llm-wiki

Compile raw sources into interlinked markdown wiki pages with schema-defined index and log updates.

4|1|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/kvokov/oh-my-ai --skill llm-wiki
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/kvokov/oh-my-ai/tree/main/skills/llm-wiki
Command: npx skills add https://github.com/kvokov/oh-my-ai --skill llm-wiki

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI agents often re-derive knowledge because they lack a durable wiki layer between raw sources and answers, so insights vanish and contradictions go unnoticed. llm-wiki keeps raw evidence untouched while having the agent synthesize summaries, concept articles, and answers into a structured markdown wiki that compounds knowledge over time.

Core Features & Use Cases

  • Schema-first workflows: Always read the schema to discover raw, wiki, index, and log locations before touching files, preventing accidental tree creation.
  • Ingest, query, and lint disciplines: Follow documented steps for ingesting sources, responding to questions with citations, and auditing contradictions, orphan pages, and gaps.
  • Index and log maintenance: Keep the index as a navigation catalog, append-only logs with standardized headings, and record contradictions alongside every change.
  • Use Case: In a research knowledge base, ingest a new article, generate linked topic pages, update the index/log, and answer future queries with wiki-backed citations instead of rerunning RAG.

Quick Start

Ingest the latest raw source, update the index and log per the schema, document any contradictions, and file a new wiki page with the synthesis.

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 raw sources for AI agents?

Build a persistent knowledge base by ingesting raw sources and compiling them into interlinked markdown wiki pages with summaries and concept articles. This approach prevents insights from vanishing by keeping raw evidence untouched while synthesizing durable, queryable knowledge.

What's the best way to answer queries using a wiki instead of rerunning RAG?

Answer queries by having the agent consult the schema-defined wiki index and append-only logs, then cite existing wiki pages for responses. This wiki-backed citation method provides durable, compound knowledge retrieval instead of rerunning retrieval-augmented generation.

How do I ingest new materials into a structured wiki without creating accidental files?

Ingest new materials using a schema-first workflow where the agent reads the schema to discover raw, wiki, index, and log locations before touching files. This prevents accidental tree creation by enforcing documented file paths and standardized headings.

Can I lint contradictions and orphan pages in a markdown knowledge base?

Lint contradictions, orphan pages, and gaps in a markdown knowledge base by applying a dedicated auditing discipline. The agent audits interlinked wiki pages, records contradictions alongside every change in append-only logs, and flags navigational inconsistencies.

Why does an AI agent re-derive knowledge without a durable wiki layer?

An AI agent re-derive knowledge without a durable wiki layer because it lacks a persistent structure between raw sources and answers. Without a wiki to synthesize summaries and log contradictions, insights vanish and contradictions go unnoticed.

How do I maintain a wiki index and append-only log when updating knowledge management files?

Maintain a wiki index as a navigation catalog and append-only logs with standardized headings when updating knowledge management files. Record contradictions alongside every change and protect raw sources from mutation by enforcing schema-defined locations before editing.