solo-you2idea-extract

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/you2idea-extract

Extract startup ideas from YouTube videos. Two operating modes depending on available tools.

从YouTube视频中提取创业想法。根据可用工具分为两种运行模式。

Mode Detection

模式检测

Check which tools are available:

With solograph MCP: use

source_search

source_list

source_tags

source_related

for indexed corpus

Without MCP (standalone): use yt-dlp + Read for transcript analysis

检查可用工具：

有solograph MCP时：对已索引的语料库使用
```
source_search
```
、
```
source_list
```
、
```
source_tags
```
、
```
source_related
```
无MCP（独立模式）时：使用yt-dlp + Read进行字幕分析

MCP Tools (if available)

MCP工具（若可用）

```
source_search(query, source="youtube")
```
— semantic search over indexed videos
```
source_list()
```
— check indexed video counts
```
source_tags()
```
— auto-detected topics with confidence scores
```
source_related(video_url)
```
— find related videos by shared tags
```
kb_search(query)
```
— cross-reference with knowledge base
```
web_search(query)
```
— discover new videos to index

```
source_search(query, source="youtube")
```
— 对已索引视频进行语义搜索
```
source_list()
```
— 查看已索引视频数量
```
source_tags()
```
— 自动检测主题及置信度评分
```
source_related(video_url)
```
— 通过共享标签查找相关视频
```
kb_search(query)
```
— 与知识库进行交叉引用
```
web_search(query)
```
— 发现新视频进行索引

Steps

步骤

Mode 1: Index + Analyze (with solograph MCP)

模式1：索引+分析（有solograph MCP时）

Parse input from
```
$ARGUMENTS
```
:
- URL (
```
https://youtube.com/watch?v=...
```
  ) → single video index
- Channel name (
```
GregIsenberg
```
  ) → channel batch index
- Query text → search existing corpus (skip to step 4)
- If empty, ask: "Video URL, channel name, or search query?"

Index video(s) via solograph:

bash

# Install if needed
pip install solograph  # or: uvx solograph

# Single video
solograph-cli index-youtube -u "$URL"

# Channel batch (needs web search for discovery)
solograph-cli index-youtube -c "$CHANNEL" -n 5

Verify indexing —
```
source_list()
```
to confirm new video count.
```
source_tags()
```
for topic distribution.

Search corpus —

source_search(query="startup ideas", source="youtube")

Cross-reference —
```
kb_search(query)
```
for related existing opportunities (if knowledge base available).
Extract insights — for each relevant video chunk:
- Identify the startup idea mentioned
- Note timestamp and speaker context
- Rate idea potential (specificity, market evidence, feasibility)
- Flag ideas that match trends or validated patterns
Write results to
```
docs/youtube-ideas.md
```
or print summary.

解析输入：从
```
$ARGUMENTS
```
中获取输入：
- URL（
```
https://youtube.com/watch?v=...
```
  ）→ 单视频索引
- 频道名称（
```
GregIsenberg
```
  ）→ 频道批量索引
- 查询文本 → 搜索现有语料库（直接跳到步骤4）
- 若输入为空，询问：“请提供视频URL、频道名称或搜索查询？”

通过solograph索引视频：

bash

# 若需要则安装
pip install solograph  # 或：uvx solograph

# 单视频
solograph-cli index-youtube -u "$URL"

# 频道批量索引（需网页搜索发现视频）
solograph-cli index-youtube -c "$CHANNEL" -n 5

验证索引结果 — 使用
```
source_list()
```
确认新增视频数量。使用
```
source_tags()
```
查看主题分布。

搜索语料库 — 执行

source_search(query="startup ideas", source="youtube")

。

交叉引用 — 若有知识库，使用
```
kb_search(query)
```
查找相关的现有机会。
提取洞察 — 针对每个相关视频片段：
- 识别提及的创业想法
- 记录时间戳和发言者上下文
- 评估创意潜力（具体性、市场证据、可行性）
- 标记符合趋势或已验证模式的创意
输出结果 — 将结果写入
```
docs/youtube-ideas.md
```
或打印摘要。

Mode 2: Standalone (without MCP)

模式2：独立模式（无MCP时）

Parse input — same as Mode 1 step 1.

