← 返回 Skills 市场
linkfox-ai

Eureka Bibliography

作者 linkfox-ai · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
61
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install linkfox-eureka-bibliography
功能描述
从Eureka专利数据库查询专利著录项目(Bibliography)信息,包括标题、摘要、申请人、发明人、分类号、优先权、引用文献等。当用户提到专利著录项目、专利基本信息、专利标题摘要、专利申请人发明人、专利分类号、IPC分类、CPC分类、专利代理、审查员、优先权、引用文献、关联文件、预估到期日、patent b...
使用说明 (SKILL.md)

Eureka Patent Bibliography

This skill guides you on how to retrieve patent bibliography (bibliographic) information via the Eureka patent platform, helping users quickly obtain structured metadata for one or more patents — including titles, abstracts, applicants, inventors, classifications, priority claims, cited references, and more.

Core Concepts

The Eureka Bibliography tool returns comprehensive bibliographic data for each patent, organized into several categories:

  1. Identification — Patent ID (patentId) and publication number (pn).
  2. Title & Abstract — Multi-language invention titles (inventionTitle) and abstracts (abstracts).
  3. Patent Type — One of APPLICATION, PATENT, UTILITY, or DESIGN.
  4. Parties — Original applicants (applicants), current assignees (assignees), inventors (inventors), patent agents (agents), filing agency (agency), and examiners (examiners).
  5. Dates & References — Application reference, publication reference, dates of public availability, and estimated expiry date (exdt).
  6. Classifications — IPC-R (classificationIpcr), CPC (classificationCpc), UPC (classificationUpc), GBC (classificationGbc), Locarno (classificationLoc), FI (classificationFi), F-term (classificationFterm).
  7. Citations & Related Documents — Cited patents (referenceCitedPatents), cited non-patent literature (referenceCitedOthers), and related documents such as divisionals/continuations (relatedDocuments).
  8. PCT Data — PCT or regional filing data and publishing data.

Patent identification: Patents can be looked up by either patent ID or publication number. When both are provided, patent ID takes priority. Multiple values can be submitted in a single request (comma-separated, up to 100).

Parameter Guide

Parameter Required Description
patentId Conditionally Patent ID. At least one of patentId or patentNumber must be provided. Comma-separated for multiple values, up to 100.
patentNumber Conditionally Publication (announcement) number. At least one of patentId or patentNumber must be provided. Comma-separated for multiple values, up to 100.
  • If the user provides a publication number (e.g., CN115000000A, US11000000B2, EP3000000A1), use patentNumber.
  • If the user provides an internal patent ID, use patentId.
  • When both are supplied, patentId takes precedence.

Response Fields

Field Description
patentId The patent's internal ID
pn Publication (announcement) number
inventionTitle Array of patent titles with language information
abstracts Array of patent abstracts with language information
patentType Patent type: APPLICATION, PATENT, UTILITY, or DESIGN
applicants Array of original applicants
assignees Array of current assignees (rights holders)
inventors Array of inventors
agents Array of patent agents
agency Array of filing agencies
examiners Array of patent examiners
priorityClaims Array of priority claims
applicationReference Application filing information (object)
publicationReference Publication information (object)
datesOfPublicAvailability Dates when the patent became publicly available (object)
classificationIpcr IPC-R classification (object)
classificationCpc CPC classification (object)
classificationUpc UPC classification (object)
classificationGbc GBC classification (object)
classificationLoc Locarno classification (array)
classificationFi FI classification (array)
classificationFterm F-term classification (array)
referenceCitedPatents Array of cited patent references
referenceCitedOthers Array of cited non-patent literature
relatedDocuments Array of related documents (divisional, continuation, etc.)
pctOrRegionalFilingData PCT or regional filing data (object)
pctOrRegionalPublishingData PCT or regional publishing data (object)
exdt Estimated expiry date (integer timestamp)
total Total number of records returned
costToken Token cost for this query

Usage Examples

1. Retrieve basic info for a single patent

Show me the bibliography for patent CN115000000A.

2. Get applicants and inventors for a patent

Who are the applicants and inventors of US11000000B2?

3. Batch-query bibliographic data for multiple patents

Get the titles, abstracts, and classification for patents EP3000000A1, CN115000001A, and JP2022000001A.

4. Check priority claims and related documents

What are the priority claims and related documents for patent US11000000B2?

5. Look up patent expiry date

When does patent CN115000000A expire?

6. Retrieve patent agent and examiner information

Who is the patent agent and examiner for CN115000000A?

