Your notes app is a graveyard.
You save everything, and at the end, you find nothing.
Obsidian fixes that in 7 days. Here is the full plan: π
βοΈ Day 1: Download and Explore
β Download Obsidian free at obsidian. md and create your first Vault.
β Open File Explorer, Editor, and Graph View to get familiar.
β Create your first note with Ctrl/Cmd + N.
βοΈ Day 2: Learn Linking
β Create 5 notes on topics you care about.
β Link them together using the [[Note Name]] syntax.
β Open Graph View with Ctrl/Cmd + G to see your knowledge map.
βοΈ Day 3: Build the Daily Notes Habit
β Enable Daily Notes in Core Plugins.
β Open today's note with Ctrl+Shift+D every morning.
β Write 3 things to remember. Set your folder to "Journal."
βοΈ Day 4: Set Up PARA Folder Structure
β Create 4 folders: Projects, Areas, Resources, Archive.
β Move every existing note into the right folder today.
β Never create a new folder until you have 10+ notes that need it.
βοΈ Day 5: Install the Right Plugins
β Go to Settings, enable Community Plugins, and install Templater.
β Add Calendar for visual daily navigation and Dataview to query notes like a database.
β These 3 plugins alone will change how you use Obsidian forever.
βοΈ Day 6: Create Your Templates
β Build a Daily Note template with date, tasks, captures, and links.
β Build a Meeting Note template with attendees, actions, and context.
β Set Templater to auto-load on every new note you create.
βοΈ Day 7: Connect and Review
β Open Graph View and find every orphan note with no connections.
β Link every orphan to at least one other note.
β Create your first Map of Content and set a weekly Sunday review reminder.
----
For more Guides and cheatsheets:
1. Go to https://t.co/rnjW2PWRtc
2. Repost this to share β»οΈ it with your friend
3. Follow me for more systems and workflows like this.
Supertonic just killed ElevenLabs.
A text-to-speech model that runs entirely on your device. No cloud. No API key. No per-character pricing.
2,700 GitHub stars. 100% open source. MIT licensed.
The numbers are wild:
β 167x faster than real-time on an M4 Pro
β Only 66M parameters
β 1,263 chars/sec vs ElevenLabs Flash at 287
β 1,048 chars/sec vs OpenAI TTS-1 at 55
β Runs on a Raspberry Pi. Runs on an e-reader in airplane mode.
Reads currency, dates, phone numbers, and technical units correctly without preprocessing. ElevenLabs fails these. OpenAI fails these. Gemini fails these.
Supports 11 platforms and 5 languages. Chrome extension turns any webpage into audio in under a second.
I've watched on-device models lose to cloud APIs for years. This one doesn't lose.
The cloud TTS business just got cooked.
Hereβs the full Claude Code course by - Nick Saraev.
One of the most valuable Claude Code resources available right now.
And it is quite beginner friendly.
Creator of Claude Code (Boris Cherny) :
"I do not prompt Claude anymore"
> "My job is no longer to write code"
> "My job is to write loops"
in 20 minutes, he breaks down exactly how and shares his 3-tier system for when to let the loop run and when to stay in the driver's seat
Claude Code + agents + loop engineering + auto mode
Worth more than a $400 AI engineering course
60 MINUTES. ONE COURSE. EVERYTHING YOU NEED TO AUTOMATE ANYTHING WITH CLAUDE.
Not a highlight reel. Not a surface-level overview.
A complete course that takes you from manually prompting Claude to building automations that run without you initiating anything.
The developers who watch this today will stop doing manually in a week what Claude can handle automatically.
Bookmark it before you close this tab.
A 1-month-old YouTube channel just crossed $60,000 in ad revenue. Each video takes 20 minutes.
He took a screenshot of a channel called Axon. 7 videos, $15,000 a month, first upload sitting at 600,000 views. Dropped the screenshot into Claude with one prompt.
Claude read the niche and the title structure, then listed video ideas the channel never covered. He picked one: how ancient humans knew who their father was.
A second prompt pulled 10 obscure facts on the topic. That step decides everything now. YouTube runs uploads through Gemini, and scripts that read like generic AI get buried.
The old pipeline ate 7 hours: 30 image prompts, generated one by one, renamed by hand. A bulk scene generator now turns the script into 50 numbered slides in minutes, scene 1 to scene 50, ready to drag into CapCut.
Voiceover used to cost $1,000 per 1,500-word script on Fiverr. He picks 1 of 9,500 AI voices and has the audio in under 60 seconds. His channels stay monetized.
The dashboard shows $2,000 a day. And his copy targets are doing the same: Professor Historian, 9 videos, $15,000 a month. Forgotten American Survival, $17,000. Another channel hit $29,000 a month 60 days after upload one.
Several of his own channels flopped first. The framework removes the 7 hours, not the risk.
YouTube pays the same $2,000 whether the video took 7 hours or 20 minutes.