NRNishikanta Rayinblog.nishikanta.in·2d ago · 22 min readAI Skills Are Not Just Prompts: A Practical Architecture for Building, Evaluating, Shipping, and Maintaining Agent SkillsThe current generation of AI coding agents makes it surprisingly easy to create a "skill." Write a Markdown file. Add instructions. Give it a name. Put it inside .claude/skills/. Done. Except it isn't10
NRNishikanta Rayinblog.nishikanta.in·2d ago · 23 min readWhat If Your Coding Agent Could Remember What It Learned Yesterday?I built Attic to help Claude Code and Codex CLI remember what they discover — and now you can save knowledge from your browser too. You ask your AI coding assistant to investigate a bug. It searches 00
NRNishikanta Rayinblog.nishikanta.in·Aug 23 · 9 min readYour Computer Is Busy When You're Not: Building a Desktop Observability Tool with ElectronYou close your laptop. The screen goes dark. You assume everything stopped. But what if it didn't? Maybe Docker is still transferring data. Maybe Chrome is still downloading something. Maybe an applic12J
NRNishikanta Rayinblog.nishikanta.in·Aug 8 · 8 min readBuilding an AI-native Second Brain with Multi-RAG, Knowledge Graphs, and MCPClaude is incredibly good at reasoning. But reasoning is only as useful as the context available to it. Your architecture might be in GitHub. Your notes might be in Obsidian. Your decisions might be b42J
NRNishikanta Rayinblog.nishikanta.in·Aug 1 · 8 min readMind Maps in MCP: A Powerful Feature or Just Eye Candy?Mind maps are an excellent addition to an MCP ecosystem when they help users understand relationships between data, tools, and reasoning. They should complement—not replace—traditional dashboards, tab00
