使い方
- インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
- 必要なツール、認証情報、対応環境を原文で確認します。
- 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/linkfox-ai/linkfox-skills --skill linkfox-ruiguan-text-trademark-detection開始前の確認
- 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
- スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。
Ruiguan Text Trademark Detection
This skill guides you on how to perform text-based trademark detection against product titles and other product text, helping e-commerce sellers identify potential trademark infringement risks before publishing listings.
Core Concepts
Text Trademark Detection scans product text (titles, descriptions, bullet points) against registered trademark databases across 15 countries/regions. It returns matched trademarks along with risk scores, registration details, and holder information so sellers can avoid intellectual property violations.
Risk score logic: The highestModeScore field ranges from 0 to 5 -- a higher value indicates greater infringement risk. The textTrademarkRadar field classifies overall product risk into three levels: 0 (low risk), 1 (needs manual review), 2 (high risk).
Blacklist and whitelist: The response may include blacklistTrademarks (known dangerous trademarks to always avoid) and whitelistTrademarks (safe trademarks that can be ignored). Always surface blacklist matches prominently to the user.
Parameters
| Parameter | Type | Required | Description | Example |
|---|---|---|---|---|
| productTitle | string | Yes | Product title to scan (max 1000 chars) | Wireless Bluetooth Headphones Noise Cancelling |
| regions | string | No | Country/region codes, comma-separated. Supported: US, EM, GB, DE, FR, IT, ES, AU, CA, MX, JP, CN, WO, TR, BX | US,EM,GB |
| limit | integer | Yes | Max number of results to return (default 100, max 500) | 100 |
| productText | string | No | Additional product text such as bullet points, description (max 1000 chars) | Ergonomic design with premium sound quality |
Supported Regions
| Code | Region |
|---|---|
| US | United States |
| EM | European Union |
| GB | United Kingdom |
| DE | Germany |
| FR | France |
| IT | Italy |
| ES | Spain |
| AU | Australia |
| CA | Canada |
| MX | Mexico |
| JP | Japan |
| CN | China |
| WO | WIPO (World Intellectual Property Organization) |
| TR | Turkey |
| BX | Bolivia |
When the user does not specify a region, default to US.
调用方式
- API 端点：
POST /ruiguan/textTrademarkDetection（完整参数/响应/错误码见references/api.md） - Python 脚本：
python scripts/ruiguan_text_trademark_detection.py '<JSON 参数>' [--inline] - 成本约束：本工具会消耗算力；同一会话同一参数组合默认只调用一次，脚本带 24h 本地缓存。失败/空结果不得自动换关键词、翻页或改邮编连续试探；需要继续检索时先向用户说明会产生额外消耗。
输出策略（脚本默认行为）：
- 始终将完整响应写入
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-ruiguan-text-trademark-detection-<timestamp>.json（<cwd>为脚本执行时的工作目录，在 Claude Code 里即当前项目目录；<session>取自环境变量SESSION_ID，按用户任务自动聚合；禁止写入 /tmp，当前目录不可写则报错） - 响应体 ≤ 8 KB：落盘后把完整 JSON 打印到 stdout
- 响应体 > 8 KB：落盘后 stdout 只输出摘要（顶层字段、常见计数如
total/costToken、最大列表字段的长度 + 前 3 条样本） - 加
--inline强制全量打印到 stdout（同样落盘）
读数据建议：先看摘要判断是否足够；需要具体字段时优先用 jq或ConvertFrom-Json 从保存的 json 文件按需抽取，避免整份 JSON 进入上下文。
解决认证和算力问题
发生以下异常情况时，采用 references/onboarding.md 引导解决问题：
异常情况
- 未配置API Key：环境变量未配置
LINKFOX_AGENT_API_KEY，也未配置LINKFOXAGENT_API_KEY。 - 响应401或402状态码
- 响应提示算力或余额不足：消息含"算力余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值"，或类似含义的内容。
How to Build Requests
Principles
- Include the full product title: Always pass the complete product title in
productTitle-- partial text may miss trademark matches. - Choose target regions: Select regions matching the marketplaces where the product will be sold. Use comma-separated codes for multi-region checks.
