This skill guides you on how to retrieve translated patent titles and abstracts from the Eureka patent data platform, supporting Chinese, English, and Japanese translations.
Core Concepts
Eureka is a professional patent data platform. This tool queries its database to return translated titles and abstracts for one or more patents. You can look up patents by patent ID or publication (announcement) number, and receive translations in Chinese, English, or Japanese.
Patent identification: Each patent can be identified by either a patentId (internal identifier) or a patentNumber (public publication/announcement number such as US20200012345A1 or CN112345678A). If both are provided, the patent ID takes priority.
Family patent fallback: When the original patent has no abstract available, you can optionally substitute the abstract from a related family patent by setting replaceByRelated to 1.
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 a family patent abstract when the original is 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 a substitute abstract 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[].title | Translated patent title |
| data[].abstractText | Translated patent abstract |
| data[].pnRelated | Publication number of the substitute family patent (only present when family replacement was used) |
| costToken | Tokens consumed by this request |
Usage Examples
1. Translate a single patent abstract to English by publication number
Look up patent number US20200012345A1 and give me the English abstract.
Parameters: patentNumber = "US20200012345A1", lang = "en"
2. Translate multiple patents to Chinese
Get the Chinese translation of abstracts for patents CN112345678A and US20200067890A1.
Parameters: patentNumber = "CN112345678A,US20200067890A1", lang = "cn"
3. Look up by patent ID with family fallback
Get the Japanese abstract for patent ID 12345678. If the abstract is unavailable, use a family patent instead.
Parameters: patentId = "12345678", lang = "jp", replaceByRelated = 1
4. Batch query by patent IDs
Translate the titles and abstracts for these patent IDs: 111111, 222222, 333333.
Parameters: patentId = "111111,222222,333333", lang = "en"
5. Translate to Chinese with family patent fallback enabled
查询专利CN112345678A的中文摘要，如果没有就用同族专利替代。
Parameters: patentNumber = "CN112345678A", lang = "cn", replaceByRelated = 1
Display Rules
- Present data clearly: Show results in a well-structured table with patent number, title, and abstract.
- Indicate language: Mention the translation language in the output header so users know which language the results are in.
- Family patent notice: If
pnRelatedis present in any result, explicitly inform the user that the abstract was sourced from a family patent and show the substitute publication number. - Long abstracts: For very long abstracts, display the full text without truncation so users can review the complete content.
- Error handling: When a query fails or returns no results, explain the likely cause (e.g., invalid patent number, patent not found in database) and suggest corrections.
How to Call
- API Endpoint：
POST /tool-eureka/abstractDataTranslated(For full parameters/responses/error codes, seereferences/api.md） - Python Script：
python scripts/eureka_abstract_translated.py '<JSON 参数>' [--inline] - Cost Constraints: This tool consumes credits; by default, the same parameter combination in the same session is called only once, and the script has a 24h local cache. On failure/empty results, do not automatically switch keywords, page through, or change the postal code to probe repeatedly; if further retrieval is needed, first explain to the user that it will incur additional consumption.
Output Strategy (Script Default Behavior)：
- Alwayswrite the full response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-eureka-abstract-translated-<timestamp>.json（<cwd>is the working directory when the script is executed, which in Claude Code is the current project directory;<session>is taken from the environment variableSESSION_ID, automatically aggregated according to the user's task;Writing to /tmp is prohibited, and if the current directory is not writable, report an error) - Response body ≤ 8 KB: after writing to disk, print the complete JSON to stdout
- Response body > 8 KB: after writing to disk, stdout outputs only a summary (top-level fields, common counts such as
total/costToken, length of the largest list field + first 3 samples) - Add
--inlineto force full printing to stdout (also written to disk)
Data Reading Suggestions: First look at the summary to determine whether it is sufficient; when specific fields are needed, prefer to use jqorConvertFrom-Json to extract on demand from the saved json file, avoiding bringing the entire JSON into the context.
Resolving Authentication and Credit Issues
When the following abnormal situations occur, take the following measures to handle them:
Abnormal Situation
- API Key not configured: The environment variable is not configured with
LINKFOX_AGENT_API_KEY, andLINKFOXAGENT_API_KEY。 - Response 401 or 402 status code
- Response indicates insufficient credits or balance: The message contains "insufficient credit balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge", or content with a similar meaning.
Measures
- Prefer to use the onboarding.md within the skill to guide problem resolution.
- If the onboarding.md file cannot be found, load the /linkfox-onboarding skill and handle it according to its guidance. If not installed, please install it first:
- Fallback measure: only when all efforts with the previous two measures have failed, prompt the user to follow the https://skill.linkfox.com/linkfoxskills/guide.htm guidance to obtain an API Key, or go to https://os.linkfox.com/ to add credits.
Important Limitations
- Identifier required: At least one of patent ID or publication number must be provided; the tool cannot perform keyword-based searches.
- Translation languages: Only Chinese (
cn), English (en), and Japanese (jp) are supported. - No full-text retrieval: This tool returns only titles and abstracts, not full patent claims or descriptions.
- Family replacement is optional: The substitute family patent abstract is only provided when explicitly requested via
replaceByRelated = 1. - Batch limit: A maximum of 100 patents per request.
User Expression & Scenario Quick Reference
Applicable -- Patent abstract and title translation queries:
| User Says | Scenario |
|---|---|
| "Translate this patent abstract" | Single patent translation |
| "What does patent XX say / what is it about" | Abstract lookup |
| "Get the Chinese/Japanese version of this patent" | Specific language translation |
| "Look up the abstract for patent number XX" | Publication number lookup |
| "Translate these patents in batch" | Batch translation |
| "The abstract is missing, try a family patent" | Family patent fallback |
Not applicable -- Needs beyond abstract translation:
- Full patent text, claims, or description retrieval
- Patent search by keyword, classification, or applicant
- Patent legal status, citation analysis, or landscape reports
- Patent valuation or infringement analysis
Boundary -- Edge cases:
- If the user asks for "patent content" without specifying which part, default to abstract translation and inform them about claim/description tools.
- If the user provides more than 100 patents, split into multiple batches.
Credit Consumption Rules
Billed according to dynamic rules: credits consumed = 81 × max(number of returned records, 1).
Important: The service of this skill is calculated dynamically by a multiplier, and may consume a large number of credits at once. The user must be reminded, and the user decides whether to continue.
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, visit LinkFox Skills.