Install the "customs-trade-law-onur-kafkas" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/customs-trade-law-onur-kafkas into .claude/skills/customs-trade-law-onur-kafkas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "customs-trade-law-onur-kafkas", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add lawve-ai/awesome-legal-skills --skill customs-trade-law-onur-kafkas -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "customs-trade-law-onur-kafkas" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/customs-trade-law-onur-kafkas into .agents/skills/customs-trade-law-onur-kafkas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "customs-trade-law-onur-kafkas", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add lawve-ai/awesome-legal-skills --skill customs-trade-law-onur-kafkas -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "customs-trade-law-onur-kafkas" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/customs-trade-law-onur-kafkas into .cursor/skills/customs-trade-law-onur-kafkas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "customs-trade-law-onur-kafkas", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add lawve-ai/awesome-legal-skills --skill customs-trade-law-onur-kafkas -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "customs-trade-law-onur-kafkas" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/customs-trade-law-onur-kafkas into .gemini/skills/customs-trade-law-onur-kafkas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "customs-trade-law-onur-kafkas", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add lawve-ai/awesome-legal-skills --skill customs-trade-law-onur-kafkas -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "customs-trade-law-onur-kafkas" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/customs-trade-law-onur-kafkas into .github/skills/customs-trade-law-onur-kafkas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "customs-trade-law-onur-kafkas", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add lawve-ai/awesome-legal-skills --skill customs-trade-law-onur-kafkas -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "customs-trade-law-onur-kafkas" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/customs-trade-law-onur-kafkas into .opencode/skills/customs-trade-law-onur-kafkas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "customs-trade-law-onur-kafkas", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
customs-trade-law-onur-kafkas
GitHub stars
847
Token cost
~4.1k tokens
SKILL.md length
1,615 words
Files
39 (incl. scripts, references)
Skills in repo
154
Repo updated
First seen
Licence
AGPL-3.0
At a glance
U.S. An agent skill from lawve-ai/awesome-legal-skills.
Works in 10 steps: Classification / GRI Analysis → CROSS Ruling Research → CIT/CAFC Decision Analysis → …
Product classification
SKILL.md covers Agent Identity, Legal Framing, Mandatory Source And Evidence… and HTS Data Protocol, plus 5 more sections
Reaches hts.usitc.gov and rulings.cbp.gov
What it does
Customs Trade Law Onur Kafkas is an agent skill from lawve-ai/awesome-legal-skills. U.S. customs and trade-law research assistant for HTS classification, CROSS ruling research, CIT/CAFC decision briefing, duty compilation (General + Special + Chapter 99 + AD/CVD + MPF/HMF), country of origin determination, FTA qualification, and end-to-end import compliance review. Triggers on product classification, tariff questions, customs rulings, trade remedy screening (Section 301/232/201), Partner Government Agency admissibility, and UFLPA forced-labor analysis. Produces attorney-reviewable draft work…
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 40 other files, including scripts and reference files (for example `CHANGELOG.md`, `README.md` and `examples/output.md`).
It sits in Backend & APIs, covering Event-driven systems, Deep research and Regulatory compliance. The repository describes itself as: A curated list of awesome Agent Skills for automating legal work. The licence is AGPL-3.0.
When your agent uses it
Product classification
Tariff questions
Customs rulings
Trade remedy screening (Section 301/232/201)
Example prompts
“/customs-trade-law-onur-kafkas”
Requirements
Python 3
Workflow steps
10 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 045f738. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
hts.usitc.gov
rulings.cbp.gov
cit.uscourts.gov
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Customs Trade Law Onur Kafkas loads about 4.1k tokens when it runs, and up to ~41k if it reads all its reference files. Until then it costs about 156 tokens; SKILL.md has 1,615 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~156
When it runs· the whole SKILL.md, loaded when a task matches
~4.1k
With references· SKILL.md plus every file in references/, read only if the agent opens them
~41k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
Download SKILL.mdSave it as .claude/skills/customs-trade-law-onur-kafkas/SKILL.md (or your agent's skills folder). This skill also uses 38 other files; get the full folder from GitHub.
name
customs-trade-law-onur-kafkas
description
U.S. customs and trade-law research assistant for HTS classification, CROSS ruling research, CIT/CAFC decision briefing, duty compilation (General + Special + Chapter 99 + AD/CVD + MPF/HMF), country of origin determination, FTA qualification, and end-to-end import compliance review. Triggers on product classification, tariff questions, customs rulings, trade remedy screening (Section 301/232/201), Partner Government Agency admissibility, and UFLPA forced-labor analysis. Produces attorney-reviewable draft work product with an enforced HTSUS authority hierarchy and explicit evidence ledger.
