corpus-health

Report Lorekit central corpus health with doctor, vector index, and ingest queue status.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It quickly tells you whether your Lorekit central corpus and its supporting indexes are healthy, what is stale or failing, and what to do next—without performing risky repairs.

Core Features & Use Cases

  • Central corpus health reporting: Checks corpus path, hard failures, warnings, stale indexes, and pending ingest items.
  • Workflow and integration verification: Validates vector index status and optionally GBrain freshness/doctor output when configured.
  • Report-only safety: Avoids mutating knowledge, sources, artifacts, and wiki state during health checks.

Quick Start

Ask an AI to run the corpus-health skill to report the default corpus status from your configured global-corpus.json and summarize any failures, warnings, stale indexes, and pending ingest items.

Frequently Asked Questions about corpus-health

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

FAQPage Schema
How do I check corpus health and diagnose stale vector indexes?

You can check corpus health by running a diagnostic report that identifies stale vector indexes, hard failures, warnings, and pending ingest items within your central corpus. This read-only process safely summarizes index status without mutating knowledge or artifacts.

What is the best way to verify ingest queue status and GBrain freshness?

Verifying ingest queue status and optional GBrain freshness involves checking workflow integration outputs and vector index conditions. This diagnostic approach reports pending items and GBrain doctor output to highlight drift or broken workflow steps across corpus updates.

Why does my LLM wiki have stale indexes or broken workflow steps after updates?

Your LLM wiki may have stale indexes or broken workflow steps due to drift in the default corpus during ongoing operations. A health diagnostic can separate hard failures from warnings and identify pending ingest items causing the issue.

Can I troubleshoot corpus issues without modifying sources or wiki state?

Yes, you can troubleshoot corpus issues safely using a report-only diagnostic approach. This method validates vector index status and ingest queues while strictly avoiding mutations to knowledge, sources, artifacts, and wiki state.

Do I need a global-corpus.json configuration to diagnose central corpus health?

Yes, diagnosing central corpus health requires read-only execution from your configured global-corpus.json. This configuration allows the diagnostic tool to access the default corpus path and accurately report doctor output and index freshness.