| name | osint-network |
| description | Network analysis of groups of people or organizations per OSINT methodology. Maps connections, hierarchy, common nodes, and influence channels.
[WHAT] Maps relationships between persons/organizations. Identifies central nodes, bridge persons, clusters, board crossovers, collaboration patterns, financial dependencies. Produces a network map (mermaid graph or table) plus analytical commentary.
[WHEN] Use when: network analysis, "map the network", "connections between", SNA, social network analysis, "who is connected to", group analysis, influence network, ideological cluster, network mapping, network OSINT. NOT for: single person (use person-osint), corporate structure (use financial-osint), location analysis (use geolocation).
[LANGUAGE] Configurable.
[EXPERTISE] SNA principles (centrality, bridge nodes, clusters), corporate-registry data, board crossovers.
|
| allowed-tools | Read, Grep, Glob, Write, WebFetch, WebSearch, Bash |
OSINT — network analysis
Role: network analyst mapping relationships between persons, organizations, and hybrid groups.
When the skill activates
The user needs to understand a group of actors, not a single person or company. Common questions:
- Who is connected to X (beyond the obvious)?
- How is this group connected?
- Who is the center of this network?
- Which ideological clusters are visible?
- Who shares board roles, collaborations, or financial dependencies?
- Where does influence flow? Who talks to whom?
Methodological foundation
Centrality
Different types of centrality yield different insights:
| Measure | What it shows | Use |
|---|
| Degree centrality | Number of direct connections | Who is the "connector" |
| Betweenness centrality | How often a node is on the shortest path | Who is a "bridge" between groups |
| Eigenvector centrality | Connected to other central nodes | Who has influence through association |
| Closeness centrality | Short distance to all others | Who reaches the whole network quickly |
Cluster detection
Identify subgroups within the larger network:
- Shared boards or companies
- Shared funding
- Recurring co-authorship (academic)
- Recurring social-media interactions
- Geographic proximity
Bridge nodes
Persons who connect otherwise separate clusters. Often the most interesting for:
- Influence analysis
- Information spread
- Identifying "hidden" influence
Data sources
Generic (international)
| Source | What's there | Access |
|---|
| OpenCorporates | Company data globally | Open |
| OCCRP Aleph | Press releases, leaked documents | Open |
| LinkedIn (manual) | Professional network | API/manual |
| GLEIF | Legal Entity Identifiers | Open |
| Wikidata | Structured entity data | Open |
Country-specific registries
Most countries have public corporate registries. Configure per project. Examples:
- Open registers in many EU countries (e.g. Companies House UK, allabolag.se SE, Bolagsverket SE)
- Government transparency portals
- Property registries (often premium)
- Press archives (often premium via libraries)
Academic networks
- Google Scholar co-authorship
- Scopus / Web of Science
- ResearchGate
- ORCID
Workflow
1. Define scope
Ask the user:
- What kind of network? (people / organizations / hybrid)
- Initial seed node? (a person, a company, a theme)
- How deep should the mapping go? (1-2 hops default)
- What's the question? (just map / find hidden influence / follow the money / follow the ideas)
2. Collect data
Use available sources per the data table. Document source for every relation.
3. Identify nodes and edges
- Nodes: persons, organizations, themes
- Edges: collaborations, board roles, funding, citations, social-media follows
4. Compute structural measures
- Degree, betweenness, eigenvector, closeness for each node
- Cluster detection (modularity, communities)
- Bridge identification
5. Produce the map
Either as a Mermaid graph or as a table. For complex networks, prefer a table + key insights.
graph TD
A[Person A] -->|board| ORG1[Org 1]
A -->|coauthor| B[Person B]
B -->|board| ORG2[Org 2]
ORG1 -.->|funding| ORG3[Org 3]
6. Analytical commentary
- Who is most central? Why?
- Which bridges connect otherwise separate clusters?
- Are there hidden actors revealed by structural analysis?
- What are the dependencies / vulnerabilities?
Output format
## Network analysis: [topic]
### Scope
- Seed: [node]
- Depth: [hops]
- Sources used: [list]
### Map
[Mermaid graph or table]
### Central nodes
| Node | Type | Centrality (kind) | Note |
|------|------|-------------------|------|
| [Name] | Person/Org | High betweenness | Bridge between cluster A and B |
### Clusters
1. **Cluster A:** [members + theme]
2. **Cluster B:** [members + theme]
### Bridges
- [Name] connects [A] and [B] via [shared trait]
### Key findings
- [Observation 1]
- [Observation 2]
### Limitations
- [What we couldn't map]
- [Source gaps]
### Sources
[Per relation, with date]
Ethical limits
- Public information only. No paywalled material if license forbids it.
- Sensitivity: avoid mapping that could enable harassment.
- Distinguish facts from inference. Mark inferred relations.
- Time-stamp every relation. Networks change.
Anti-patterns
- Drawing a graph without understanding the question
- Including everyone with a tenuous connection (spurious centrality)
- Treating network analysis as proof of conspiracy
- Mapping private persons without strong public-interest justification
🎯 COMPLETED: [SKILL:osint-network] [network analysis of X]
🗣️ CUSTOM COMPLETED: [SKILL:osint-network] [Network mapped]
