solo-you2idea-extract

# /you2idea-extract

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

## Mode Detection

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

## MCP Tools (if available)

- `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

## Steps

### Mode 1: Index + Analyze (with solograph MCP)

1. **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?"

2. **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
   ```

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

4. **Search corpus** — `source_search(query="startup ideas", source="youtube")`.

5. **Cross-reference** — `kb_search(query)` for related existing opportunities (if knowledge base available).

6. **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

7. **Write results** to `docs/youtube-ideas.m...