Find knowledge clusters (groups of highly connected notes). Triggers on "clusters", "knowledge clusters", "note clusters", "find clusters".
Finds dense groups of linked notes (knowledge clusters) by starting with hub notes and expanding to connected groups. Triggers on "clusters", "knowledge clusters", "note clusters", or "find clusters".
/plugin marketplace add bencassie/flywheel/plugin install flywheel@flywheelThis skill is limited to using the following tools:
Find groups of notes that are densely connected (knowledge clusters).
Clusters are groups of notes that:
Identifying clusters helps:
A cluster is 3+ notes where:
hubs = find_hub_notes(min_links=10)
→ Start with highly connected notes
for hub in hubs:
cluster = [hub]
// Get all notes linking to/from hub
connections = get_backlinks(hub) + get_forward_links(hub)
// Find notes that also link to each other
for note in connections:
shared_links = count_shared_connections(note, cluster)
if shared_links >= 2:
cluster.append(note)
cohesion = internal_links / (internal_links + external_links)
→ Higher cohesion = tighter cluster
Knowledge Clusters
═══════════════════════════════════════════════
Found 12 knowledge clusters
🎯 Top Clusters by Size:
**Cluster 1: Data Platform** (23 notes, 89% cohesion)
Hub: [[Main Project]]
Notes: [[Database]], [[API]], [[Pipeline]], [[Data Quality]], ...
**Cluster 2: Development Tools** (18 notes, 76% cohesion)
Hub: [[Dev Environment]]
Notes: [[Git]], [[VS Code]], [[GitHub]], [[Python]], [[Node.js]], ...
**Cluster 3: Work Process** (15 notes, 82% cohesion)
Hub: [[Workflow]]
Notes: [[Deployments]], [[Releases]], [[Testing]], [[Change Management]], ...
📊 Cluster Statistics:
• Total clusters: 12
• Average size: 14.3 notes
• Average cohesion: 78%
• Unclustered notes: 200 (20% of vault)
💡 Insights:
• 3 major topic areas dominate vault
• Data platform cluster is largest and most cohesive
• Consider creating MOC (Map of Content) for each cluster
• Unclustered notes may need topic assignment
═══════════════════════════════════════════════
For each cluster:
MOC Example:
# Data Platform MOC
Core Platform:
- [[Main Project]]
- [[Database]]
- [[Architecture]]
Data Sources:
- [[Source A]]
- [[Source B]]
- [[Data Quality]]
[... organized cluster view]
Version: 1.0.0
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.