本文へ移動
cccskills
無料GitHub で公開

ecommerce.patent-description-data-translation

Retrieve translated patent description (specification) text from Nexscope. Triggered when users request patent specification translation, patent full text in other languages, translated patent full text, or want to view patent specifications in Chinese, English, or Japanese, patent specification translation, patent description translation, Nexscope, or patent translation. Also triggered when users provide a patent ID or publication number and request specification/description content in another language, or mention "patent specification translation," "description translation," "translated full text," or similar intent.

インストール方法を見る

含まれるファイル(4)

  • SKILL.md7.2 KB
  • manifest.json333 B
  • references/api.md4.7 KB
  • scripts/patent_description_data_translation.py1.7 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Nexscope Patent Description (Translated)

This skill guides you on how to retrieve translated patent description (specification) text via the Nexscope data service. It supports translation into Chinese, English, or Japanese, and can look up patents by patent ID or publication number.

Core Concepts

A patent description (also called "specification") is the full technical text of a patent document. This tool fetches the translated version of that text from the Nexscope patent database, supporting three target languages: Chinese (cn), English (en), and Japanese (jp).

When a patent's description is unavailable, the tool can optionally substitute it with a description from a patent family member (a related patent filed in another jurisdiction covering the same invention).

Parameters

ParameterTypeRequiredDescription
patentIdstringConditionallyPatent ID. At least one of patentId or patentNumber must be provided. If both are given, patentId takes priority. This Skill sends one patent ID per call; the gateway accepts up to 100 comma-separated IDs.
patentNumberstringConditionallyPublication (announcement) number. At least one of patentId or patentNumber must be provided. This Skill sends one publication number per call; the gateway accepts up to 100 comma-separated numbers.
langstringNoTarget translation language. Supported values: en (English, default), cn (Chinese), jp (Japanese).
replaceByRelatedintegerNoWhether to substitute with a patent family member's description when the original is unavailable. 1 = yes, 0 = no (default).

Key Rules

  1. At least one identifier required: Either patentId or patentNumber must be provided. If the user gives a publication number like "US10123456B2", use patentNumber. If they give a numeric patent ID, use patentId.
  2. Priority: When both identifiers are supplied, patentId takes precedence.
  3. Single patent per request: This Skill sends one patent per call to control credits. For multiple patents, obtain explicit consent before separate calls; the gateway accepts up to 100 per request.
  4. Default language: If the user does not specify a language, default to en (English).

Skill single-patent policy: This endpoint consumes credits. If you need to check multiple patents, you must obtain explicit user consent and make separate requests. This Skill uses one patent per call; the gateway supports up to 100 English comma-separated identifiers.

Invocation

  • API Endpoint: POST /zhihuiya/descriptionDataTranslated (full parameters/response/error codes in references/api.md)
  • Python Script: python scripts/patent_description_data_translation.py '<JSON params>' [--inline]
  • Cost Constraints: This tool consumes credits. The same parameter combination defaults to a single call per session. The script includes a 24-hour local cache. Do not automatically retry with different keywords, pagination, or modified parameters on failure or empty results; inform the user that additional costs will be incurred before continuing to search. Skill single-patent policy: This endpoint consumes credits. This Skill uses one patent per call to control credits. For multiple patents, obtain explicit user consent before separate calls; the gateway supports up to 100 per request.

Output Strategy (default script behavior):

  • Always write the full response to <cwd>/nexscope/<YYYY-MM-DD>/<session>/data/nexscope-zhihuiya-description-data-translated-<timestamp>.json (<cwd> is the working directory at script execution time, which in Claude Code is the current project directory; <session> is taken from the SESSION_ID environment variable, auto-grouped by user task; writing to /tmp is forbidden -- error if the current directory is not writable)
  • Response body <= 8 KB: print the full JSON to stdout after writing to disk
  • Response body > 8 KB: print only a summary to stdout after writing to disk (top-level fields, common counts like total/costToken, length of the largest list field + first 3 samples)
  • Add --inline to force full output to stdout (still writes to disk)

Data Reading Tip: Check the summary first to determine if it is sufficient; when specific fields are needed, prefer using jq or ConvertFrom-Json to extract from the saved JSON file on demand to avoid loading the entire JSON into context.

