graph

name	graph
description	Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".
version	1.0
generated_from	arscontexta-v1.6
user-invocable	true
context	fork
model	sonnet
allowed-tools	Read, Grep, Glob, Bash
argument-hint	[operation] [target] — operations: health, triangles, bridges, clusters, hubs, siblings, forward, backward, query

Runtime Configuration (Step 0 — before any processing)

Read these files to configure domain-specific behavior:

1. ops/derivation-manifest.md — vocabulary mapping, platform hints

   • Use vocabulary.notes for the notes folder name
   • Use vocabulary.note / vocabulary.note_plural for note type references
   • Use vocabulary.topic_map / vocabulary.topic_map_plural for MOC references
   • Use vocabulary.cmd_reflect for connection-finding command name
   • Use vocabulary.cmd_reweave for backward-pass command name

2. ops/config.yaml — for graph thresholds (MOC size limits, orphan thresholds)

If no derivation file exists, use universal terms (notes, MOCs, etc.).

---

EXECUTE NOW

Target: $ARGUMENTS

Parse the operation from arguments:

• If arguments match a known operation: route to that operation
• If arguments are a natural language question: map to the closest operation (see Interactive Mode)
• If no arguments: enter interactive mode

START NOW. Route to the appropriate operation.

---

Philosophy

The graph IS the knowledge. This skill makes it visible.

Individual {vocabulary.note_plural} are valuable, but their connections create compound value. /graph reveals the structural properties of those connections — where the graph is dense, where it is sparse, where it is fragile, and where synthesis opportunities hide.

Every operation produces two things: findings (what the analysis reveals) and actions (what to do about it). Never dump raw data. Always interpret results with {vocabulary.note} descriptions and domain context. Always suggest specific next steps.

---

Operations

/graph health

Full graph health report: density, orphans, dangling links, coverage.

Step 1: Collect raw metrics

# Count total notes (excluding MOCs)
NOTES_DIR="{vocabulary.notes}"
TOTAL=$(ls -1 "$NOTES_DIR"/*.md 2>/dev/null |  -l |  -d )
MOC_COUNT=$(grep -rl  /*.md 2>/dev/null |  -l |  -d )
NOTE_COUNT=$((TOTAL - MOC_COUNT))


LINK_COUNT=$(grep -ohP  /*.md 2>/dev/null |  -l |  -d )




 


 f  /*.md; 
  NAME=$(  .md)
  INCOMING=$(grep -rl  / 2>/dev/null | grep -v  |  -l |  -d )
  [[  -eq 0 ]] &&  



grep -ohP  /*.md 2>/dev/null |  -u |   -r ; 
  NAME=$(  | sed )
  [[ ! -f  ]] &&  



COVERED=0
 f  /*.md; 
  NAME=$(  .md)
  
  grep -q   2>/dev/null && 
  
   grep -rl  /*.md 2>/dev/null | xargs grep -l  >/dev/null 2>&1; 
    COVERED=$((COVERED + ))