Does this skill work with any note-taking app?

It is designed for Markdown-based vaults that use YAML frontmatter and wiki-link syntax, such as Obsidian, Foam, or Logseq, especially when managed via Claude Code.

What is the 'cold-read' prediction test?

The cold-read test is a unique quality check where the AI attempts to predict a note's full content using only its title and description. This ensures that metadata is descriptive enough for both humans and AI agents to understand the note's purpose without opening it.

Can I customize the intensity of the verification?

Yes, the skill supports three processing depths: 'deep' for exhaustive link and orphan analysis, 'standard' for balanced checks, and 'quick' for basic schema and link verification.

How does it handle semantic search testing?

The skill uses vector search tools to see if a note's description allows it to be retrieved in the top results for relevant queries, ensuring your AI tools can find the information later.

Knowledge Base Quality Verifier

Name: Knowledge Base Quality Verifier
Author: LopeWale

byLopeWale

0•

Gestión de Contenido

Automates multi-stage quality audits for digital notes by validating schema compliance, link integrity, and semantic discoverability.

The Verify skill acts as a rigorous quality gate for personal knowledge management systems, Zettelkastens, and documentation vaults. It implements a unique 'cold-read' prediction test to ensure note descriptions are genuinely informative, alongside traditional YAML schema validation and link health checks. By auditing link density, Map of Content (MOC) integration, and semantic search findability, it ensures that every piece of information in your vault remains discoverable, accurately represented, and well-connected within your knowledge graph.

Características Principales

01Cold-read prediction test to score description accuracy and semantic clarity

02Comprehensive wiki link resolution and broken link detection

03Health auditing for orphan risk, content staleness, and MOC integration

04Semantic search testing to verify note findability via vector embeddings

05Automated YAML frontmatter validation against defined schemas

060 GitHub stars

Casos de Uso

01Improving AI retrieval performance by optimizing note titles and descriptions

02Enforcing strict documentation standards across a shared technical knowledge base

03Auditing a digital garden or Zettelkasten for broken links and orphaned entries

Características Principales

01Cold-read prediction test to score description accuracy and semantic clarity

02Comprehensive wiki link resolution and broken link detection

03Health auditing for orphan risk, content staleness, and MOC integration

04Semantic search testing to verify note findability via vector embeddings

05Automated YAML frontmatter validation against defined schemas

060 GitHub stars

Casos de Uso

01Improving AI retrieval performance by optimizing note titles and descriptions

02Enforcing strict documentation standards across a shared technical knowledge base

03Auditing a digital garden or Zettelkasten for broken links and orphaned entries