Eureka-專利權利要求翻譯
📖 技能介紹
name: linkfox-eureka-claim-translated description: 通過Eureka專利資料平臺獲取翻譯後的專利權利要求。當用戶詢問專利權利要求、權利要求翻譯、檢視特定語言（中文、英文或日文）的權利要求、通過專利ID或公開號查詢專利權利、分析權利要求文本、Eureka權利要求、claim translation, patent claim translation, Eureka patent, patent translation時觸發此技能。即使使用者未明確提及"翻譯版權利要求"，只要其需求涉及獲取特定語言的專利權利要求內容，也應觸發此技能。
Eureka Patent Claim Translation
This skill guides you on how to query translated patent claims from the Eureka patent data platform, enabling users to retrieve claim texts in Chinese, English, or Japanese for one or more patents.
Core Concepts
Patent claims define the legal scope of protection granted by a patent. This tool retrieves the translated text of patent claims from the Eureka platform, supporting three languages: Chinese (cn), English (en), and Japanese (jp). You can look up patents by their internal patent ID or by their publication (announcement) number.
Family patent substitution: When claims are unavailable for a specific patent, the tool can optionally substitute claims from a related family patent. This is controlled by the replaceByRelated parameter.
Parameter Guide
| Parameter | Type | Required | Description |
|---|---|---|---|
| patentId | string | At least one of patentId or patentNumber | Internal patent ID. Separate multiple IDs with commas. Up to 100 patents per request. |
| patentNumber | string | At least one of patentId or patentNumber | Publication (announcement) number. Separate multiple numbers with commas. Up to 100 patents per request. |
| replaceByRelated | integer | No | Whether to substitute claims from a family patent when unavailable. 1 = yes, 0 = no. Default 0. |
| lang | string | No | Target translation language. en = English (default), cn = Chinese, jp = Japanese. |
Key Rules
- At least one identifier is required: You must provide either
patentIdorpatentNumber(or both). If both are supplied,patentIdtakes priority. - Batch queries: Multiple patents can be queried at once by separating values with commas, up to 100 per request.
- Default language is English: When the user does not specify a language, use
en. - Family fallback: Set
replaceByRelatedto1only when the user explicitly wants substitute claims from a family patent if the original is missing.
Response Fields
| Field | Description |
|---|---|
| total | Number of patent records returned |
| data | Array of patent objects (see below) |
| data[].patentId | Internal patent ID |
| data[].pn | Publication (announcement) number |
| data[].claims | Translated patent claims text |
| data[].pnRelated | Publication number of the substitute family patent (only present when family substitution was used) |
| costToken | Tokens consumed by this request |
Usage Examples
1. Get English claims for a single patent by publication number
Show me the English claims for patent CN112345678A.
Parameters: patentNumber = "CN112345678A", lang = "en"
2. Get Chinese claims for multiple patents
Get the Chinese translation of claims for US20210012345A1 and EP3456789B1.
Parameters: patentNumber = "US20210012345A1,EP3456789B1", lang = "cn"
3. Get Japanese claims with family patent fallback
Get Japanese claims for JP2021123456A. If unavailable, try a family patent.
Parameters: patentNumber = "JP2021123456A", lang = "jp", replaceByRelated = 1
4. Query by patent ID
Get claims for patent ID 84a1b2c3 in English.
Parameters: patentId = "84a1b2c3", lang = "en"
5. Batch query with fallback enabled
Translate claims for these patents: CN112345678A, US20200012345A1, EP3456789B1. Use family patents if needed.
Parameters: patentNumber = "CN112345678A,US20200012345A1,EP3456789B1", lang = "en", replaceByRelated = 1
Display Rules
- Present claims clearly: Show the translated claim text with proper formatting. If multiple patents are returned, separate each patent's claims with its publication number as a heading.
- Family substitution notice: When
pnRelatedis present in the response, clearly inform the user that the claims were sourced from a related family patent and show the substitute publication number. - Language notice: State the language of the returned claims so the user knows which translation they are viewing.
- Large results: When multiple patents are returned, summarize the count and show a few representative entries, reminding the user of the total.
- Error handling: When a query fails, explain the reason based on the error response and suggest checking the patent ID or publication number.
