moc-curator

To find missing links in wiki Maps of Content, this Skill analyzes semantic embeddings to detect notes that belong in existing MOCs but lack connections. It compares note similarities to suggest specific navigational updates for comprehensive topic coverage.

To cluster orphan notes into thematic groups, this Skill applies embedding-based analysis to group disconnected notes by similarity. It uncovers hidden themes and proposes fresh Maps of Content for emerging clusters like Prompt Engineering Basics.

To organize unlinked notes with semantic embeddings, this Skill runs Python scripts using sentence-transformers to evaluate note content. It processes frontmatter tags and links to suggest navigational improvements after passing user approval gates.

Yes, you need Python with scikit-learn, numpy, and sentence-transformers to run semantic clustering on your notes. These dependencies power the embedding-based analysis required to detect MOC gaps and group orphan notes.

The best way to maintain navigational layers in an LLM wiki is using semantic embedding analysis to detect gaps in existing maps. This approach suggests updates to topic guides and organizes orphan notes into thematic clusters for enhanced discoverability.

You cannot automatically apply MOC updates because this Skill requires user approval gates before integration. It suggests updates and new Maps of Content based on semantic embeddings, then processes note frontmatter for tags and links only after explicit approval.