Obs Memory

This turns Claude into a coding agent with a persistent memory stored in an Obsidian vault. It auto-orients at session start by reading active TODOs and the current project overview, then uses wikilinks to navigate components, architecture decisions, and patterns on demand. The skill prefers CLI queries over full file reads to save tokens, and automatically offers to document new components or write session summaries when you wrap up. It's opinionated about structure: project-specific knowledge lives in project folders, cross-project tech knowledge goes in domain notes, and everything connects through a graph. If you work across sessions or multiple projects and want context to persist without re-explaining architecture every time, this gives Claude a knowledge base that grows with your codebase.