OpenSkillIndex← back to search
claude-code

Oraclaw oraclaw-graph

Network intelligence for AI agents. PageRank, community detection (Louvain), critical path, and bottleneck analysis for any graph of connected things.

install
source · Clone the upstream repo
git clone https://github.com/Whatsonyourmind/oraclaw
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/Whatsonyourmind/oraclaw "$T" && mkdir -p ~/.claude/skills && cp -r "$T/mission-control/packages/clawhub-skills/oraclaw-graph" ~/.claude/skills/whatsonyourmind-oraclaw-oraclaw-graph && rm -rf "$T"
manifest: mission-control/packages/clawhub-skills/oraclaw-graph/SKILL.md
source content

OraClaw Graph — Network Intelligence for Agents

You are a network analysis agent that uses PageRank, Louvain community detection, and shortest-path algorithms to analyze any graph.

When to Use This Skill

Use this when you need to:

  • Find the most influential nodes in a network (PageRank)
  • Cluster related items into groups (Louvain communities)
  • Find the critical path between two points
  • Identify bottleneck nodes that block everything downstream
  • Analyze task dependencies, org charts, knowledge graphs, or any connected data

Tool: 
analyze_decision_graph

Input: nodes + edges. Output: PageRank scores, community assignments, bottlenecks, critical path.

Node types: 

decision
, 
signal
, 
action
, 
outcome
, 
constraint
, 
goal
Edge types: 
depends_on
, 
influences
, 
blocks
, 
enables
, 
conflicts_with
, 
supports

Rules

  1. Nodes need: id, type, label, urgency, confidence (0-1), impact (0-1), timestamp
  2. Edges need: source, target, type, weight (0-1, higher = stronger)
  3. For critical path: provide sourceGoal and targetGoal
  4. PageRank identifies influence even in complex, non-obvious networks
  5. Communities group tightly-connected subgraphs — useful for sprint planning

Pricing

$0.05 per analysis (USDC on Base via x402). Free tier: 500 analyses/month with API key.