Igor Strmecki

Entrepreneur consultant ICT business, MBA, father, photographer, motorcycling. 25yrs exp, ex-CIO multinationals SAP L'Oreal Coke. @Pragmatekh BusConsult #gdpr

[Igor Strmecki @strma]

Epic 🥰 https://t.co/NM0npUJTRm

[Dani Olmo @daniolmo7]

Terrassa.
Barcelona.
Zagreb.
Leipzig.
Barcelona.
Nueva York.
❤️🌎

[CyrilXBT @cyrilXBT]

Fable 5 flips to pay‑per‑use in 48 hours. Burn the remaining runway to make sure you don’t actually leave anything behind.

The play: have Fable comb your repo and draft a complete skills library before the timer hits zero. Frame it as a retiring principal engineer doing a final handoff to the team, and it snaps into a totally different gear.

On the other side you get 10–16 skill files—debugging runbooks, change policies, the painful failure tales that ate days. Every instinctive judgment it would’ve made silently is now documented and reusable by Opus and Sonnet for pennies.

Single pass. About 30% of your weekly budget. Value keeps compounding even after it’s locked behind credits.

[David Ondrej @DavidOndrej1]

im releasing all my agent skills to the public

this is hundreds of hours of trial & error

every single global .agents skill i have

go grab it. it's free.

[David Ondrej @DavidOndrej1]

Kimi K2.7 Code is fucking incredible

the tokens per second on such a smart model are just... wow

[AI Edge @aiedge_]

These Claude prompts have completely changed my life.

I've tested dozens of mega prompts inside Claude, and these 6 are the best.

Coding prompts, productivity prompts & more.

Full resources included - you'll want to save this:

[Igor Strmecki @strma]

@nevenvorkapic Ma moze i prime na film :), Konica ili Olympus. Kolko para?

[Neven Vorkapić @nevenvorkapic]

Kako nekome može biti dosadno, nikad mi neće biti jasno.

[Zelena alternativa - ORaH: zaista zeleni!!!!! @ORaHrvatske]

Danas je Dan planeta Zemlje - to je naš dom, naša odgovornost i naša budućnost. Svaka mala promjena koju napravimo danas može imati veliki utjecaj sutra. Zemlja ne pripada nama, mi pripadamo njoj. Čuvajmo je zajedno – ne samo danas, nego svaki dan. #DanPlanetaZemlje #zaorah

[Igor Strmecki @strma]

@ai_rohitt Course thx

[Igor Strmecki @strma]

@vishisinghal_ Pls Bible thx 👍

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[Erik Kuna 🚀 @erikkuna]

One frame. One moment. Everything after this is momentum, trajectory, physics. But right here, right now, a rocket is deciding to leave the Earth. The solid boosters ignite and hold down claps release. This is the last instant four astronauts are still on Earth but once those clamps release when the booster fire, there’s no going back, only forward.

📸 credit: me for @SuperclusterHQ - Artemis II liftoff | Pad 39B, Kennedy Space Center | April 1, 2026

[Igor Strmecki @strma]

@itsolelehmann Cowork

[Forbes @Forbes]

Healthcare professions such as doctors, nurses, therapists, and counselors continue to rank among the most automation-resistant. They involve unpredictable human needs, emotional complexity, and ethical decision-making, which are areas where algorithms still lag. Find out more about the other high-paying jobs.
Read more: https://t.co/okGyuR4A9H

[Sinkovic Brothers @SinkovicBros]

This victory not only adds to our personal achievements but also marks a historic moment for Croatian sports. We’re proud to become the first Croatian athletes to win four Olympic medals since our country’s independence 🇭🇷
Thank you to everyone for your unwavering support!

[Igor Strmecki @strma]

#hotoutside

[🎸 Rock History 🎸 @historyrock_]

A rock band is performing and the singer sees a kid with a banner asking to play guitar with them. The singer asks him:

- Do you really know how to play guitar?
- Yeah!
- What's your favorite band?
- Guns N' Roses

What happens next is incredible.

[Eric Kimberling @erickimberling]

Before jumping on the latest tech trends like AI and blockchain, ensure your organization is digitally ready. I share how to build a solid foundation for successful digital transformation in this blog post. #DigitalTransformation #ERP #TechTrends
https://t.co/xFe79eAC7Q

[Igor Strmecki @strma]

Out of office day