agentleFS
yfgeyfge/video-skills-suite/skills/insight-extractor/SKILL.md

insight-extractor

Skill1 starsChanged 9 months agoMITView on GitHub

从长文本(直播文稿、会议记录、播客转录、文章)中提炼核心观点、金句、争议点和行动项。输出结构化的观点摘要,可直接供 article-forge 等下游 skill 使用。适用于:直播回放分析、会议纪要提炼、长文精读、内容策划前的素材整理。

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. glebis/claude-skills★ 410same name
    2. tezansahu/ai-garage★ 16same name
    3. JAVICHILEON/claude---Skills★ 0same name
    4. KISHOR403/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

Files
SKILL.md

Insight Extractor — 长文本观点提炼

输入

接受任何长文本:

  • 直播/会议转写稿(video-to-text 输出的 .txt)
  • 播客文字版
  • 长文章、研报
  • 任意需要提炼的文本素材

提炼流程

Step 1: 通读全文,建立框架

快速扫描全文,识别:

  • 参与者:有几位说话人?各自角色/立场是什么?
  • 话题边界:讨论了哪几个大的话题?大约在什么时间段?
  • 情绪/态度变化:哪些地方有争论、兴奋、犹豫?

Step 2: 按话题分段提炼

对每个话题段落,提取:

核心论点 (Key Arguments)

  • 每位说话人的核心主张是什么?
  • 用一句话概括每个论点
  • 标注论据类型:经验/数据/类比/假设

金句 (Quotable Quotes)

  • 原话引用,保留口语感
  • 优先选:有画面感的、反直觉的、能引发讨论的
  • 标注说话人和大致时间戳

争议点 (Debates & Tensions)

  • 哪些观点有分歧?
  • 双方各自的理由是什么?
  • 最终是否达成共识?

行动项 (Action Items)

  • 提到了哪些具体的下一步?
  • 谁负责?什么时间?

Step 3: 输出结构化摘要

输出格式(Markdown):

# 观点摘要:<标题>

## 元信息
- 来源:<文件路径或名称>
- 时长/字数:<>
- 参与者:<说话人列表及角色>
- 日期:<>

## 话题概览
1. <话题1名称> — 一句话总结
2. <话题2名称> — 一句话总结
...

## 详细观点

### 话题1:<名称>

**核心论点:**
- [说话人A] <论点> — <论据类型>
- [说话人B] <论点>

**金句:**
> "原话引用" — 说话人, [MM:SS]

**争议:**
- <分歧描述>

---
(重复每个话题)

## 行动项
- [ ] <具体事项> — 负责人, 时间

## 整体洞察
- <3-5 条跨话题的高层洞察>
- <这些讨论对行业/团队/读者意味着什么>

Step 4: 存档

保存到 workspace/insights/ 目录:

  • 命名:<来源简称>-insights.md(如 直播0226-insights.md)

提炼原则

  1. 保留原味:金句用原话,不美化不总结。口语的力量在于真实。
  2. 区分事实和观点:某人说"我觉得 X 会取代 Y"是观点,不是事实。
  3. 抓冲突和转折:观点一致的地方一笔带过,有争论的地方展开。
  4. 不补脑:文本里没说的,不要推断。不确定的标注"待确认"。
  5. 聚焦可行动:优先提炼能变成文章、决策、行动的内容。

长文本处理策略

  • < 30K 字:一次性读取,直接提炼
  • 30K - 100K 字:分 3-5 段读取,逐段提炼后汇总
  • > 100K 字:先用 grep/搜索定位关键段落,重点提炼

与其他 Skill 的衔接

  • 上游:video-to-text(提供转写稿)
  • 下游:article-forge(消费观点摘要,生成文章)
  • 观点摘要的 ## 详细观点 和 ## 整体洞察 是 article-forge 的主要输入

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.