般 5-12 段;短视频(<3 分钟)通常不需要章节。
- 章节最短 ≥10 秒(平台 YouTube 要求相邻章节间隔 ≥10s)。
3. 输出目录
写 chapters.txt(每行 mm:ss 章节名,首行必须 00:00):
00:00 开场|今天聊什么
01:24 第一个坑:xxx
03:50 实测环节
...
同时写 chapters.json:[{"start": 0, "title": "开场|今天聊什么"}, ...]。
平台格式差异
- YouTube:贴在视频描述区,首个必须
0:00,≥3 章、每章 ≥10s 自动生效。 - B站:作为"看点/进度条章节"或分P说明,格式
mm:ss 标题。 - 通用:
chapters.txt通用可读。
规则
- 章节边界按话题转折定,不是均匀切时间。
- 首章必须 00:00;相邻章节间隔 ≥10s。
- 章节名点明看点、简洁有吸引力,不用"第一部分"这类空名。
- 不编造视频没讲的内容;依据转录如实划分。
- 产物统一进
outputs/主题名/。
参考来源
章节时间戳是 YouTube/B站 提升完播与检索的标准做法(首章 0:00、≥10s 间隔为平台硬规则)。 转录用 faster-whisper(asr.py)出时间轴,话题切分交给 LLM——确定性 IO 与语义划分分层。
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 · 75 lines · 158 tokens per session scan A 2af4df61055c
video-chapters is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed yesterday), licensed Apache-2.0. It adds 158 tokens to every session and 1,090 once invoked, about $0.0008 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…