Skip to main content

Oraclaw Graph

Skill Active

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

Purpose

To equip AI agents with advanced network analysis capabilities, enabling them to understand the structure, influence, and critical components of connected data.

Features

  • PageRank score calculation
  • Louvain community detection
  • Critical path analysis
  • Bottleneck node identification
  • Analysis of decision graphs

Use Cases

  • Finding most influential nodes in a network
  • Clustering related items into groups
  • Determining critical paths between points
  • Identifying bottleneck nodes in workflows

Non-Goals

  • General-purpose data visualization
  • Real-time network monitoring
  • Graph manipulation (adding/deleting nodes/edges)

Documentation

  • warning:Configuration & parameter referenceThe SKILL.md lists an `ORACLAW_API_KEY` as a required environment variable but does not specify how to obtain it or its required scopes, nor does it detail other configuration parameters.

Security

  • warning:Secret ManagementThe SKILL.md specifies `ORACLAW_API_KEY` as a required environment variable, but the README and SKILL.md do not detail how to obtain this key or its scope, increasing the risk of misconfiguration or mishandling.

Install

  • warning:Installation instructionWhile installation instructions for the MCP server and REST API are provided, the requirement for an `ORACLAW_API_KEY` is mentioned without clear steps on how to obtain it or its necessary scopes.

Practical Utility

  • info:Usage examplesWhile the README provides examples for the REST API and SDKs, and the SKILL.md lists node/edge types, there are no end-to-end, copy-pasteable examples for the `analyze_decision_graph` tool within the skill context.
  • info:Edge casesThe SKILL.md mentions node and edge types and basic requirements, but does not explicitly document failure modes or recovery steps for malformed input or unmet dependencies.

Installation

npx skills add Whatsonyourmind/oraclaw

Runs the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.

Quality Score

75 /100
Analyzed about 24 hours ago

Trust Signals

Last commit12 days ago
Stars8
LicenseMIT
Status
View Source

Similar Extensions

PageRank Analyzer Agent

98

Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer

Skill
ruvnet

OraClaw Pathfind

99

A* pathfinding and task sequencing for AI agents. Find the optimal path through workflows, dependencies, and decision trees. K-shortest paths via Yen's algorithm. Cost/time/risk breakdown.

Skill
Whatsonyourmind

Browser Trace

99

Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.

Skill
browserbase

Agent Quorum Manager

98

Agent skill for quorum-manager - invoke with $agent-quorum-manager

Skill
ruvnet

NetworkX

98

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Skill
K-Dense-AI

AlterLab NetworkX

98

Part of the AlterLab Academic Skills suite. Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Skill
AlterLab-IEU

© 2025 SkillRepo · Find the right skill, skip the noise.