llm-wiki

Compiles and maintains interlinked markdown knowledge bases from diverse sources with linting and logging.

1|Updated Jul 31, 2026
One-click install
npx skills add https://github.com/icyzh/hermes-web --skill llm-wiki-icyzh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/icyzh/hermes-web/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/icyzh/hermes-web --skill llm-wiki-icyzh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the problem of fragmented knowledge by transforming scattered research, notes, and documents into a structured, compounding, and interlinked markdown knowledge base that evolves with your work.

Core Features & Use Cases

  • Compounding Knowledge: Automatically cross-references new information with existing pages to prevent duplication and ensure consistency.
  • Automated Maintenance: Includes built-in linting to identify broken links, orphan pages, and stale content, keeping your wiki healthy.
  • Use Case: Use this to maintain a research repository for AI/ML papers where the agent automatically links new paper summaries to existing concept pages and flags contradictory claims for your review.

Quick Start

Ask the agent to initialize a new wiki in your home directory and ingest the provided research article as the first source.

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 scattered research notes?

To build a persistent markdown knowledge base, compile and interlink diverse source materials using a defined schema. This automatically cross-references new information with existing pages to prevent duplication and ensure consistency.

How does automated cross-referencing work for an interlinked wiki?

Automated cross-referencing for an interlinked wiki works by compiling diverse source materials and automatically linking new entries to existing concept pages. It requires consistent adherence to a defined schema and log-based activity tracking to maintain structural coherence.

Does this knowledge base approach work for tracking entities across large collections of documents?

Tracking entities across large collections of documents is supported by compiling diverse source materials into a persistent markdown wiki. It facilitates research synthesis and entity tracking while using automated linting to ensure data integrity.

How do I identify broken links and orphan pages in a markdown wiki?

Identifying broken links and orphan pages in a markdown wiki is achieved through built-in automated linting. The maintenance feature flags broken links, orphan pages, and stale content to keep your research repository healthy and coherent.

What is the best way to maintain a research repository for AI and ML papers?

The best way to maintain a research repository for AI and ML papers is to use a persistent markdown knowledge base. It automatically links new paper summaries to existing concept pages and flags contradictory claims for your review.

Do I need a specific schema to maintain a markdown knowledge base?

A specific schema is required to maintain a markdown knowledge base effectively. Consistent adherence to this defined schema, alongside log-based activity tracking, ensures data integrity and structural coherence across all ingested research notes.