llm-wiki

Ingest URLs, files, and pastes into an interlinked Markdown wiki.

4|Updated May 18, 2026
One-click install
npx skills add https://github.com/ZardLi1115/zedclaw --skill llm-wiki-zardli1115
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/ZardLi1115/zedclaw/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/ZardLi1115/zedclaw --skill llm-wiki-zardli1115

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

It solves the problem of fragmented, hard-to-reuse knowledge by maintaining a persistent, interlinked Markdown wiki that compiles sources into consistent, queryable notes over time.

Core Features & Use Cases

  • Compounding knowledge base: Ingest URLs/files/pastes into an Obsidian-compatible directory of markdown pages with cross-references and synthesis.
  • Three-layer wiki architecture: Stores immutable raw sources, agent-owned entity/concept/comparison/query pages, and a schema that enforces conventions and tag taxonomy.
  • Orientation, linting, and trust controls: Reads schema/index/recent logs before work, then supports linting for orphans, broken wikilinks, index completeness, stale content, contradictions, confidence/quality signals, and source drift.
  • Practical workflows: Create/initialize a new wiki, ingest new material, answer questions from the wiki, and file valuable syntheses back into the knowledge base.

Quick Start

Use the llm-wiki skill to ingest a source into your wiki at ~/wiki by asking: "Ingest https://example.com/article into my LLM wiki and update the relevant pages and index."

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 Markdown knowledge base from multiple research sources?

To build a persistent Markdown knowledge base, you can ingest URLs, files, and pastes into an interlinked wiki structure. The system automatically synthesizes raw sources into queryable notes with cross-references and enforces a consistent tag taxonomy.

How does entity extraction and contradiction detection work in a wiki?

Entity extraction and contradiction detection work by mapping ingested content into agent-owned entity, concept, and comparison layers. The system runs lint audits to identify conflicting information, stale content, and source drift using sha256 verification.

What is the best way to organize research synthesis notes with wikilinks?

The best way to organize research synthesis notes is using a three-layer wiki architecture that separates immutable raw sources from synthesized pages. This structure enforces wikilinks, maintains a schema index, and files valuable syntheses back into the knowledge base.

Can I ingest new URLs into an existing Obsidian-compatible markdown wiki?

Yes, you can ingest new URLs into an existing Obsidian-compatible markdown wiki. The system reads the schema and recent logs, extracts entities and concepts, updates the index, and creates cross-referenced pages while preserving raw source immutability.

How do I detect source drift and broken wikilinks in a knowledge base?

You detect source drift and broken wikilinks by running a lint audit across the wiki. The audit checks for orphans, index completeness, stale content, contradictions, and uses sha256 hash drift detection to verify that raw sources remain immutable.

How do I query answers from an interlinked research wiki?

You query answers from an interlinked research wiki by asking questions against the existing content. The system reads the schema and index, retrieves relevant synthesized notes from the entity and concept layers, and provides answers based on the ingested sources.