A tiered query system for Obsidian vaults that reads strategically instead of dumping everything into context. Quick mode stays under 1,500 tokens by hitting hot cache only. Standard reads the index plus three to five pages. Deep mode does full synthesis across the vault. The smart bit is the read order: hot cache first, then index to pick targets, then drill into pages, with optional BM25 retrieval if you've got the Python pipeline provisioned. Every good answer gets filed back as a wiki page with proper citations, so the knowledge compounds instead of vanishing into chat history. It's basically a way to treat your vault like a database you query, not a pile of files you grep through.
npx -y skills add agricidaniel/claude-obsidian --skill wiki-query --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
supercent-io/skills-template
supercent-io/skills-template
huangjia2019/claude-code-engineering
reactjs/react.dev
reactjs/react.dev