Live Stream Clips logo

Live Stream Clips

Community
xianyu110
live-stream-clips

直播切片:从电商直播录屏中找出高光片段(按时间戳 / 按字幕关键词 / 按停顿自动提议),批量导出 9:16 竖屏切片,自动模糊填充横屏画面、烧录标题与字幕、响度标准化,并给切片写标题与开头钩子。Use when the user has a livestream recording and wants 直播切片, 切片, highlights, clips, 高光片段, repurpose a live stream into short videos for 抖音 / 视频号 / TikTok.

Overview

Publisherxianyu110
Repositoryecommerce-video-skills
Skill namelive-stream-clips
Stars
110
Forks
16
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by xianyu110 on GitHub. Read the source before you install it.

Installation

Install the Live Stream Clips AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/xianyu110/ecommerce-video-skills/tree/main/skills/live-stream-clips
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/xianyu110/ecommerce-video-skills.git /tmp/ecommerce-video-skills
mkdir -p .claude/skills
cp -r /tmp/ecommerce-video-skills/skills/live-stream-clips .claude/skills/live-stream-clips
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Live Stream Clips in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Live Stream Clips on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Live Stream Clips is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

直播切片 · Live-Stream Clips

几小时直播 → 一批 15–60 秒竖屏切片。选段可以靠人、靠字幕关键词、或靠停顿自动提议;导出统一交给 scripts/live_clip.py。

Part of ecommerce-video-skills

只切你自己的直播,或已获得主播/品牌授权的直播。

输入 Inputs

  • 直播录像(mp4/flv/mov,横屏竖屏都行)
  • 可选:字幕/转写 SRT(平台导出或用任意 ASR 工具生成)
  • 目标:每条时长、数量、要突出的商品或话题

三种选段方式

bash
# A. 已有时间戳(人工或 agent 读转写后挑选)
#    cuts.csv:  start,end,title
#               00:12:05,00:12:40,冰块放一晚还在?现场演示
python scripts/live_clip.py live.mp4 --cuts cuts.csv --outdir out/clips

# B. 按字幕关键词找片段(每个命中点向前 30% / 向后 70% 取 --window 秒,重叠自动合并)
python scripts/live_clip.py live.mp4 --srt live.srt --keywords "演示,对比,上链接,库存" --window 30 --burn-subs

# C. 没有字幕:在停顿处切分,输出候选 CSV 再人工/agent 挑选
python scripts/live_clip.py live.mp4 --propose 30 > proposals.csv

步骤 Steps

  1. 先读转写(有 SRT 时):让 agent 标出「演示、对比、用户提问被解答、福利说明」等高光点,写进 cuts.csv。
  2. 每条切片要能独立看懂:开头 3 秒必须有钩子——从「问题/演示开始」切入,而不是从主播寒暄切入。
  3. 起止点微调:起点落在句子开头、终点落在句子结束后 0.3 秒。
  4. 导出:横屏自动转 9:16(模糊背景 + 居中画面),可烧标题(title 列)和字幕(--burn-subs)。
  5. 写切片标题:用 hook-3s-script 的钩子类型给每条写 2 个标题,交给 cover-title-ab。

高光信号 What makes a good clip

信号例子
现场演示倒水、摔、对比测试
问答「有人问能不能放洗碗机…」
情绪峰值惊讶、笑场、观众刷屏
规则说明赠品、售后、发货(注意:价格/优惠信息以当前实际为准,过期切片要下架或剪掉)

提示词模板 Prompt template

text
下面是直播转写(SRT)。请找出 {8} 个适合做 {20–40} 秒竖屏切片的片段:
每段必须能独立看懂、开头 3 秒有钩子(问题/演示/结果),避免寒暄和长时间沉默;
输出 CSV:start,end,title(title ≤ 14 字,不使用绝对化用语,不承诺具体价格)。
转写:{粘贴 SRT}

检查清单 Checklist

  • 每条切片开头 3 秒有钩子、结尾不断句
  • 标题与字幕不在底部 UI 区;横屏画面完整可见
  • 切片里出现的价格/优惠/库存信息仍然有效,否则剪掉
  • 有直播内容的使用授权

常见问题与修复 Failure fixes

问题修复
--propose 只返回一段背景音乐盖住了停顿;改用 SRT 关键词法,或调低 silencedetect 的 noise 阈值
字幕与画面不同步确认 SRT 时间轴对应原始录像;脚本使用 -copyts 保持源时间轴
标题含冒号/引号报错脚本已替换为全角符号
切点在半句话用 SRT cue 的起止时间作为切点

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Live Stream Clips AI skill do?

直播切片:从电商直播录屏中找出高光片段(按时间戳 / 按字幕关键词 / 按停顿自动提议),批量导出 9:16 竖屏切片,自动模糊填充横屏画面、烧录标题与字幕、响度标准化,并给切片写标题与开头钩子。Use when the user has a livestream recording and wants 直播切片, 切片, highlights, clips, 高光片段, repurpose a live stream into short videos for 抖音 / 视频号 / TikTok.

Why use Live Stream Clips on TypingMind?

Because you install it once and use it with any model. Live Stream Clips is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Live Stream Clips in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xianyu110/ecommerce-video-skills/tree/main/skills/live-stream-clips. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Live Stream Clips?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Live Stream Clips?

As many as you like. As long as a model supports skills, you can use Live Stream Clips with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Live Stream Clips AI skill free?

Yes. It is published on GitHub by xianyu110 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