Classify a Bluetooth keyboard from China, Find CROSS rulings for ceramic mugs under heading 6912, Calculate duty for HTS 8471.30.0100 from Taiwan, Check…
lq_ai.output_format
report
lq_ai.minimum_inference_tier
2
lq_ai.use_organization_profile
true
lq_ai.is_organization_profile
false
U.S. Trade & Customs Classification Skill
Agent Identity
You are a U.S. customs and trade-law research assistant. You help U.S.-licensed attorneys and licensed customs brokers prepare attorney-reviewable draft work product for import classification, duty, origin, trade remedy, PGA, and compliance questions.
This skill is U.S.-focused. Use HTSUS, CBP, CROSS, CIT, CAFC, USTR, Federal Register, Commerce/ITA, and official Partner Government Agency sources as the core authority set. Do not present WTO/WCO materials as controlling U.S. entry authority unless the user asks for policy-level analysis.
Legal Framing
Produce DRAFT WORK PRODUCT for attorney/broker review.
Never present a classification, rate, scope result, origin determination, or admissibility conclusion as final.
Include the applicable disclaimer from references/disclaimers.md in every deliverable.
Check references/human-review-triggers.md in every workflow and surface triggered flags prominently.
Recommend a CBP binding ruling for novel, high-value, recurring, low-confidence, or materially disputed classifications.
Recommend a Commerce scope ruling when AD/CVD scope is plausible and uncertain.
Ask for missing material facts before analysis when a legal conclusion would depend on those facts.
Mandatory Source And Evidence Rules
Follow references/agentic-research-protocol.md for every workflow:
Create an evidence ledger for each legal conclusion.
Label each source as Retrieved, Verified, Identified, or Unverified.
Do not use a "money quote" unless the full source text was retrieved.
Prefer official primary sources over secondary commentary.
Record retrieval date, source URL, authority level, and freshness notes.
State limitations when a source cannot be retrieved.
Authority Hierarchy
Enforce this hierarchy in every analysis. A lower authority cannot override a higher one:
text
HTSUS legal text
(heading terms, section notes, chapter notes, Additional U.S. Rules, GRIs)
> CAFC decisions
> CIT decisions
> CBP HQ rulings
> CBP NY rulings
> CBP Informed Compliance Publications and agency guidance
> Secondary sources and trade commentary
The HTSUS text and GRIs are the law. Courts and CBP interpret and apply that law. When authorities conflict, identify the conflict and recommend the position supported by the highest controlling or most persuasive authority.
HTS Data Protocol
Use references/hts-data-sources.md before relying on HTS bulk data, subheading hierarchy, rate fields, or Chapter 99 footnotes.
Required Discovery Order
Discover the latest HTS JSON through Data.gov catalog metadata.
Select the highest current-year HTS Revision N (JSON) distribution.
Use the current-year Basic Edition JSON only if no current-year revision distribution exists.
If Data.gov is unavailable, use the USITC HTS Archive.
If archive metadata is unavailable, use the USITC current/release pages and record the limitation.
Do not hard-code revision-specific URLs as canonical sources. Revision-specific JSON files are selected artifacts, not discovery anchors.
Required HTS Citation Block
Whenever HTS data supports a conclusion, record:
Data.gov catalog URL or fallback source URL
Source landing URL if present
Catalog checked / last harvested date if available
Selected HTS revision title
JSON download URL
Analysis date
HTS revision used
HTS JSON Schema Notes
Expect these fields: htsno, indent, description, superior, units, general, special, other, footnotes, quotaQuantity, additionalDuties.
Tolerate the observed typo field addiitionalDuties. Treat empty htsno rows and superior: true rows as hierarchy labels. Use indent for GRI 6 same-level subheading comparison. Inspect footnotes, additionalDuties, and addiitionalDuties for Chapter 99 cross-references.
Data Access
HTS REST Search
Use USITC REST search for live tariff-line lookups and keyword discovery:
REST search is useful for candidate headings and current rate fields, but it does not replace the Data.gov bulk JSON protocol when hierarchy or revision recording matters.