- Provide additional text when available: If the user has bullet points, descriptions, or backend keywords, include them in
productTextfor a more thorough scan. - Set an appropriate limit: Use the default of 100 for standard checks. Increase up to 500 when scanning titles with many potential matches.
Usage Examples
1. Basic US Trademark Check for a Product Title
productTitle: "Wireless Bluetooth Headphones Noise Cancelling Over Ear"
regions: "US"
limit: 1002. Multi-Region Check (US + EU + UK)
productTitle: "Portable USB-C Charger Fast Charging Power Bank"
regions: "US,EM,GB"
limit: 1003. Full Listing Scan with Additional Text
productTitle: "Stainless Steel Vacuum Insulated Water Bottle"
productText: "BPA-free, double-wall insulation, keeps drinks cold 24 hours, fits standard cup holders"
regions: "US,JP"
limit: 2004. Broad Global Check
productTitle: "LED Ring Light with Tripod Stand for Streaming"
regions: "US,EM,GB,DE,FR,IT,ES,AU,CA,MX,JP,CN"
limit: 5005. China Domestic Market Check
productTitle: "智能蓝牙耳机降噪头戴式"
regions: "CN"
limit: 100Display Rules
- Risk-first presentation: Always highlight the overall risk level (
textTrademarkRadar) at the top of results. Use clear language: "Low Risk", "Needs Manual Review", or "High Risk". - Blacklist prominence: If
blacklistTrademarksis non-empty, display them first with a clear warning. - Table format: Present trademark matches in a table with columns: Trademark Name, Region, Risk Score, Status, Holder, Application Number, Famous, Amazon Brand, Active Holder.
- Score explanation: Remind users that
highestModeScoreranges from 0 (safe) to 5 (highest risk). - Whitelist reassurance: If
whitelistTrademarkscontains entries, note them as safe/exempted trademarks. - Error handling: When a request fails, explain the issue and suggest the user check their product title or adjust regions.
- No legal advice: Always remind users that results are for reference only and do not constitute legal advice. Recommend consulting an IP attorney for definitive trademark clearance.
Important Limitations
- Text-only detection: This tool detects trademarks in text. It does not analyze logos, images, or design marks.
- Result cap: Maximum 500 results per request.
- Character limit: Both
productTitleandproductTextare limited to 1000 characters each. - Database coverage: Covers 15 countries/regions. Trademarks registered in other jurisdictions may not be detected.
User Expression & Scenario Quick Reference
Applicable -- Trademark risk analysis for product text:
| User Says | Scenario |
|---|---|
| "Check my title for trademark issues" | Basic trademark scan |
| "Is this product name safe to use" | Infringement risk check |
| "Scan my listing for brand violations" | Full listing scan |
| "Any trademark risks in this title" | Risk assessment |
| "Check trademarks in US and EU" | Multi-region check |
| "Is XX a registered trademark" | Specific term lookup |
| "Will my listing get taken down for IP" | Compliance screening |
| "Check if this keyword infringes any brand" | Keyword safety check |
Not applicable -- Needs beyond text trademark detection:
- Logo or image-based trademark analysis
- Patent infringement checks
- Copyright detection
- Legal opinions or litigation strategy
- Trademark registration or filing assistance
算力消耗规则
消耗 31 算力。
重要：本技能消耗大量算力，如果调用次数超过5次，必须用AskUserQuestion 和用户进行二次确认，要明确告知用户已消耗算力和继续调用的话预计消耗的算力，让用户自行决定是否继续。Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply:
- The functionality or purpose described in this skill does not match actual behavior
- The skill's results do not match the user's intent
- The user expresses dissatisfaction or praise about this skill
- Anything you believe could be improved
Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.
For more high-quality, professional cross-border e-commerce skills, set [LinkFox Skills](https://skill.linkfox.com/).