Authentication

Set NEXSCOPE_API_KEY. Visit https://www.nexscope.ai/help/skills-external-access?co-from=skillNS to manage credits.

Usage Examples

1. Get English translation of a patent description by publication number

patentNumber: "US10123456B2"
lang: "en"

2. Get Chinese translation of a patent description by patent ID

patentId: "abc123def"
lang: "cn"

3. Japanese translation of a specific patent

patentNumber: "JP2021012345A"
lang: "jp"

Display Rules

  1. Present the translated text clearly: Show the patent description text directly. For long descriptions, present a summary or the first section and inform the user the full text is available.
  2. Identify substitutions: When pnRelated is present in the response, clearly inform the user that the description was sourced from a family member patent and show the related publication number.
  3. Single patent results: Results contain a single patent's data per call.
  4. Error handling: When a query fails, explain the reason based on the response and suggest checking the patent ID or publication number for correctness.
  5. No fabrication: Never invent or paraphrase patent text. Only display what the API returns.

User Expression & Scenario Quick Reference

Applicable -- Patent description/specification translation queries:

User SaysScenario
"Translate this patent description to English"Single patent translation
"I need the Chinese version of patent US10123456"Specific language translation
"What does patent CN112345678A describe?"Patent description lookup
"Show me the Japanese translation of this patent's full text"Japanese translation
"The description is missing, can you try a family member?"Family member fallback

Not applicable -- Needs beyond patent description translation:

  • Patent search or discovery (finding patents by keyword/topic)
  • Patent claim analysis or claim chart generation
  • Patent legal status or prosecution history
  • Patent citation or reference analysis
  • Patent portfolio analytics or statistics

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Query 1688 product bestseller billboard data for sourcing discovery and wholesale product research. Trigger when the user mentions 1688 product rankings, 1688 bestseller lists, wholesale hot products, domestic sourcing rankings, dropshipping product selection, 1688 trending products, bulk purchase popular items, supplier product rankings, 1688 billboard, 1688 bestsellers, sourcing rankings, wholesale hot products, trending product rankings, supplier rankings, 1688 trends. Even if the user does not explicitly mention "1688 billboard", if their need involves discovering hot-selling wholesale products or sourcing opportunities on the 1688 platform, this skill should also be triggered.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Query 1688 public product details through the Nexscope research proxy. Use when the user requests this public marketplace or patent data; do not use for seller-console or store-authorized operations.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Search and analyze products on the Chinese 1688 wholesale platform (Alibaba domestic B2B market) for sourcing, supplier discovery, and product selection. Trigger when the user mentions 1688 product search, finding suppliers on 1688, wholesale product queries, factory sourcing, dropshipping supplier search, 1688 keyword product selection, wholesale price comparison, filtering by sales volume, any product research on the 1688 platform, 1688 search, 1688 product selection, find suppliers, factory lookup, wholesale pricing, supplier search, domestic sourcing, 1688 products. Even if the user does not explicitly say "1688", if their need involves searching for wholesale products, finding domestic suppliers, or sourcing from the domestic Chinese market, this skill should also be triggered.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Perform image-based product search on the 1688 platform. Use an image URL to find visually similar supplier products, returning title, price, minimum order quantity, monthly sales, repurchase rate, trade score, and seller identity. Triggered when users mention 1688 image search, 1688 visual search, find supplier by image, reverse image search 1688, 1688 product sourcing by image, or Alibaba 1688 image search. Even if the user does not explicitly mention "image search," this skill should be triggered whenever a user provides an image URL and wants to find matching or similar products on the 1688 wholesale platform.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Authorize Amazon Ads accounts and inspect safe connection and profile metadata.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Read and mutate SP, SB, and SD campaigns, ad groups, ads, targeting, and budget rules.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

nexscope-ai のスキルをすべて見る

このスキルの問題を報告する