Guide · Agent skill
How to use the Geopolitical Risk Analysis agent skill
Updated · written with AI from the project's own documentation and checked against our catalogue data
The geopolitical-risk skill is a single SKILL.md instruction file that gives an AI agent a structured way to reason about wars, sanctions and supply disruptions and how they could move markets. It is written for investors, analysts and students who want a consistent first pass rather than an ad hoc opinion. By the end of this guide you will know how to install the skill, how to phrase requests so the agent uses it, and where its outputs need independent checking.
Geopolitical Risk AnalysisHKUDS/Vibe-Trading · MIT Download the skill Quick start
- 1Download the ZIP. Get the geopolitical-risk ZIP from the skill's page in the directory.
- 2Unzip into the skills folder. Unzip the package into ~/.claude/skills/ for all projects, or into a project's .claude/skills/ folder for one project only.
- 3Or upload it in the Claude apps. In the Claude apps, open Settings, go to Capabilities, then Skills, and upload the skill.
- 4Ask a scenario question. Describe a conflict or sanction, the assets you care about and your time horizon, and mention a hotspot if relevant.
- 5Check the output. Verify every figure, data point and asset direction against current, sourced data before acting on it.
What the skill makes the agent do
The skill gives the agent a three-layer model of geopolitical risk: structural risk (slow-moving rivalries and alliances), situational risk (cyclical escalation over months or quarters), and event risk (sudden shocks on a daily or hourly scale). It also defines five dimensions for assessing a crisis: intensity, persistence, transmission, predictability and reversibility.
It includes monitoring notes for six hotspots: the Strait of Hormuz, the Taiwan Strait, the Red Sea and Suez Canal, the Russia-Ukraine conflict, the South China Sea, and a sixth area covered in the file. For each, it lists risk triggers, proxy indicators to watch such as freight indices, currency and credit measures, and the asset classes it considers likely to rise or fall. The output is text analysis, not a live data feed.
Install the skill from the ZIP
Download the ZIP for the skill from the directory page. Unzip it into your user skills folder, ~/.claude/skills/, so it is available across your projects. To limit it to one project, unzip it into that project's .claude/skills/ folder instead.
If you use the Claude apps rather than a local setup, you can upload the skill instead. Open Settings, go to Capabilities, then Skills, and add the skill there.
- The package contains one file, SKILL.md.
- Make sure the skill folder contains SKILL.md after unzipping.
Trigger the skill with natural requests
The skill is about conflicts, sanctions and supply shocks, so ask in those terms and name the market you care about. Name the scenario, the assets or sectors affected, and the time horizon. Requests that include a hotspot name, such as the Strait of Hormuz or the Taiwan Strait, tie the agent to the relevant section of the playbook.
The file does not list exact trigger phrases, so the examples below are phrasings that match its topics rather than documented commands.
- Walk me through how a closure of the Strait of Hormuz could affect oil, shipping and airline stocks over the next month.
- Score a Taiwan Strait blockade scenario on intensity, persistence, transmission, predictability and reversibility.
- What proxy indicators should my team watch for Red Sea shipping disruption, and what would count as high alert?
- How would expanded sanctions on a major gas exporter pass through to European energy costs?
Read the output as a structured draft
A good use is to have the agent apply the five-dimension scoring to a scenario and list the proxies and asset directions the playbook suggests. Treat the result as a checklist for your own research: it shows what to look at and why, and it gives your team a consistent set of questions.
The asset directions are generic heuristics written as text. The file gives no backtests, data sources or dated figures to confirm them, and the specific statistics it quotes, such as chokepoint shares and freight-time estimates, are stated without sources and may be out of date. Verify any number before you use it.
- Use the framework to structure notes, then check current data for every figure.
- Do not rely on the skill to confirm what is happening now, since it contains no live feed.
What people use it for
- Structuring a first-pass note on how a conflict could affect oil, shipping, semiconductors or currencies.
- Teaching students how geopolitical events transmit into markets using a consistent framework.
- Giving a research team a shared set of indicators to monitor for each hotspot.
- Drafting the scenario section of an event-driven research note before adding sourced data.
Frequently asked questions
Is the geopolitical-risk skill free to use?
The skill is published under the MIT licence, as listed on its page. The licence terms are the authoritative source for what you may do with it, so read the licence file in the repository before reusing it commercially.
What do I need to install and run the geopolitical-risk skill?
The skill lists no requirements. It runs no scripts and uses no network access, and its package contains only a SKILL.md file. You need an agent environment that supports skills, such as a local Claude setup with the ~/.claude/skills/ folder or the Claude apps.
Where do I put the skill folder?
Unzip the package into ~/.claude/skills/ to make it available everywhere, or into a project's .claude/skills/ folder to limit it to that project. In the Claude apps, you can upload it under Settings, then Capabilities, then Skills.
Can I use this skill to make trading decisions?
No, not on its own. The asset directions are generic heuristics, and the file provides no data sources or backtests to verify them. Use the output as a structured starting point and confirm everything with current, sourced data and your own judgement.
Does the skill give me live news or current geopolitical events?
No. The skill contains no live data feed and cannot confirm what is happening now. It provides a framework, indicators and hotspot notes, and you need separate, up-to-date sources for current events.
How does this compare with asking an agent for analysis without a skill?
A skill gives the agent a fixed structure: the same three risk layers, the same five scoring dimensions and the same hotspot indicators each time. Without it, the agent chooses its own framework, which can vary between requests. The skill does not add data or verification.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
This skill suits investors, analysts and students who want a consistent, structured first pass at how a conflict or sanction could affect markets, and teams that need shared indicators for event-driven notes. It is a poor fit for trading or allocation decisions, for relying on its quoted statistics, or for anything that depends on current events, since it has no data sources, backtests or live feed.
Download the skill