agentleFS
fortunto2fortunto2/solo-factory/skills/index-youtube/SKILL.md

solo-index-youtube

Skill18 starsChanged 4 months agoMITView on GitHub

Use when "index YouTube", "add YouTube channel", "update video index", "index transcripts", or need searchable YouTube content.

  • Installs packages

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 5 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check that yt-dlp is available:

    line 20
  2. Distinctive:

    If empty or "all": index all channels (from config or ask user)

    line 29
  3. Very specific:

    If one or more handles: index only those channels (e.g., GregIsenberg ycombinator)

    line 30
  4. Distinctive:

    Check which mode is available:

    line 35
  5. Very specific:

    If the MCP tool source_search is available, use solograph for indexing and search.

    line 39
  6. Very specific:

    If solograph-cli is not on PATH, try:

    line 64
  7. Distinctive:

    If solograph MCP tools are NOT available, use yt-dlp directly to download transcripts and analyze them.

    line 76
  8. Distinctive:

    Read each transcript with the Read tool.

    line 101
  9. Very specific:

    Write a summary index to docs/youtube/index.md:

    line 107
  10. Very specific:

    Fix: Run brew install yt-dlp (macOS), pip install yt-dlp, or pipx install yt-dlp.

    line 142

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/index-youtube

Index YouTube video transcripts into a searchable knowledge base. Supports two modes depending on available tools.

Prerequisites

Check that yt-dlp is available:

which yt-dlp || echo "MISSING: install yt-dlp (brew install yt-dlp / pip install yt-dlp / pipx install yt-dlp)"

Arguments

Parse $ARGUMENTS for channel handles or "all":

  • If empty or "all": index all channels (from config or ask user)
  • If one or more handles: index only those channels (e.g., GregIsenberg ycombinator)
  • Optional flags: -n <limit> (max videos per channel, default 10), --dry-run (parse only)

Mode Detection

Check which mode is available:

Mode 1: With solograph MCP (recommended)

If the MCP tool source_search is available, use solograph for indexing and search.

Setup (if not yet installed):

# Install solograph
pip install solograph
# or
uvx solograph

Indexing via solograph CLI:

# Single channel
solograph-cli index-youtube -c GregIsenberg -n 10

# Multiple channels
solograph-cli index-youtube -c GregIsenberg -c ycombinator -n 10

# All channels (from channels.yaml in solograph config)
solograph-cli index-youtube -n 10

# Dry run (parse only, no DB writes)
solograph-cli index-youtube --dry-run

If solograph-cli is not on PATH, try:

uvx solograph-cli index-youtube -c <handle> -n 10

Verification via MCP:

  • source_search() — the sources with counts (youtube should appear) and the auto-detected topics
  • source_search("startup idea", source="youtube") — test search
  • source_search(related=video_id) — find related videos by tags

Mode 2: Without MCP (standalone fallback)

If solograph MCP tools are NOT available, use yt-dlp directly to download transcripts and analyze them.

Step 1: Download video list

# Get recent video URLs from a channel
yt-dlp --flat-playlist --print url "https://www.youtube.com/@GregIsenberg/videos" | head -n 10

Step 2: Download transcripts

# Download auto-generated subtitles (no video download)
yt-dlp --write-auto-sub --sub-lang en --skip-download --sub-format vtt \
  -o "docs/youtube/%(channel)s/%(title)s.%(ext)s" \
  "<video-url>"

Step 3: Convert VTT to readable text

# Strip VTT formatting (timestamps, positioning)
sed '/^$/d; /^[0-9]/d; /^NOTE/d; /^WEBVTT/d; /-->/d' docs/youtube/channel/video.vtt | \
  awk '!seen[$0]++' > docs/youtube/channel/video.txt

Step 4: Create index

Read each transcript with the Read tool. For each video, extract:

  • Title (from filename or yt-dlp metadata)
  • Key topics and insights
  • Actionable takeaways
  • Timestamps for notable segments (if chapter markers exist)

Write a summary index to docs/youtube/index.md:

# YouTube Knowledge Index

## Channel: {channel_name}

### {video_title}
- **URL:** {url}
- **Key topics:** {topic1}, {topic2}
- **Insights:** {summary}
- **Actionable:** {takeaway}

Step 5: Search indexed content

With transcripts saved as text files, use Grep to search:

# Search across all transcripts
grep -ri "startup idea" docs/youtube/

Output

Report to the user:

  1. Number of videos indexed
  2. Number of transcripts downloaded (vs skipped — no transcript available)
  3. How many had chapter markers
  4. Index file location
  5. How to search the indexed content (MCP tool or Grep command)

Common Issues

"MISSING: install yt-dlp"

Cause: yt-dlp not installed. Fix: Run brew install yt-dlp (macOS), pip install yt-dlp, or pipx install yt-dlp.

Videos skipped (no transcript)

Cause: Video has no auto-generated or manual subtitles. Fix: This is expected — some videos lack transcripts. Only videos with available subtitles can be indexed.

Rate limiting from YouTube

Cause: Too many requests in short time. Fix: Reduce -n limit, add --sleep-interval 2 to yt-dlp commands, or use --cookies-from-browser chrome for authenticated access.

solograph-cli not found

Cause: solograph not installed or not on PATH. Fix: Install with pip install solograph or uvx solograph. Check which solograph-cli.

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.