English | Русский The Seven Biggest Claude Skills Collections: What’s Inside, Which to Trust, and How to Use Them TL;DR — if you only read this box: Start here: anthropics/skills for a small, production-grade, vetted set. Add glebis/claude-skills (~90 tidy personal skills) if you want more, or obra/superpowers if you want a whole workflow, not … Continue reading “The Seven Biggest Claude Skills Collections: What’s Inside, Which to Trust, and How to Use Them”

English | Русский Language, format, placement: how to write prompts an LLM understands better I spend my days wrangling big prompts to language models — and the same question keeps coming up: what actually works better? Is it true that if you write tersely, telegraph-style, with no filler, the model both understands more precisely and … Continue reading “Language, format, placement: how to write prompts an LLM understands better”

English | Русский How to Organize a Repository for an LLM Agent More complex is better? I don’t think so. Five tiers of repository organization: Tier 0 — flat files. Everything in context. Prototypes, configs, small projects under 20 files. Tier 1 — text search + CLAUDE.md. How every AI coding agent works. Code projects … Continue reading “How to Organize a Repository for an LLM Agent”

English | Русский The AI Productivity Paradox: Why Experts Slow Down Why experts get slower, novices get faster, and context matters more than profession The Paradox Nobody Expected Experienced developers with five years of tenure, working on repositories exceeding one million lines of code, gained access to cutting-edge AI tools. Economists predicted they would speed … Continue reading “The AI Productivity Paradox and Trend: Why Experts Slow Down but it still profitable, or not?”

English | Русский July 2025. Jason Lemkin—founder of SaaStr, one of the largest startup communities—was working on his project using the Replit platform. He made a quick code edit. He was confident in his safety measures. He’d activated code freeze (blocking all changes), given clear instructions to the AI agent, used protective protocols. Everything by … Continue reading “How to Adapt Proven Management Methods to AI’s Unique Characteristics”