maintain

Audit and repair LLM wiki links, citations, tags, and storage health.

5|1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/GYF0311/lorekit --skill maintain-gyf0311
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: maintain
Source: https://github.com/GYF0311/lorekit/tree/main/brain/skills/maintain
Command: npx skills add https://github.com/GYF0311/lorekit --skill maintain-gyf0311

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps prevent your LLM wiki from drifting by detecting stale content, broken linking, missing citations, and filing or tagging issues before they compound.

Core Features & Use Cases

  • Back-link iron law enforcement to ensure every mention is properly cross-linked.
  • Citation and provenance audit to spot missing Source citations and timeline attribution gaps.
  • Structural maintenance including stale page detection, orphan detection, dead link cleanup, cross-reference creation, and optional graph/timeline backfills.

Quick Start

Ask an AI to run the maintain skill to audit brain health, fix link and citation issues, and produce a structured maintenance report with per-dimension counts.

Frequently Asked Questions about maintain

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

FAQPage Schema
How do I audit my knowledge base for stale content and orphan pages?

To detect orphan pages and stale content in your wiki, run an audit that checks link integrity, citation provenance, and structural filing. This process identifies broken cross-references and isolated entries, allowing you to apply targeted fixes before quality issues compound.

What is the best way to fix broken cross-references and dead links in a wiki?

Fixing broken cross-references and dead links requires enforcing back-link standards and running structural maintenance. You cleanup dead links, create missing cross-references, and optionally backfill graph or timeline connections to restore wiki connectivity.

How do I perform a citation audit for missing provenance in my wiki?

Performing a citation audit checks your wiki pages for missing Source citations and timeline attribution gaps. By scanning provenance metadata, you can spot pages lacking required references and apply targeted fixes to enforce citation standards across the knowledge base.

Can I use this knowledge base maintenance approach for post-import cleanup?

Yes, this knowledge base maintenance approach supports post-import cleanup. After importing data, you can audit link integrity, filing, tags, and embeddings, then apply targeted fixes to resolve structural issues and ensure the newly added content meets required quality benchmarks.

How do I generate a health report for my persistent LLM wiki?

Generating a health report for your persistent LLM wiki requires running a maintenance audit across all pages. The process outputs a dimensioned health report with per-dimension counts and remaining issues, detailing the status of links, citations, embeddings, and storage health.

When should I run a quality benchmark regression check on my wiki?

You should run a quality benchmark regression check during routine brain maintenance, after post-import cleanup, or periodically to prevent content drift. This check enforces required link and citation standards to ensure your knowledge base maintains structural integrity over time.