Total 5 posts
Every new AI session has to re-understand your project. CLAUDE.md is the project-level memory that solves this. Of the seven sections in this template, the most useful one I've found is "Do not change."
Agent Skills package domain know-how and workflows into a folder an agent can load on demand. This explains how the three-layer progressive disclosure works, how code execution fits in, and how Skills differ from MCP and multi-agent architectures.
The core of MCP is standardizing your capabilities into tools AI can understand. This walks the full flow — from writing your first tool, to deploying it as a network service that other people and other AIs can call.
Set up an AI knowledge base in Obsidian that can run first — organize a local Markdown vault, connect via a CLI agent, then validate the loop with two scenarios — accumulating materials and advancing projects.
Turn a topic, notes, or PPTX into a single-file HTML presentation, with style preview, keyboard navigation, mobile swipe, PDF export, and one-click deploy.
