llm-wiki

Ingests raw sources into an Olapanda vault and synthesizes them into linked pages.

6|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/caohaotiantian/llm-wiki-skill --skill llm-wiki-caohaotiantian
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/caohaotiantian/llm-wiki-skill/tree/main/llm-wiki
Command: npx skills add https://github.com/caohaotiantian/llm-wiki-skill --skill llm-wiki-caohaotiantian

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, networkx, psycopg, openai, anthropic, sentence-transformers, frontmatter, mineru, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Ingests raw sources into an Obsidian vault and synthesizes them into interlinked wiki pages with provenance, cross-references, and periodic linting, enabling a persistent knowledge base that stays up-to-date without re-queried raw documents.

Core Features & Use Cases

  • Ingest: convert raw sources (markdown, PDFs, code, docs) into wiki pages with [[wikilinks]] and provenance tracking.
  • Query: search the wiki and synthesize answers with citations, supporting cross-page references and incremental updates.
  • Lint: health checks for dead links, alias mismatches, stale content, and orphaned pages; automated stubs and diffs guide fixes.
  • Use Case: enterprise design docs, research knowledge bases, and personal learning by accumulating and cross-referencing sources over time.
  • Diff-based re-ingestion: only re-ingest changed sources to minimize tokens while propagating updates through the graph.

Quick Start

Ingest raw sources into wiki pages, then query the wiki with citations to surface answers.

Frequently Asked Questions about llm-wiki

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

FAQPage Schema
How do I build an interconnected Obsidian wiki knowledge base from raw sources like PDFs and code?

To build an Obsidian wiki knowledge base, you can ingest raw sources like markdown, PDFs, code, and transcripts to automatically synthesize them into interlinked pages with [[wikilinks]] and provenance tracking.

What is the best way to maintain cross-references and avoid dead links in a wiki knowledge base?

The best way to maintain cross-references and avoid dead links in a wiki knowledge base is to run periodic linting health checks, which detect dead links, alias mismatches, stale content, and orphaned pages to guide automated fixes.

How does incremental re-ingestion handle updated documents without reprocessing the entire knowledge base?

Incremental re-ingestion uses snapshot diffing and a manifest-based coordination flow to process only changed sources, minimizing token usage while automatically propagating updates through the knowledge graph.

Can I query my Obsidian vault and synthesize answers with citations from multiple wiki pages?

Yes, you can query the Obsidian vault to search synthesized wiki pages, retrieve answers with citations, and surface information by leveraging typed links and cross-page references.

Does this knowledge base tool support tracking provenance for ingested enterprise design docs?

Yes, the tool supports provenance tracking for enterprise design docs by ingesting raw sources into wiki pages with compiled frontmatter, ensuring source attribution is maintained across interlinked documents.

What are the limitations of using compiled frontmatter and typed links for wiki page models?

Using compiled frontmatter and typed links requires maintaining a manifest-based coordination flow and snapshot diffing; if the linting process is skipped, stale content and alias mismatches may accumulate across orphaned pages.