A powerful tool for building Neo4j knowledge graphs from OSINT data to discover hidden connections and community patterns.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install osint-graph-analyzer
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install osint-graph-analyzer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
OSINT Graph Analyzer is a specialized utility designed to transform fragmented data from Openclaw Skills into structured, actionable intelligence. By leveraging Neo4j's graph database engine, it enables investigators and analysts to ingest data from diverse sources—including social media APIs, CSV files, and JSON Cypher queries—to build comprehensive knowledge graphs. The tool excels at identifying entity links across platforms and revealing the underlying structure of complex networks through advanced mathematical algorithms, providing a clear visual representation of otherwise hidden relationships.
Ensure you have Python 3.9+ and Neo4j 5.x installed. You can launch a local instance via Docker to begin processing data for Openclaw Skills:
docker run -d --name neo4j -p 7474:7474 -p 7687:7687 -e NEO4J_AUTH=neo4j/password neo4j:5.23
Install the neo4j-driver package and ingest your data source:
python3 scripts/osint-graph.py --ingest data/sources.csv
The skill organizes data using a node-and-edge model optimized for graph traversal and pattern recognition.
| Component | Description | Examples |
|---|---|---|
| Nodes | Individual entities identified in the data | Person, Handle, Organization, Location |
| Edges | Logical relationships between nodes | MENTIONED, FOLLOWS, LIVES_IN, WORKS_AT |
| Properties | Metadata attributes for nodes and edges | Country, Timestamp, Verification status |
Loading
A centralized tool for discovering, scoring, and managing Model Context Protocol (MCP) servers through semantic search and quality metrics.

Agentic Compass is a local-only self-reflection tool that transforms AI agent memory logs into objective action plans and measurable performance metrics.

A unified verification layer that validates AI agent identities and reputation scores across multiple on-chain and off-chain trust protocols.

Create high-signal, actionable digests from agent community feeds and forums by clustering themes and ranking signal.

An asynchronous Python-based tool that enables AI agents to aggregate and deduplicate search results from multiple search engines simultaneously.

A comprehensive self-audit tool designed to verify workspace file structures and ensure adherence to standard OpenClaw conventions.








































