osint-investigation

Connect entities across public-record sources into traceable JSON evidence chains.

31|3|Updated May 7, 2026
One-click install
npx skills add https://github.com/markwang2658/hermes-windows-native --skill osint-investigation-markwang2658
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: osint-investigation
Source: https://github.com/markwang2658/hermes-windows-native/tree/main/hermes-agent/optional-skills/research/osint-investigation
Command: npx skills add https://github.com/markwang2658/hermes-windows-native --skill osint-investigation-markwang2658

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Identify and connect entities across multiple public-record sources to build traceable evidence chains.

Core Features & Use Cases

  • Multi-source ingestion and cross-linking across SEC EDGAR, USAspending, OFAC SDN, ICIJ Offshore Leaks, NYC ACRIS, CourtListener, Wayback Machine, Wikipedia + Wikidata, and GDELT.
  • Stdlib-only workflow: data acquisition, entity normalization, cross-source matching, and evidence-chain construction with explicit sources and confidence.
  • Structured findings generation (JSON) with traceable provenance for investigations and due-diligence workflows.

Quick Start

Run the osint-investigation workflow on a sample dataset to generate findings.json.

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 to build an evidence chain for corporate due diligence?

Cross-reference public records by ingesting data from SEC EDGAR, USAspending, and ICIJ Offshore Leaks, then apply entity normalization and matching to construct traceable evidence chains with explicit source citations and confidence levels.

What is the best way to perform sanctions screening and entity resolution across multiple data sources?

Perform sanctions screening by querying the OFAC SDN list, then use entity resolution workflows to normalize and connect matching identities across other public-record sources, generating structured JSON findings with provenance.

How does cross-source OSINT investigation handle property history and litigation research?

Cross-source OSINT investigation handles property and litigation research by acquiring data from NYC ACRIS and CourtListener, applying timing analysis, and cross-linking entities to build a structured record of traceable evidence.

Can I conduct entity resolution using only Python standard library tools without external dependencies?

Yes, you can conduct entity resolution using a deterministic, stdlib-only workflow that handles data acquisition, entity normalization, and cross-source matching without requiring external dependencies or APIs.

Does this OSINT workflow support archived web content and global event data for investigations?

Yes, the OSINT workflow supports archived web content and global event data by ingesting from the Wayback Machine and GDELT, integrating this information into the cross-source matching and evidence-chain construction process.

What limitations exist when using automated entity normalization for public records matching?

Limitations include relying on deterministic stdlib-only matching logic, which may require manual review for ambiguous entity names, and the scope is constrained to the supported public-record sources like SEC EDGAR and Wikipedia.