Youtube Info Diet

Youtube Info Diet

Tim asked me the other day about Claude getting YT video content. I haven’t had any problems with Claude Code or Jarvis doing this for me, but it relies on me searching YT. So, I just built a YT Info Diet. It runs locally using Apify (free plan) and my Claude Code subscription. It runs every 12 hours, excludes Shorts and send the summary with a reco to my Slack. I gave it a list of channels to “watch”

YouTube Channel Intelligence Monitor — Setup Guide

Auto-summarize new YouTube videos from your favorite channels every 12 hours, with watch/skim/skip verdicts delivered to Slack. No API costs (uses Claude Code subscription).

What You'll Get

Every 12 hours, the monitor checks your favorite YouTube channels. When a new long-form video drops, it:

1. Fetches the transcript

2. Sends it to Claude for analysis

3. Posts a structured intelligence brief to Slack with WATCH / SKIM / SKIP verdict, summary, key insights, and an actionable playbook

4. Saves a markdown report locally

YouTube Shorts are automatically filtered out.

---

Prerequisites

- macOS (this guide; Linux works too with cron instead of launchd)

- Python 3.9+

- https://claude.com/claude-code installed and logged in (claude command working)

- https://github.com/yt-dlp/yt-dlp — pip install yt-dlp

- An https://apify.com account (free tier is fine — used as transcript fallback)

- A Slack workspace where you can create webhooks

---

Step 1 — Install Python Dependencies

pip3 install feedparser youtube-transcript-api slack-sdk pyyaml

Step 2 — Get Your Apify Token

1. Sign up at https://apify.com (free)

2. Go to Settings → Integrations → API tokens

3. Copy your token (starts with apify_api_...)

Step 3 — Create a Slack Incoming Webhook

1. Go to https://api.slack.com/apps → Create New App → From scratch

2. Name it "YT Monitor", pick your workspace

3. In sidebar: Incoming Webhooks → toggle ON

4. Click Add New Webhook to Workspace → pick the channel where reports should land

5. Copy the webhook URL (starts with https://hooks.slack.com/services/...)

Step 4 — Create the Project

mkdir -p ~/dev/yt-channel-monitor

cd ~/dev/yt-channel-monitor

Create config.yaml:

check_interval_hours: 12

max_transcript_chars: 100000

slack_webhook_url: ''

channels: []

Create monitor.py — copy the full script from [paste your gist URL here]. (Or share the file directly with your friend.)

Step 5 — Add Channels

Find a channel ID by visiting the channel page (e.g. https://www.youtube.com/@peterdiamandis), then run:

yt-dlp --skip-download --playlist-items 1 --print "%(channel_id)s" "https://www.youtube.com/@peterdiamandis"

Add it:

python3 monitor.py add "Peter Diamandis" "UCvxm0qTrGN_1LMYgUaftWyQ" --tags ai futurism

Repeat for each channel you want to monitor.

Step 6 — Seed (Important!)

This marks all current videos as "already seen" so you don't get a flood of backfill on first run:

python3 monitor.py seed

Step 7 — Test It

export SLACK_WEBHOOK_URL="https://hooks.slack.com/services/YOUR/WEBHOOK/URL"

export APIFY_TOKEN="apify_api_YOUR_TOKEN"

# Process anything from the past 1 day as a test

python3 monitor.py run --since-days 1

You should see Slack notifications arrive within a few minutes.

Step 8 — Schedule Every 12 Hours (macOS)

Create ~/Library/LaunchAgents/com.yourname.yt-monitor.plist:

<?xml version="1.0" encoding="UTF-8"?>

<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">

<dict>

<key>Label</key>

<string>com.yourname.yt-monitor</string>

<key>ProgramArguments</key>

<array>

<string>/usr/bin/python3</string>

<string>/Users/YOUR_USERNAME/dev/yt-channel-monitor/monitor.py</string>

</array>

<key>WorkingDirectory</key>

<string>/Users/YOUR_USERNAME/dev/yt-channel-monitor</string>

<key>EnvironmentVariables</key>

<dict>

<string>/Users/YOUR_USERNAME/.local/bin:/usr/local/bin:/opt/homebrew/bin:/usr/bin:/bin</string>

<key>SLACK_WEBHOOK_URL</key>

<string>YOUR_WEBHOOK_URL_HERE</string>

<key>APIFY_TOKEN</key>

<string>YOUR_APIFY_TOKEN_HERE</string>

<string>/Users/YOUR_USERNAME</string>

</dict>

<key>StartCalendarInterval</key>

<array>

<dict><key>Hour</key><integer>6</integer><key>Minute</key><integer>0</integer></dict>

<dict><key>Hour</key><integer>18</integer><key>Minute</key><integer>0</integer></dict>

</array>

<key>StandardOutPath</key>

<string>/Users/YOUR_USERNAME/dev/yt-channel-monitor/monitor.log</string>

<key>StandardErrorPath</key>

<string>/Users/YOUR_USERNAME/dev/yt-channel-monitor/monitor.error.log</string>

</dict>

</plist>

Replace YOUR_USERNAME and the credentials, then load it:

launchctl load ~/Library/LaunchAgents/com.yourname.yt-monitor.plist

launchctl list | grep yt-monitor # confirm it's loaded

That's it. Reports land in Slack at 6 AM and 6 PM daily.

---

Daily Commands

# Add a channel

python3 monitor.py add "Channel Name" "UC..." --tags ai marketing

# List all channels

python3 monitor.py list

# Remove a channel

python3 monitor.py remove "UC..."

# Run manually right now

launchctl start com.yourname.yt-monitor

# Watch the logs

tail -f ~/dev/yt-channel-monitor/monitor.log

# Stop the schedule

launchctl unload ~/Library/LaunchAgents/com.yourname.yt-monitor.plist

---

How It Works

- YouTube RSS feeds (free, no API key) check each channel for new uploads

- Three-tier transcript fetching: youtube-transcript-api → yt-dlp → Apify (rotating proxies)

- YouTube Shorts filtered automatically (videos ≤ 180 seconds)

- claude -p headless mode runs analysis using your Claude Code subscription — no Anthropic API key needed

- State persistence in state.json ensures each video is only processed once

- Markdown archive in reports/ so you can grep/search past analyses

---

Tips

- Start small — 3-5 channels first. Easier to tune.

- Tag aggressively — tags help when scanning the Slack feed.

- Heavy Shorts posters (like creators who do daily Shorts) are mostly filtered out, but their occasional long-form videos still come through.

- Cost: ~$0 in normal use. Apify free tier handles ~5K videos/month easily. Claude Code subscription handles unlimited analysis.

2 comments

Ecom AI

skool.com/ecomai

Ecom AI is for e-commerce sellers that want to use AI to improve their businesses. Cut costs, improve marketing, and operate with more agents.

Leaderboard (30-day)