llm-wiki

Builds persistent interlinked markdown knowledge bases from user-provided sources.

1|Updated May 16, 2026
One-click install
npx skills add https://github.com/devMoez/titan --skill llm-wiki-devmoez
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/devMoez/titan/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/devMoez/titan --skill llm-wiki-devmoez

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

It eliminates the inefficiency of repeatedly regenerating answers from scratch by turning scattered sources into a persistent, interlinked markdown knowledge base that compounds over time.

Core Features & Use Cases

  • Persistent interlinked wiki: Maintains entity, concept, comparison, and query pages that cross-reference each other with wikilinks.
  • Ingest-to-synthesis workflow: Ingests sources into an immutable raw layer, then synthesizes and updates curated wiki pages with provenance markers.
  • Orientation + quality control: Orients on SCHEMA.md, index.md, and recent log entries to avoid duplicates, and supports linting/auditing (orphans, broken wikilinks, frontmatter validation, drift, contradictions).
  • Use cases: Build research notes for a domain (papers, articles, transcripts), answer questions using the wiki’s compiled structure, and file new deep-dive comparisons or query results back into the vault.

Quick Start

Ask the agent to initialize a new LLM wiki at your configured path and then ingest your first set of sources so it can create SCHEMA.md, index.md, and log.md.

Frequently Asked Questions about llm-wiki

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

FAQPage Schema
How do I build a persistent knowledge base from research papers and articles?▼

Initialize a new LLM wiki at your configured path to generate SCHEMA.md, index.md, and log.md, then ingest your first set of sources like papers or articles to automatically populate the persistent markdown wiki structure.

Can I detect contradictions and broken wikilinks in a markdown knowledge base?▼

Lint your markdown wiki to detect orphans, broken wikilinks, frontmatter validation issues, content drift, and contradictions, ensuring your research notes maintain consistency and structural integrity over time.

What is the best way to maintain provenance when ingesting sources into a wiki?▼

Maintain provenance by storing ingested sources in an immutable raw layer with content hashes, then synthesizing curated wiki pages with provenance markers that trace back to the original articles, papers, or transcripts.

Does this approach work as a RAG alternative for querying domain knowledge?▼

As a RAG alternative, it compiles entity, concept, and comparison pages that cross-reference each other with wikilinks, letting you query the wiki's structured knowledge rather than retrieving raw document chunks.

How do I avoid duplicate pages when adding new research notes to an existing wiki?▼

Avoid duplicates by orienting on SCHEMA.md, index.md, and recent log entries before ingesting new sources, ensuring new content updates existing entity or concept pages rather than creating redundant ones.