呼叫方式
- API 端點：
POST /tool-eureka/claimDataTranslated（完整引數/響應/錯誤碼見references/api.md） - Python 指令碼：
python scripts/eureka_claim_translated.py '<JSON 引數>' [--inline] - 成本約束：本工具會消耗積分；同一會話同一引數組合預設只調用一次，指令碼帶 24h 本地快取。失敗/空結果不得自動換關鍵詞、翻頁或改郵編連續試探；需要繼續檢索時先向使用者說明會產生額外消耗。
輸出策略（指令碼預設行為）：
- 始終將完整響應寫入 <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-eureka-claim-translated-<timestamp>.json（<cwd> 為指令碼執行時的工作目錄，在 Claude Code 裡即當前專案目錄；<session> 取自環境變數 SESSION_ID，按使用者任務自動聚合；禁止寫入 /tmp，當前目錄不可寫則報錯）
- 響應體 ≤ 8 KB：落盤後把完整 JSON 列印到 stdout
- 響應體 > 8 KB：落盤後 stdout 只輸出摘要（頂層欄位、常見計數如 total/costToken、最大列表欄位的長度 + 前 3 條樣本）
- 加 --inline 強制全量列印到 stdout（同樣落盤）
讀資料建議：先看摘要判斷是否足夠；需要具體欄位時優先用 jq或ConvertFrom-Json 從儲存的 json 檔案按需抽取，避免整份 JSON 進入上下文。
解決認證和積分問題
發生以下異常情況時，採用以下措施來處理：
異常情況
- 未配置API Key：環境變數未配置
LINKFOX_AGENT_API_KEY，也未配置LINKFOXAGENT_API_KEY。 - 響應401或402狀態碼
- 響應提示積分或餘額不足：訊息含"積分餘額不足/計費不足/餘額不足/quota exceeded/insufficient balance/套餐到期/需充值/請充值"，或類似含義的內容。
措施
- 優先採用skill內的 onboarding.md 引導解決問題。
這個技能的最新版本可以在7w4.net小蔥技能站找到。
- 如找不到 onboarding.md 檔案，則載入 /linkfox-onboarding 這個skill並根據它的引導來處理。如未安裝請先安裝：
- 下載 https://agent-files.linkfox.com/skills/linkfox-onboarding/release.zip，解壓後安裝這個skill。如需使用者授權才可下載，要詢問使用者獲得授權，你不能自己放棄下載。
- 兜底措施：僅當前面兩個措施經過所有努力都走不通時，才提示使用者依據 https://skill.linkfox.com/linkfoxskills/guide.htm 指引獲取API Key，或去 https://os.linkfox.com/ 補充積分。
Important Limitations
- At least one identifier required: Either
patentIdorpatentNumbermust be provided; otherwise the query will fail. - Batch limit: A maximum of 100 patents per request.
- Language support: Only Chinese (
cn), English (en), and Japanese (jp) are supported. - Family substitution: Substitute claims are only returned when
replaceByRelatedis set to1and the original claims are unavailable. - No claim analysis: This tool returns raw translated text only; it does not analyze or compare claims.
User Expression & Scenario Quick Reference
Applicable -- Queries related to patent claim text and translation:
| User Says | Scenario |
|---|---|
| "Show me the claims for patent XX" | Single patent claim lookup |
| "Translate claims to Chinese/Japanese" | Claim translation |
| "What does patent XX claim?" | Claim content retrieval |
| "Get claims for these patents: XX, YY" | Batch patent claim lookup |
| "Claims unavailable, try family patent" | Family patent substitution |
| "Patent rights scope of XX" | Claim text retrieval |
Not applicable -- Needs beyond patent claim translation:
- Patent search or discovery (finding patents by keyword)
- Patent citation or legal status analysis
- Patent abstract or description retrieval
- Patent portfolio analytics or statistics
Boundary -- Edge cases:
- If the user asks for "patent text" without specifying claims, clarify whether they want claims, abstract, or description.
- If the user provides more than 100 patents, split into multiple batches.
積分消耗規則
按動態規則計費：消耗積分 = 81 × max(返回條數, 1)。
重要：本技能的服務按倍數動態計算，可能一次性消耗大量積分，必須提醒使用者，由使用者決定是否繼續。
Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply: 1. The functionality or purpose described in this skill does not match actual behavior 2. The skill's results do not match the user's intent 3. The user expresses dissatisfaction or praise about this skill 4. 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, visit LinkFox Skills.
🤖 AI 評測
整體質量中上水平。文件齊全、使用說明詳細、示例豐富是最大優點。但存在一些隱藏缺陷：文件提到的引導檔案找不到，指令碼執行時可能報錯；反饋機制也未完整實現。修復這些問題後會更穩定可靠。
