ingestigate
Investigative intelligence — document search, entity extraction, and relationship graphing. Analyze document corpuses to find connections between people, organizations, and identifiers.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aingestigate/ingestigateWhat This Skill Does
The Ingestigate skill transforms your AI agent into a high-powered investigative analyst. It enables deep-dive research across massive, unstructured document corpuses, allowing for complex entity extraction, relationship graphing, and evidence-based analysis. Whether you are dealing with thousands of PDFs, spreadsheets, or raw email exports, Ingestigate maps connections between people, organizations, and sensitive identifiers like crypto addresses or phone numbers. It doesn't just search for keywords; it understands the structure of the data and provides actionable intelligence by linking entities across disparate files.
Installation
To add this capability to your agent, execute the following command in your terminal: clawhub install openclaw/skills/skills/aingestigate/ingestigate. After installation, ensure you have your INGESTIGATE_TOKEN and INGESTIGATE_BASE_URL configured in your platform's environment settings. This ensures your agent can authenticate securely with the investigation engine without exposing your keys in chat logs.
Use Cases
- Financial Crimes Investigations: Track the flow of funds by identifying wire transfer mentions and connecting individuals to shell organizations.
- Legal Discovery: Quickly parse through thousands of pages of discovery documents to identify recurring people of interest and their specific associations within internal memos.
- Due Diligence: Automate the mapping of corporate networks and beneficial ownership by analyzing public or proprietary document sets for entity overlaps.
- Intelligence Analysis: Aggregate data from multiple file formats to uncover patterns or hidden relationships that manual review would miss.
Example Prompts
- "Analyze the project files in the 'Q3-Financials' collection and map all relationships between 'John Smith' and any offshore corporations identified."
- "I need to know how the 'Acme Corp' entity is linked to the crypto wallet address '1A1zP1eP5QGefi2DMPTfTL5SLmv7DivfNa'. Can you find the source documents proving this connection?"
- "Look through the uploaded depositions and provide a summary of all emails mentioned, including a network map of who is communicating with whom."
Tips & Limitations
- Be Specific: When tracing paths, ensure you are using the normalized values for entity names to get the most accurate results from the graph database.
- Authentication First: Always verify your environment variables before starting a large analysis task to prevent mid-workflow interruptions.
- Evidence Matters: Always ask the agent to cite specific document IDs to ensure your final report is verifiable.
- Limitations: Large graph queries (over 20 bridge nodes) may take longer to compute; if a query hangs, try narrowing your entity search filters first. The skill is designed for text-heavy documents and may require preprocessing for heavily obfuscated or poor-quality image files.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aingestigate-ingestigate": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, data-collection, external-api