Trade Policy Analysis

---
name: trade-policy-analysis
description: "Simulates trade policy and tariff scenarios with quantitative trade and CGE models, including retaliation, value-chain propagation and welfare effects."
---
<!-- Generated from .claude/skills/trade-policy-analysis/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->

# /trade-policy-analysis — Trade Policy Analysis

**Category:** Analysis · **Primary agent:** `trade-policy-simulation-specialist`

Simulates trade policy and tariff scenarios with quantitative trade and CGE models, including retaliation, value-chain propagation and welfare effects.

Arguments: whatever the user wrote after the command name.

## Purpose
Simulate tariff and trade-policy scenarios (including retaliation and value-chain propagation) with quantitative trade and CGE models, decompose welfare into terms-of-trade, efficiency and reallocation effects, and report winners and losers by country, sector and household group. The output shows how conclusions depend on elasticities, closures and the trade-balance treatment.

**Use it when** assessing tariffs, trade wars, trade agreements, export restrictions or border measures.

**Do not use it when** a new trade model must be built and estimated (`/build-trade-model`), or the shock is a physical supply disruption (`/supply-chain-shock`).

## Before you start
1. **Check required inputs.** For each input below record `FOUND` or `ABSENT` (never 'assumed'):
   - Approved trade or CGE model
   - Tariff and trade-cost data
   If a required input is `ABSENT`, that part is **`NOT ASSESSED — NO DATA`**: do not estimate or invent it; name what is missing and which skill produces it. If all required inputs are absent, stop and say so.
2. **Check confidentiality.** Identify the data classification level of the inputs (`.claude/docs/confidentiality-and-ai-use.md`). Do not proceed with restricted or confidential data in a way the policy does not allow.
3. **Collaboration.** Follow `.claude/docs/collaboration-protocol.md`: ask questions first, present options, get approval before writing files, and update `production/session-state/active.md` after each approved section.

## Agents
- `trade-policy-simulation-specialist` — primary agent; coordinates the work and integrates results
- `cge-modeling-specialist` — Builds computable general equilibrium models
- `trade-gvc-specialist` — Models trade and global value chains
- `production-networks-specialist` — Models production networks and supply chains
- `global-spillover-specialist` — Analyzes global spillovers

Each agent is defined in `.claude/agents/<name>.md`. If your tool runs subagents, run these agents as subagents, in parallel where the steps are independent; otherwise read each agent's file and apply its instructions in turn. Subagents only write to the paths named in your instructions.

## Key design decisions (present options, let the user choose)
| Decision | Typical options | What it changes |
|---|---|---|
| Scenario | unilateral tariffs, retaliation, agreement, export restrictions | Policy space |
| Models | structural gravity GE, multi-sector with IO links, CGE | Channels covered |
| Elasticities | estimated, literature low/central/high | Welfare magnitudes |
| Trade balance | balanced, fixed deficits | Counterfactual results |
| Revenue | rebated lump sum, used in budget | Fiscal and welfare effects |

## Workflow
1. Define the scenario: instruments, countries, sectors, retaliation and timing
2. Run in at least two models or elasticity sets
3. Decompose effects: terms of trade, efficiency, reallocation, value-chain propagation
4. Report winners and losers by country, sector and, where possible, household group
5. State elasticity and closure dependence of the conclusions

## Checkpoints with the user
- After the scenario: confirm instruments and retaliation
- After results: confirm groups for winners-and-losers reporting

## Common pitfalls
- Trade-flow changes reported as welfare
- Single-sector models for tariffs on intermediates
- Unstated trade-balance treatment
- Tariff revenue ignored

## Output
`forecasts/trade/<name>.md`

The report defines the scenario, presents results by model and elasticity set, decomposes welfare, and lists winners and losers with caveats.

## Gate / verdict
- At least two models or elasticity sets used
- Trade balance treatment stated
- Welfare is decomposed into its sources
- Tariff revenue treatment is stated

## Suggested next steps
- `/policy-brief`
- `/chart-pack`