// Find disconnected clusters in the Awesome Search Obsidian vault — groups of notes that are internally linked but isolated from the rest of the graph. Identify semantic overlap between clusters and suggest bridge links. Use for deep graph connectivity audits.
Build and maintain a dense semantic knowledge graph about search and IR inside an Obsidian vault. Triggers on article URLs, article titles or names (from Clippings/, raw_articles/, or unprocessed vault notes), and requests to enrich or reprocess existing notes for concepts, people, companies, tools, or topics.
Audit all notes in the Awesome Search Obsidian vault for missing or incomplete frontmatter. Reports violations by folder and optionally auto-fixes notes where values can be inferred from content. Use for KG consistency checks.
Audit hub notes in the Awesome Search Obsidian vault — rank notes by inbound link count and compare against existing Topics/ notes. Surfaces mismatches where high-traffic concepts lack a proper topic page. Use for periodic graph structure reviews.
Find orphan notes in the Awesome Search Obsidian vault — notes with no wikilinks in or out — and suggest or apply connections to existing notes. Use when running a graph health audit or when the KG feels sparse.
| name | awesome-search-kg-clusters |
| description | Find disconnected clusters in the Awesome Search Obsidian vault — groups of notes that are internally linked but isolated from the rest of the graph. Identify semantic overlap between clusters and suggest bridge links. Use for deep graph connectivity audits. |
Use this skill to find groups of notes that form isolated islands — internally connected but with no links to the rest of the vault. Then identify semantic overlap between clusters and suggest specific bridge links.
Always use the Obsidian MCP server for all vault operations — never access the vault directly via the filesystem (no Read/Write/Bash file tools). The MCP server is the only sanctioned way to read, search, create, and edit notes.
Group notes into clusters based on wikilink connectivity:
List all clusters with size ≥ 3 notes:
CLUSTER REPORT
==============
Cluster A (12 notes): centred on Hybrid Search, BM25, SPLADE
External links: 8
Cluster B (7 notes): centred on Agentic Search, SIRA, RAG
External links: 2 ← potentially isolated
Cluster C (4 notes): centred on Autocomplete, Mirror Mirror article
External links: 1 ← isolated
For each cluster with few external links, read the notes and summarise:
For each pair of semantically overlapping but disconnected clusters, suggest specific wikilinks that would connect them:
BRIDGE SUGGESTIONS
==================
Cluster B (Agentic Search) ↔ Cluster A (Hybrid Search)
Suggested links:
- In "Agentic Search.md": add [[Hybrid Search]] (agentic systems use hybrid retrieval)
- In "SIRA.md": add [[Retrieval Pipeline]] (already in Cluster A)
Cluster C (Autocomplete) ↔ main graph
Suggested links:
- In "Autocomplete.md": add [[Query Understanding]] (natural parent concept)
- In "Topics/Autocomplete and Autosuggest.md": add [[Search Intent]]
Find notes that already bridge multiple clusters (high betweenness centrality):
BRIDGE NOTES (already connecting clusters)
==========================================
- "Retrieval Pipeline" — bridges Agentic, Hybrid, and RAG clusters
- "Search Evaluation" — bridges Metrics, A/B Testing, and LLM Judge clusters
Add the suggested wikilinks to the relevant notes. Only add links that are semantically justified — do not create links purely to improve graph connectivity scores.