Doctree Mcp
BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.
/ask â Question Answering
Fast answers from your vault. Uses QMD hybrid search (BM25 + vector + rerank) when available, with automatic fallback to vault grep.
writ
Hybrid RAG knowledge retrieval service for AI coding rule enforcement. Replaces flat-file rule loading with graph-native retrieval via a five-stage pipeline (domain filter, BM25 keyword, ANN vector, graph traversal, RRF ranking). Rules are injected automatically into Claude's context via hooks -- no manual loading required. Activates on ALL software engineering tasks: code generation, code review, design, research, auditing, debugging, testing, planning, and architecture decisions. The knowledge base is always queried -- task complexity only determines the level of ceremony, not whether Writ activates.
add-qmd
Add QMD (Query Markup Documents) as an advanced memory search backend. Upgrades the built-in grep-based memory_search with hybrid BM25 + vector semantic search + LLM re-ranking. Fully local, no API keys needed. Triggers on "add qmd", "qmd memory", "semantic memory search", "upgrade memory".
Io.Github.Kurovu146/Memory Fts
Long-term memory for Claude Code with SQLite FTS5 search and BM25 ranking
Mcp Sap Docs
Fast MCP server for unified SAP docs search (SAPUI5, CAP, OpenUI5, wdi5) with BM25 full-text search
qi-cli
Guide for using qi, a local-first knowledge search CLI for macOS. Use this skill whenever the user asks about qi commands, indexing documents, searching a knowledge base, asking questions with RAG, configuring providers (Ollama, OpenAI), understanding search modes (BM25, hybrid, vector), or anything related to the qi tool. Triggers on phrases like "qi index", "qi search", "qi ask", "qi query", "how do I use qi", "set up qi", "configure qi", "search my notes with qi", or any mention of the qi CLI.