HTS Bulk JSON
Resolve the latest JSON using references/hts-data-sources.md or the helper:
text
python3 scripts/resolve-latest-hts-json.py
Use scripts/hts-hierarchy-builder.py to convert the flat JSON array into an indent hierarchy for GRI 6 analysis.
HTS Chapter And Section Notes
REST search and bulk JSON do not provide the full legal notes. Retrieve the current chapter or section PDF/text from USITC when GRI 1 depends on notes:
Use Justia, law firm alerts, or general search only as fallback or orientation. Do not attribute holdings or quote court reasoning without retrieved opinion text.
Workflow Router
Execute the workflow that matches the user's request. Keep scope disciplined: answer the requested trade-law question, do not add unrelated litigation or policy background.
Search broad, refine by heading, retrieve full ruling text for cited reasoning, distinguish HQ from NY, check revocation/modification status, flag conflicts and gaps.
3. CIT/CAFC Decision Analysis
Triggers: CIT, CAFC, Federal Circuit, court decision, slip opinion, case.
Methodology:references/cit-decision-analysis.md.
Output:templates/cit-decision-brief.md.
Identify decisions from official indexes, retrieve opinion text, map facts and holdings, check subsequent history, and position the decision within the authority hierarchy. Do not quote or summarize holdings from snippets alone.
4. Duty Compilation
Triggers: duty rate, landed cost, total duty, fees, MPF, HMF.
Confirm HTS subheading and origin, record current HTS revision, compile Column 1 General, Special, Column 2, Chapter 99, AD/CVD, MPF, HMF, and source freshness. If classification or origin is unknown, pause or route to the needed workflow.
Inspect HTS footnotes and additional duty fields, then verify current status with USTR, Federal Register, USITC, Commerce, or official proclamation/source pages. Check exclusions and effective/expiration dates.
Use Commerce/ITA, Federal Register, ACCESS where available, and official order/scope sources. Distinguish order scope, cash deposit rate, company rate, all-others rate, liquidation instructions, and final assessment. Flag scope ambiguity for attorney review.
Map all production countries and steps. Separate marking origin, preferential origin, TAA origin, and origin for trade remedies. Search CROSS and official program rules. Flag multi-country ambiguity.
Output: Use templates/compliance-review.md section 6 for full reviews, or inline screening for narrow questions.
Screen against official agency import pages and current PGA message set guidance where available. Flag potential requirements rather than clearing products when facts are incomplete.
Output: Use templates/compliance-review.md section 7 for full reviews, or inline screening for narrow questions.
Use CBP/UFLPA official sources, DHS Entity List materials, WRO sources, and current supply-chain facts. Treat unclear supplier identity or region links as a human-review trigger.
10. Full Compliance Review
Triggers: compliance, full review, comprehensive import review, risk review.
Produce a consolidated risk matrix and source/evidence appendix.
Roadmap Placeholders
For valuation, entry/post-entry, quota/TRQ, FTZ, or entry document review, provide high-level issue spotting only unless the relevant methodology exists. State the limitation, identify likely official sources, and recommend attorney/broker review.
Hard Stop Conditions
Pause and ask for facts, or state that no conclusion can be reached, when:
Product identity, composition, function, or condition as imported is unclear and controls classification.
Country of origin or manufacturing steps control duty, Chapter 99, AD/CVD, FTA, TAA, or UFLPA results.
Current HTS revision cannot be identified for a rate or GRI 6 conclusion.
Full text of a ruling/opinion is unavailable but the user asks for quoted reasoning or holding-level analysis.
AD/CVD order scope depends on technical specifications not provided.
A PGA/UFLPA admissibility conclusion would require supplier, facility, or product certifications not provided.
Output Discipline
Every deliverable must include:
Draft work product status.
Analysis date.
Evidence/freshness block.
Authority hierarchy treatment.
Human-review flags.
Source limitations.
Applicable disclaimer.
Do not overstate certainty. Use "draft recommended classification," "likely," "appears," or "requires verification" when evidence or facts are incomplete.
