wiki-rag

Retrieve wiki vault pages via progressive loading and wikilink traversal for cross-domain queries.

8|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/ShaheerKhawaja/ProductionOS --skill wiki-rag
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wiki-rag
Source: https://github.com/ShaheerKhawaja/ProductionOS/tree/main/skills/wiki-rag
Command: npx skills add https://github.com/ShaheerKhawaja/ProductionOS --skill wiki-rag

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Progressive retrieval-augmented context from the SecondBrain wiki vault, enabling cross-project understanding across domains with structured drill-down and graph traversal.

Core Features & Use Cases

  • Local RAG with progressive loading (hot cache → index → domain pages → individual pages) for responsive context.
  • Graph RAG via wikilink traversal to surface related nodes and their summaries for planning and research.
  • Use Case: when answering cross-project questions or when building context for planning tasks that touch multiple domains.

Quick Start

Start the wiki-rag skill to load contextual pages from the SecondBrain vault for a cross-domain query.

Frequently Asked Questions about wiki-rag

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How does graph RAG improve wiki context retrieval for cross-project planning?

Graph RAG improves wiki context retrieval by traversing wikilinks to surface related nodes and their summaries, enabling cross-project understanding across multiple domains. This graph-based loading method provides structured drill-down for complex research and planning tasks.

What is progressive loading in local RAG and how does it manage wiki context?

Progressive loading in local RAG manages wiki context by sequentially querying a hot cache, then the index, domain pages, and individual pages. This tiered context retrieval ensures responsive performance when fetching information from a wiki vault.

Can I use wiki rag to answer questions that touch multiple knowledge domains?

Yes, you can use wiki rag to answer questions touching multiple knowledge domains. It retrieves relevant context from a SecondBrain wiki vault to support cross-project reasoning, fetching linked pages and summaries to build comprehensive contextual understanding.

How do I retrieve context from a wiki vault using wikilink traversal?

To retrieve context from a wiki vault using wikilink traversal, start the wiki-rag skill with a cross-domain query. It performs graph-based context loading by following wikilinks between pages to surface related nodes and their summaries for research.

When should I use graph-based context loading instead of standard vector embeddings?

You should use graph-based context loading instead of standard vector embeddings when answering cross-project questions or building context for planning tasks. Graph RAG traverses wikilinks to surface related nodes, providing structured drill-down across multiple domains.