osint-investigation

Automate public record acquisition and cross-referencing to construct evidence chains.

Updated Jun 25, 2026

Search Tags:#investigation #compliance #data analysis #due diligence #osint #public records

Ready to run

npx skills add https://github.com/Rheasilvia/hermes-desktop --skill osint-investigation-rheasilvia

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: osint-investigation
Source: https://github.com/Rheasilvia/hermes-desktop/tree/main/optional-skills/research/osint-investigation
Command: npx skills add https://github.com/Rheasilvia/hermes-desktop --skill osint-investigation-rheasilvia

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the challenge of manually cross-referencing fragmented public records, allowing you to build evidence chains and identify relationships between entities across disparate government and corporate databases.

Core Features & Use Cases

Multi-Source Data Acquisition: Fetch data from SEC EDGAR, USAspending, OpenCorporates, CourtListener, and more using standardized scripts.
Entity Resolution: Automatically link entities across different datasets using normalized naming and fuzzy matching logic.
Statistical Analysis: Perform timing correlation tests to identify suspicious patterns, such as lobbying filings occurring in close proximity to government contract awards.

Quick Start

Use the osint-investigation skill to fetch corporate filings for a specific company and cross-reference them with federal contract data to identify potential conflicts of interest.

Frequently Asked Questions about osint-investigation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I cross-reference public records for due diligence investigations?▼

Cross-referencing public records for due diligence involves acquiring data from fragmented government and corporate databases and applying entity resolution to build evidence chains. This skill automates that acquisition and normalization process across heterogeneous data sources.

Can I perform sanctions screening using SEC EDGAR and USAspending data?▼

Yes, sanctions screening can be performed by fetching corporate filings from SEC EDGAR and cross-referencing them with federal contract data from USAspending. This process identifies potential conflicts of interest and maps financial relationships.

What is the best way to resolve entities across disparate corporate databases?▼

Resolving entities across disparate corporate databases requires normalized naming and fuzzy matching logic to link records. The skill applies these techniques to standardized CSV outputs to automatically connect related entities across different datasets.

Do I need Python to run statistical timing analysis on normalized CSV outputs?▼

Yes, you need Python standard library execution to perform statistical timing analysis on normalized CSV outputs. This environment is required to run the scripts that identify suspicious patterns, such as lobbying filings occurring near government contract awards.

How does timing correlation work for identifying suspicious financial patterns?▼

Timing correlation for identifying suspicious financial patterns works by applying statistical timing analysis to normalized CSV outputs. It detects anomalies such as lobbying filings occurring in close temporal proximity to government contract awards across cross-referenced datasets.

What are the limitations of automated entity resolution in OpenCorporates and CourtListener data?▼

Automated entity resolution in OpenCorporates and CourtListener data is limited by the accuracy of normalized naming and fuzzy matching logic. Heterogeneous data sources with inconsistent formatting can hinder the construction of reliable evidence chains.