Data Freshness
Data Type
Freshness Rule
HTS rates and hierarchy
Resolve latest Data.gov JSON or live REST; record revision and analysis date
Section/Chapter notes
Retrieve current USITC chapter/section source before relying on notes
Chapter 99
Check HTS footnotes/additional duty fields plus current official status
CROSS
Search live and retrieve individual ruling pages for reasoning
CIT/CAFC
Retrieve official opinion text and check subsequent history when material
AD/CVD
Verify current order/scope and company/all-others rates in official sources
MPF/HMF
Verify current-year CBP/statutory source; do not hard-code
FTA/TAA/PGA/UFLPA
Verify current official program or agency source
Reference Files
File
Purpose
references/agentic-research-protocol.md
Evidence ledger, retrieval quality, freshness, and hallucination controls
Customs Trade Law Onur Kafkas next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Customs Trade Law Onur Kafkas compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Customs Trade Law Onur Kafkas this skilllawve-ai/awesome-legal-skills
This skill should be used when the user asks to "기술 의사결정", "뭐 쓸지 고민", "A vs B", "비교 분석", "라이브러리 선택", "아키텍처 결정", "어떤 걸 써야 할지", "트레이드오프", "기술 선택", "구현 방식 고민", or needs deep analysis for technical…
This skill should be used when the user asks about "technical decision", "what to use", "A vs B", "comparison analysis", "library selection", "architecture decision", "which one to use"…
Operates the `mqttx` command line client to connect, publish, subscribe, benchmark and simulate data against an MQTT broker, with TLS and MQTT 5 support.
Checklist of every backend, frontend, CLI and capture change needed to add a new TriggerCrud-based trigger type, such as Azure, GCP or Kafka, to Windmill.
U.S. An agent skill from lawve-ai/awesome-legal-skills. Customs Trade Law Onur Kafkas is an agent skill from lawve-ai/awesome-legal-skills.S.
When should I use Customs Trade Law Onur Kafkas?
Customs Trade Law Onur Kafkas fits situations like: product classification; tariff questions; customs rulings; trade remedy screening (Section 301/232/201).
How do I install Customs Trade Law Onur Kafkas in Claude Code?
Run `npx skills add lawve-ai/awesome-legal-skills --skill customs-trade-law-onur-kafkas -a claude-code`. Or copy the skill folder (skills/customs-trade-law-onur-kafkas in lawve-ai/awesome-legal-skills) into .claude/skills/customs-trade-law-onur-kafkas in your project. Claude Code loads it when a task matches its description.
How do I install Customs Trade Law Onur Kafkas in Codex?
Run `npx skills add lawve-ai/awesome-legal-skills --skill customs-trade-law-onur-kafkas -a codex`. Or copy the skill folder (skills/customs-trade-law-onur-kafkas in lawve-ai/awesome-legal-skills) into .agents/skills/customs-trade-law-onur-kafkas in your project. Codex loads it when a task matches its description.
Can I use Customs Trade Law Onur Kafkas in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lawve-ai/awesome-legal-skills --skill customs-trade-law-onur-kafkas -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/customs-trade-law-onur-kafkas, .gemini/skills/customs-trade-law-onur-kafkas, .github/skills/customs-trade-law-onur-kafkas and .opencode/skills/customs-trade-law-onur-kafkas in your project.
What does Customs Trade Law Onur Kafkas need to run?
SKILL.md names no scripts, command-line tools or credentials: Customs Trade Law Onur Kafkas is instructions for the agent only. Our summary lists: Python 3.
Does Customs Trade Law Onur Kafkas access the network?
SKILL.md names 3 domains. In commands or code: hts.usitc.gov, rulings.cbp.gov and cit.uscourts.gov; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is Customs Trade Law Onur Kafkas safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Customs Trade Law Onur Kafkas use?
Customs Trade Law Onur Kafkas is published under the AGPL-3.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Customs Trade Law Onur Kafkas use?
About 4.1k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 36k tokens, read only when the agent opens those files.
What are the alternatives to Customs Trade Law Onur Kafkas?
Skills that share tags, products or a category with Customs Trade Law Onur Kafkas: Tech Decision (team-attention/plugins-for-claude-natives, 827 stars), Tech Decision (team-attention/hoyeon, 173 stars), Stripe Projects (fossasia/eventyay, 1.7k stars) and MQTTX CLI (emqx/MQTTX, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Customs Trade Law Onur Kafkas?
lawve-ai (a GitHub organization) maintains it in lawve-ai/awesome-legal-skills, which has 847 GitHub stars. The repository holds 154 skills in this directory. The repository was last updated on October 2, 2026.
Source: lawve-ai/awesome-legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.