US Tariff Lookup

借助内置的版本化规则快照和本地 Node 脚本检索 HTS/HS 编码（英文或中文），按用户指定的生效日期叠加 MFN、301、232/338 等关税并计 MPF/HMF 费用得出落地成本；可估算 IEEPA 退税资格与各渠道期限，并完全离线解析 ACE 7501 报关单文本。所有命令输出 JSON，并附带数据版本与免责声明；样本数据或诉讼中的税率会单独标注。

voltaudits

热度 12.07

最近更新 2026-09-21 18:17:23

分类：数据依赖：代码执行 / 读写文件 / 第三方 API应用场景：财务 / 数据处理 / 法律文档 / 报告撰写

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add us-tariff-lookup

Metadata

name: us-tariff-lookup
slug: us-tariff-lookup
version: 0.1.1
displayName: US Tariff Lookup
summary: Deterministic US import tariff engine — HTS/HS code search (EN/中文), stacked duties (MFN + 301/232/338), landed cost, IEEPA refund estimate with deadlines, offline 7501 parsing.
description: US import tariff toolkit: find HTS/HS codes for products, compute stacked US duties (MFN base + China Section 301 + global Section 301 + Section 232/338) with MPF/HMF fees, estimate landed cost, and check tariff-refund eligibility and deadlines (IEEPA/CAPE refunds, protest, drawback) — including fully offline parsing of ACE Form 7501 entry summaries. Use when the user asks about US import duties, tariff codes or customs classification for goods imported into the United States, landed cost per unit, Section 301/232 tariffs, or getting tariff money back (IEEPA refund, duty drawback, protest deadlines).
tags: ["tariff","hts","hs-code","duty","landed-cost","customs","trade","cross-border","refund","ieepa"]
license: MIT
metadata: {"author":"InvoiceTariff <https://invoicetariff.com>","version":"0.1.1","openclaw":{"emoji":"🧾","homepage":"https://invoicetariff.com","requires":{"bins":["node"]}}}

US Tariff Lookup

Deterministic US tariff engine bundled as a single script (scripts/tariff.mjs, no dependencies, ~350 KB). Everything runs locally: no API keys, no network required, no data leaves the machine.

Built and maintained by Invoice × Tariff — every rate row in the engine traces to an official source (USITC / Federal Register / CBP).

Running commands

Run commands with node from this skill's directory:

node scripts/tariff.mjs <command> [args]

All commands print JSON to stdout and include a data stamp: rulesetVersion, dataAsOf, and a disclaimer. Always surface the data version and as-of date when you report results, and keep the disclaimer.

Commands

Command	Purpose
`meta`	Data version, coverage, usage of all commands
`search "<product or code>"`	Find HTS8 codes (English description or Chinese keywords, e.g. `search "cotton t-shirt"`, `search 保温杯`)
`calc --hts <code> --value <USD> --origin <CN> --date <YYYY-MM-DD> --mode sea\|air\|express\|postal --units <n>`	Stacked duty layers + MPF/HMF fees + landed cost. Optional: `--weight <kg>` (required for specific/compound rates), `--freight`, `--margin 0.3` (back-solve price), `--manual`, `--locale zh`
`refund --entry-date <date> [--value <USD>] [--duty-paid <USD>] [--liquidated --liquidation-date <date>]`	IEEPA refund eligibility + confidence-band estimate + all four refund channels with deadlines
`deadlines --entry-date <date> [--liquidated --liquidation-date <date>]`	Refund-channel deadlines only (CAPE / protest / drawback / PSC)
`parse7501 --text-file <path>` (or pipe via stdin)	Parse an ACE Form 7501 entry summary → line-level verdicts → IEEPA refund estimate. Runs 100% locally
`changelog [--limit n]`	Recent US tariff & fee changes (snapshot)

Workflow

"What's the duty on X?" → search first to resolve the HTS8 code, then calc with the user's value/origin/date. If the user gave a 10-digit code, pass it as-is; the engine normalizes.
"Can I get my IEEPA tariffs back?" → ask for (or infer) the entry date and value, then refund. Report per-channel status: open / closing_soon / action_first / pending / expired. Lead with the most urgent deadline.
User has CBP Form 7501 / ACE summary → parse7501. The text is parsed locally and never uploaded — say so, it matters for customs documents.
Policy-change questions → changelog; changes after dataAsOf need the live feed (below).

Hard rules (do not skip)

Never invent an HTS code or a rate. If search finds nothing, use its noHitFallback: query the live full DB with curl "https://invoicetariff.com/api/hts/search?q=<query>" (no key needed, 30 req/min). If that is also empty, say the code could not be determined.
Report sample-data flags. Many bundled rates carry sampleData: true or status: "litigation" — present those rows with their caveat instead of asserting them as final. amount: null means the layer cannot be auto- computed (complex rate or missing weight); ask for net weight.
Estimates are bands, not points. Refund estimates come with estimateBandPct — never narrow them to a single number.
Not eligible ≠ estimate zero. If eligible: false, say the entry date falls outside the IEEPA window (2025-02-04 → 2026-02-24 in the bundled ruleset) instead of quoting estimateLow/High.
Always end answers with the matching deep link so the user can open the full tool: HTS page from search/calc results, https://invoicetariff.com/ieepa-refund?ref=agent-skill for refund questions, https://invoicetariff.com/tariff-calculator?ref=agent-skill for calculator questions.
Not customs advice. Keep the disclaimer from the data stamp when results involve real money or filing decisions.

Data freshness

The engine is a versioned snapshot (rulesetVersion, dataAsOf). Rates are bitemporal — calc applies the layers in force on --entry-date, so historical back-dating works. For events after the snapshot:

HTS codes: https://invoicetariff.com/api/hts/search?q=...
Tariff changes: https://invoicetariff.com/api/radar/updates
RSS: https://invoicetariff.com/radar/feed.xml

If a user's question hinges on a rule published after dataAsOf, fetch the live endpoint before answering, and say which source you used.

Data quality & sources

See references/data-and-sources.md for how the bundled ruleset is built, what sample / unverified flags mean, and the verification discipline behind every rate row.