I am starting to dedicate part of my Thursdays to R&D. I came up with this new skill today to help keep AI learning from all chat sessions to make it more effective with every new session. I call the skill Hindsight. At the end of your sessions, just /hindsight ## About Hindsight A self-improvement skill for AI coding assistants. At the end of a session, it reviews everything that actually happened — the tasks, the corrections, the dead ends — pulls out the lessons that would genuinely change how future work gets handled, and saves the durable ones as persistent memory. Not a journal of what got done; a filter for what's worth remembering. ## What you get - **One trigger, one pass** — "get some hindsight" (or equivalent phrasing) reviews the whole session end-to-end, not just the last exchange. - **Root causes, not symptoms** — for anything that took multiple attempts, it asks what single upstream fix would have prevented the whole chain, instead of just noting that a mistake happened. - **A real filter, not a transcript** — one-off content specifics get discarded; only lessons that would change how a *future* task gets handled get kept. A clean session gets told "nothing to report," not padded filler. - **Updates in place** — before writing a new memory entry, it checks whether an existing one already covers the topic and extends that instead of creating a near-duplicate. - **Never redoes work** — strictly read-only against the session's actual tasks. Its only writes are to memory (and whatever indexes that memory). - **Portable** — no project-specific content baked in. It works the same way regardless of what the session was actually about. - **Pays for itself in tokens, not just tidiness** — a lesson written down once means a future session doesn't re-spend tokens rediscovering it through the same trial and error, re-litigating a question that was already settled, or repeating a correction you already made. The saving compounds: the more sessions an assistant runs, the more that accumulated memory shortens the average one.

I was curious to hear what all of you guys are working on, so I thought I'd share what I'm currently working on. Right now, I'm trying to build a better system and improve the one I've already created for generating and gathering leads more efficiently. I'm experimenting with using AI, social media, and outreach to make the whole process more organized and effective. Still working on it, but I'm interested to see how much I can improve the system over time.

I've been waiting sooo long to write this post that it feels weird now that I'm actually doing it... 😅 As of this morning, my first EVER official web app has finished beta and is now LIVE! Woooo! 👉 Give it a test run here: https://www.sgnl.so/ And to celebrate the official launch of SGNL we're giving everyone a 7-day free trial, no CC required! (not sure how long we'll be doing this so test it out now while you can 🙏🏽) The premise of SGNL is this: > I attached an AI brain to youtube so that you can TALK to youtube and it will give you the exact videos you're looking for! (Which gives you the ability to learn from content at 5-10x faster than normal youtube 📈) It's changed my life & is a big reason I've been able to learn so fast and build the courses I've built this year. try it out for free (while free trials are still available): https://www.sgnl.so/ -- I've always wanted to build an app, but I honestly never thought I would. (Or at least not until I made a few mil and paid a massive engineering team to build it) But thanks to AI, non-techy entrepreneurs like me & you can actually build incredible apps... without any prior experience. What a time to be alive, I thank God for it almost daily. And if you haven't tried building an app yet with AI, give it a go! It's so much fun, and you'd be surprised at what you can accomplish so quickly. There's not a much better feeling that seeing your ideas come to life in seconds lol. (thank you claude code 👨‍💻) But anyways, hope you have a blessed day & check out SGNL if you get a chance today. Here's a short video explaining SGNL it does, why I built it, and how it could potentially change your life and learning as well: https://www.youtube.com/watch?v=5F5NzvX2tHY ​ Talk soon, and happy building!

This is my first and last GitHub offering while having a full Thyroid. 😁 I have surgery tomorrow to remove the cancer on half of it. #F***Cancer #1/2*Thyroid #KeepPositive #AICureThisForAll I have uploaded the YouTube Subscriptions Ingestor for public consumption. After the initial setup the skill will pull your subscription videos from creators and produce .md files to dump in a raw folder to be processed for those running a second brain on their systems to create searchable knowledge bases. Attached below is an infographic detailing the skill's capabilities, a progress in Obsidian as I further refined the skill, along with screenshots of the Markdown files it generates. A key feature is the prompt system—it allows you to choose between a fresh data fetch, grabbing the latest videos, or performing a local search, which saves significantly on token usage. Thanks again to @Kj Rainey and the community here for providing feedback and answering my questions as I move along my AI journey of skill building and AI automations. Peace, Love, and Happiness everyone! https://github.com/EfficientStreet/youtube-subscriptions-ingest

I am doing a 7-day challenge and finished the first assignment, a Newsletter automation in Claude Code. However, I don't have anyone signed up yet. It was good practice and a foray into Claude Code after using CoWork up to this point. I think it turned out pretty good for the first try. I used Gemini to generate the image; I was impressed with the graphic Gemini came up with after I prompted it with my title for my first newsletter. I plan to use it for my blog post on the site and create a video on the subject for my YouTube channel.