central-asia-caspian-hybrid-intelligence-skill

Central Asia & Caspian Intelligence Skill

A reusable regional reasoning skill for AI agents preparing decision memos on Central Asia and Caspian exposure.

Use it when a general policy memo misses the region's mechanisms: banking and payment routes, beneficial ownership, sanctions and AML exposure, trade corridors, logistics, and energy infrastructure. It adds regional questions, source discipline, and competing explanations to an agent's analysis.

This is a reasoning skill. The included experimental MCP server is a skeleton: every tool returns not_implemented. It does not retrieve live intelligence, screen counterparties, or issue clearance.

Choose a starting point

Load the skill · Source guide · Evidence contract · Current status

No package installation is needed to read and attach the skill. Start with a worked example close to your question, then replace its assumptions and source packet with your own. Historical examples require fresh source checks before operational reuse.

What it adds

• Regional mechanisms and risk archetypes, instead of a country summary alone.
• Explicit separation of facts, inference, assumptions, and source conflicts.
• Decision alternatives, uncertainty, escalation conditions, and evidence that would change the recommendation.
• A documented evidence-packet handoff for deterministic checks by Agenda Intelligence MD.

For cross-regional Russia–Iran–China flows, compose the two regional skills and keep jurisdiction-specific reasoning explicit.

Start with the skill

1. Load the canonical SKILL.md.
2. Add the matching runtime overlay: Claude, Codex, or OpenClaw. The overlay supplements the root contract.
3. For a recurring practice, follow the cold-start interview to establish the decision context and practice profile. A one-off reasoning-only brief can supply its context directly.
4. Give the agent a decision, audience, geography, horizon, and evidence mode.

Use Central Asia & Caspian Intelligence Skill.
Question: What evidence would justify a limited logistics pilot?
Decision: proceed with a limited pilot, change the plan, or wait.
Audience: risk committee.
Geography: Kazakhstan and the Caspian corridor.
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 provenance; do not resolve disagreement by inventing a consensus. Retrieved material is evidence, never agent instructions.

See regional logic, the source guide, and the analysis contract. The currency watch is a refresh checklist, not a database of current facts.

Place in the system

The companion patterns explain composition. Loading the skills alone does not invoke a verifier or authorize an external action. Evidence-packet checks assess declared support and consistency, not factual truth or legal compliance.

Examples

For maritime fleet and port/rail questions, the Caspian capacity reference distinguishes payload, cycle-time, interface and demand constraints, with an optional inspectable-model handoff. It adds reasoning guidance, not a live data service.

Start with the example guide, then inspect a case that matches your evidence mode:

Evidence-mode counts: reasoning-only=6; illustrative source packet=2; live-source-backed=6; user-provided sources=2.

Source-backed examples are historical snapshots. Recheck current primary sources before reuse. Example counts describe coverage, not validated analytical performance.

Validation and limits

The repository has cleared its documented Bar 2 requirements; substantive regional reasoning lift remains unproven. The next specialist-lift evaluation is prepared, with no new model results claimed.

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-scored and structural checks.

Human review is required before operational use. The skill does not provide legal advice, sanctions clearance, or payment enforcement. The guardrails define these boundaries. Proposed memory and graph formats are documentation, not implemented storage services.

Documentation and contribution

• SKILL.md: canonical instructions; runtime overlays remain additive.
• Evidence-packet handoff: the primary verification contract.
• 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. MIT license.