llm-wiki-maintainer 1.1

Maintain a Persistent, Compound Knowledge Base

The LLM Wiki Maintainer solves the "memory leak" problem in AI workflows where knowledge is lost after a conversation ends. Instead of ephemeral chats, this skill enables your agent to build and maintain a living markdown wiki that grows more valuable over time.

What it does

This skill provides a structured framework for an AI agent to act as a librarian and synthesizer. It manages a directory of markdown files using a strict schema, ensuring that raw sources remain immutable while synthesized "knowledge pages" are continuously updated. It handles provenance tracking, contradiction management, and automated indexing.

Why use this skill

• Persistence: Every useful answer the AI generates is automatically filed back into the wiki for future use.
• Provenance: Tracks source hashes and claims so you always know where information came from.
• Structural Integrity: Includes Python scripts for linting, SQLite-backed indexing, and automated log generation to prevent the wiki from becoming a "junk drawer."
• Conflict Resolution: Instead of overwriting old data, it reconciles contradictions through dedicated reflection pages.

Technical Features

Supports markdown-based folders, SQLite for high-speed querying of page metadata, and custom linting rules for structural health. It works seamlessly with local file systems or cloud-based repositories.