Gulf & Middle East Intelligence Skill
A reusable regional reasoning skill for AI agents preparing decision memos on Gulf and Middle East exposure.
Use it when a general policy memo misses the region's mechanisms: Iran/GCC and Iraq exposure, correspondent banking, ownership, sovereign capital, energy flows, and shipping chokepoints such as the Hormuz, Bab el-Mandeb, and Red Sea routes.
This is a reasoning skill and a structured decision framework, not a live intelligence feed. The included experimental MCP server is a skeleton: every tool returns not_implemented. It does not retrieve live intelligence, screen counterparties, or issue clearances.
Why this exists
Regional geopolitical and sanctions questions are often distorted by generic intelligence prompts. This skill gives an agent a tighter operating model for Gulf and Middle East analysis:
- region-specific mechanisms and risk archetypes
- explicit separation of facts, inference, assumptions, and source conflicts
- clear comparison of alternatives and escalation conditions
- evidence-aware output that can be checked by a deterministic verifier
It is designed to improve the quality of strategic reasoning, not to replace human judgment or legal review.
What this project includes
- a reusable reasoning contract in SKILL.md
- optional runtime overlays for Claude and Codex
- worked examples and source-backed patterns in examples/README.md
- an evidence handoff to Agenda Intelligence MD for deterministic checks
- regional structure and guardrails for strategic analysis tasks
Choose a starting point
| Your task | Worked example | Evidence to inspect |
|---|---|---|
| Maritime route disruption | Open example | Illustrative alternatives and assumptions |
| GCC correspondent banking | Open example | A dated source-backed example |
| Iraq banking source pack | Open example | Claims tied to supplied sources |
Start with the skill
- Load the canonical SKILL.md.
- Add the matching runtime overlay: Claude or Codex.
- For a recurring practice, use the cold-start interview to establish decision context and practice profile.
- Give the agent a concrete decision brief.
Example prompt:
Use Gulf & Middle East Intelligence Skill.
Question: What evidence would justify changing a shipping route?
Decision: proceed with a limited pilot, change the plan, or wait.
Audience: risk committee.
Geography: GCC, Iran, and the relevant maritime route.
Time horizon: next 90 days.
Evidence mode: reasoning-only; this is a hypothetical case.
Separate facts from assumptions, compare alternatives, and identify
missing evidence and escalation conditions.
For sourced analysis, choose live-source-backed, user-provided sources, or illustrative source packet explicitly. Supply the source packet or authorize collection. Preserve source dates and disclose unresolved source conflicts.
See regional logic, source guide, and analysis contract. The currency watch is a supporting regional lens for financial exposure analysis.
Place in the system
| Repository | Responsibility |
|---|---|
| Global Think Tank Analyst | General decision-memo method and executable artifact toolkit |
| This skill | Regional mechanisms, sources, and uncertainty |
| Central Asia & Caspian | Complementary reasoning for exposure crossing the regional boundary |
| Agenda Intelligence MD | Deterministic checks on supplied claim/source records |
The companion patterns explain how this skill is composed with related skills. Loading the skills alone does not invoke a verifier or authorize an external action. Evidence-packet checks assess declared support and consistency; they do not validate real-world facts on their own.
Examples
Start with the example guide, then inspect a case that matches your evidence mode:
| Example | What to inspect |
|---|---|
| Hormuz disruption | Illustrative packet and shipping alternatives |
| GCC banking | Dated primary-source evidence |
| Iraq banking packet | Supplied sources and bounded conclusions |
| Conflicting oil trackers | Unresolved disagreement in an illustrative packet |
The current set contains 9 flagship examples: 1 reasoning-only, 2 illustrative source packet, 3 live-source-backed, and 3 user-provided sources. 6 of 9 (67%) are source-anchored.
Source-backed examples are historical snapshots. Recheck current primary sources before reuse. Example counts describe coverage, not validated analytical performance.
What this is not
This project does not:
- provide live regional intelligence feeds
- screen counterparties or sanctions exposure automatically
- certify legal, regulatory, or sanctions compliance
- authorize external action or payment decisions
- substitute for a human reviewer in operational decisions
The skill is a structured reasoning and evidence-handling layer. The actual decision remains with a human or an authorized process.
Validation and limits
The repository records its artifact and structural evaluation work, while substantive regional reasoning lift remains unproven. The next specialist-lift evaluation tracks the relevant quality frontier.
There is no public, attributable real-use record. No production-usage, adoption, or benchmark numbers are claimed. STATUS.md preserves the evaluation record and the limits of self-checking.
Human review is required before operational use. The skill does not provide legal advice, sanctions clearance, or payment enforcement. The guardrails define these boundaries and review expectations.
Documentation and contribution
- SKILL.md: canonical instructions and reasoning contract
- Evidence-packet handoff: the primary verification contract
- Public signal examples: latest, archive index, and JSON Feed
- CONTRIBUTING.md and AGENTS.md: contribution workflow and repository constraints
Run the repository validator before submitting changes:
python3 scripts/validate.py
The skill package and examples remain the primary interface. The Python MCP skeleton is retained for development and does not deliver analytical findings.