Download transcript via yt-dlp:

bash

# Check yt-dlp is available
command -v yt-dlp >/dev/null 2>&1 && echo "yt-dlp: ok" || echo "Install: pip install yt-dlp"

# Download subtitles only (no video)
yt-dlp --write-auto-sub --sub-lang en --skip-download -o "transcript" "$URL"

# Convert VTT to plain text
sed '/^$/d; /^[0-9]/d; /-->/d; /WEBVTT/d; /Kind:/d; /Language:/d' transcript.en.vtt | sort -u > transcript.txt

Read transcript — Read the transcript.txt file.
Analyze for startup ideas:
- Scan for business opportunities, pain points, product ideas
- Note approximate timestamps from VTT cues
- Rate each idea on specificity and market potential
- Cross-reference with WebSearch for market validation

For channel analysis — download multiple video transcripts:

bash

# Get video list from channel
yt-dlp --flat-playlist --print "%(id)s %(title)s" "https://youtube.com/@$CHANNEL" | head -10

# Download transcripts for top videos
for id in $VIDEO_IDS; do
  yt-dlp --write-auto-sub --sub-lang en --skip-download -o "transcripts/%(id)s" "https://youtube.com/watch?v=$id"
done

Write results to

docs/youtube-ideas.md

with format:

markdown

# YouTube Ideas — [Channel/Video]
Date: YYYY-MM-DD

## Idea 1: [Name]
- **Source:** [Video title] @ [timestamp]
- **Problem:** [What pain point]
- **Solution:** [What they propose]
- **Market signal:** [Evidence of demand]
- **Potential:** [High/Medium/Low] — [why]

## Idea 2: ...

解析输入 — 与模式1步骤1相同。

通过yt-dlp下载字幕：

bash

# 检查yt-dlp是否可用
command -v yt-dlp >/dev/null 2>&1 && echo "yt-dlp: ok" || echo "安装：pip install yt-dlp"

# 仅下载字幕（不下载视频）
yt-dlp --write-auto-sub --sub-lang en --skip-download -o "transcript" "$URL"

# 将VTT转换为纯文本
sed '/^$/d; /^[0-9]/d; /-->/d; /WEBVTT/d; /Kind:/d; /Language:/d' transcript.en.vtt | sort -u > transcript.txt

读取字幕 — 读取transcript.txt文件。
分析创业想法：
- 扫描商业机会、痛点、产品创意
- 记录VTT提示中的大致时间戳
- 根据具体性和市场潜力评估每个创意
- 通过WebSearch进行市场验证交叉引用

频道分析 — 下载多个视频字幕：

bash

# 获取频道视频列表
yt-dlp --flat-playlist --print "%(id)s %(title)s" "https://youtube.com/@$CHANNEL" | head -10

# 下载热门视频的字幕
for id in $VIDEO_IDS; do
  yt-dlp --write-auto-sub --sub-lang en --skip-download -o "transcripts/%(id)s" "https://youtube.com/watch?v=$id"
done

输出结果 — 将结果写入

docs/youtube-ideas.md

，格式如下：

markdown

# YouTube创意 — [频道/视频]
日期：YYYY-MM-DD

## 创意1：[名称]
- **来源：** [视频标题] @ [时间戳]
- **问题：** [痛点描述]
- **解决方案：** [提出的方案]
- **市场信号：** [需求证据]
- **潜力：** [高/中/低] — [原因]

## 创意2：...

Common Issues

常见问题

yt-dlp not found

yt-dlp未找到

Fix:

pip install yt-dlp

brew install yt-dlp

解决方法：

pip install yt-dlp

或

brew install yt-dlp

No subtitles available

无可用字幕

Cause: Video has no auto-generated or manual captions. Fix: Try

--sub-lang en,ru

for multiple languages. Some videos only have auto-generated subs.

原因： 视频没有自动生成或手动添加的字幕。 解决方法： 尝试使用

--sub-lang en,ru

指定多种语言。部分视频仅提供自动生成的字幕。

solograph MCP not available

solograph MCP不可用

Fix: Skills work in standalone mode (yt-dlp + Read). For indexed search across many videos, install solograph:

pip install solograph

. For enhanced web search, set up SearXNG (private, self-hosted, free).

解决方法： 该功能可在独立模式下运行（yt-dlp + Read）。如需对大量视频进行索引搜索，请安装solograph：

pip install solograph

。如需增强网页搜索功能，请搭建SearXNG（私有、自托管、免费）。

Too many ideas, hard to prioritize

创意过多，难以优先排序

Fix: Use

/validate

on the top 3 ideas to score them through STREAM framework.

解决方法： 对排名前三的创意使用

/validate

，通过STREAM框架进行评分。