geopolitical-elite-mapping

Generate a confidence-coded geopolitical elite network map from a topic keyword.

52|4|Updated Mar 28, 2026
One-click install
npx skills add https://github.com/katarism/geopolitical-elite-mapping --skill geopolitical-elite-mapping
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geopolitical-elite-mapping
Source: https://github.com/katarism/geopolitical-elite-mapping/tree/main
Command: npx skills add https://github.com/katarism/geopolitical-elite-mapping --skill geopolitical-elite-mapping

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you transform an ambiguous geopolitical topic into a structured elite-network graph, with explicit HIGH/MED/LOW/INFERRED confidence labeling and an accompanying narrative report.

Core Features & Use Cases

  • 6-phase agentic workflow: forces topic scoping, actor discovery, relationship research, confidence audit, visualization output, and report generation in order.
  • Honest confidence-first modeling: every node and edge must be labeled HIGH/MED/LOW/INFERRED, with strict Phase 3 checks before visualization.
  • Time-sliced interactive outputs: generates an interactive HTML viewer with era filtering and a markdown report including actor lists, confidence audit, and relationship verification.
  • Use case: when you need an initial power-relationship “working map” for a fresh topic (e.g., “Middle East oil geopolitics”), but want a transparent, uncertainty-aware structure you can iteratively improve.

Quick Start

Ask the AI to build an elite network for the topic "Middle East oil geopolitics" using the default 1973–2026 scope and then ask you to confirm the issue profile before starting research.

Frequently Asked Questions about geopolitical-elite-mapping

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

FAQPage Schema
How do I map elite networks and power relationships for a geopolitical topic?

To map elite networks, this Skill generates a confidence-coded graph from a topic keyword, applying actor discovery and relationship investigation across factions, proxies, and alliances. It outputs an interactive HTML viewer with era filtering and a markdown verification report.

What is confidence-coded elite network mapping and how does the verification process work?

Confidence-coded elite network mapping labels every node and edge with HIGH, MED, LOW, or INFERRED status to track evidence reliability. The workflow enforces strict Phase 3 checks before visualization, ensuring relationship verification and uncertainty awareness are baked into the output structure.

How do I generate a time-sliced geopolitical graph visualization from a broad research topic?

You generate a time-sliced geopolitical graph by providing a topic keyword like "Middle East oil geopolitics" and confirming the issue profile. The Skill then applies era-based slicing across your defined scope, such as the default 1973–2026 range, to produce interactive visual outputs.

Can I use this elite network mapping approach for a fresh topic without prior actor lists or data?

Yes, you can map a fresh topic without prior data because the 6-phase agentic workflow forces actor discovery and relationship research from scratch. It builds an initial power-relationship working map that you can iteratively improve as new information emerges.

Does geopolitical elite network mapping support custom time ranges for era-based analysis?

Geopolitical elite network mapping supports custom era-based slicing, defaulting to a 1973–2026 scope but allowing adjustments during the mandatory topic confirmation phase. This ensures the actor discovery and relationship investigation fit your specific historical or contemporary research boundaries.

What are the limitations of using inferred confidence labels for elite network relationship verification?

INFERRED confidence labels indicate relationships lacking direct evidence, meaning the graph represents a transparent working hypothesis rather than verified fact. This uncertainty-aware structure requires iterative improvement and manual verification before relying on the mapped connections for definitive conclusions.