Display Rules

  1. Present data clearly: Show results in a well-structured format. For single patents, use labeled sections. For multiple patents, use a summary table with key fields and expand details as needed.
  2. Title and abstract: Display the title and abstract in the language most relevant to the user. If multiple languages are available, show the user's preferred language first, with the original language in parentheses if different.
  3. Classification codes: Format IPC/CPC/UPC codes clearly. When the user is looking at technology domains, provide the top-level description when possible.
  4. Dates: Convert integer timestamps to human-readable date formats (YYYY-MM-DD).
  5. Error handling: If the query fails or returns no results, explain the possible reasons (invalid patent number format, patent not found in database) and suggest the user double-check the input.
  6. Volume notice: When querying many patents, present a summary table and note the total count returned.

Important Limitations

  • Up to 100 patents per request: The maximum number of patent IDs or publication numbers in a single call is 100.
  • At least one identifier required: Either patentId or patentNumber must be provided; the request will fail if both are empty.
  • Patent ID priority: When both patentId and patentNumber are provided, the system uses patentId and ignores patentNumber.
  • Data coverage: Results depend on the Eureka patent database coverage; some very recent filings may not yet be reflected.

User Expression & Scenario Quick Reference

Applicable — Queries about patent bibliographic/metadata information:

User Says Scenario
"Show me the basic info for patent XX" Full bibliography retrieval
"Who are the applicants/inventors of XX" Party information lookup
"What classifications does patent XX have" Classification query
"Get the title and abstract for these patents" Batch title/abstract query
"When does this patent expire" Expiry date check
"What patents does XX cite" Cited references query
"Is this a utility or design patent" Patent type check
"Show the priority claims for XX" Priority information lookup

Not applicable — Needs beyond patent bibliography:

  • Patent legal status queries (use the legal-status skill)
  • Patent full-text claims or description retrieval
  • Patent search by keyword or classification
  • Patent image/drawing search
  • Patent family analysis
  • Freedom-to-operate (FTO) analysis

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.

安全使用建议
This skill legitimately calls a remote Eureka bibliography API and requires an API key (LINKFOXAGENT_API_KEY) to work, but the skill manifest did not declare that requirement. Before installing: 1) Confirm you trust the endpoints (tool-gateway.linkfox.com and skill-api.linkfox.com) and the publisher. 2) Ask the publisher to update the skill metadata to declare the required env var (so you know an API key will be used). 3) If you proceed, create a scoped/limited API key for this use and avoid reusing highly privileged credentials. 4) Review the feedback endpoint behavior if you care about telemetry (it posts to a separate skill-api.linkfox.com). If the publisher cannot justify the missing metadata or the endpoints look unfamiliar, treat the skill as higher-risk and do not provide sensitive credentials.
功能分析
Type: OpenClaw Skill Name: linkfox-eureka-bibliography Version: 1.0.0 The skill bundle is designed to query patent bibliographic information from the Eureka database. The Python script (eureka_bibliography.py) implements standard API interaction using the urllib library, and the instructions in SKILL.md are consistent with the stated purpose of retrieving and formatting patent metadata without any signs of malicious intent or unauthorized data access.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The skill's name/description (Eureka bibliographic queries) matches the included API docs and the Python client which POSTs to https://tool-gateway.linkfox.com/eureka/bibliography. Requiring an Authorization API key for that endpoint is reasonable for this purpose.
Instruction Scope
SKILL.md and references/api.md instruct calls to the Eureka API and a separate feedback endpoint; the runtime script and docs expect an environment variable LINKFOXAGENT_API_KEY for Authorization. The metadata published with the skill, however, lists no required env vars — so the instructions access a secret (API key) that the manifest does not declare.
Install Mechanism
No install spec (instruction-only plus a small helper script). No downloads, extracted archives, or third-party package installs were found.
Credentials
The code requires a single API key (LINKFOXAGENT_API_KEY) to call the remote API; that credential is appropriate for the skill’s network calls but it is not declared in the skill metadata (no primaryEnv / requires.env). The missing declaration is a proportionality/visibility problem — the skill asks for a secret at runtime but the manifest doesn't tell users.
Persistence & Privilege
The skill is not always-enabled, does not request elevated persistence, and does not modify other skills or system-wide settings. Autonomous invocation is allowed (default) but this is normal for skills.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install linkfox-eureka-bibliography
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /linkfox-eureka-bibliography 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
Slug linkfox-eureka-bibliography
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Eureka Bibliography 是什么?

从Eureka专利数据库查询专利著录项目(Bibliography)信息,包括标题、摘要、申请人、发明人、分类号、优先权、引用文献等。当用户提到专利著录项目、专利基本信息、专利标题摘要、专利申请人发明人、专利分类号、IPC分类、CPC分类、专利代理、审查员、优先权、引用文献、关联文件、预估到期日、patent b... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 61 次。

如何安装 Eureka Bibliography?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install linkfox-eureka-bibliography」即可一键安装,无需额外配置。

Eureka Bibliography 是免费的吗?

是的,Eureka Bibliography 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Eureka Bibliography 支持哪些平台?

Eureka Bibliography 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Eureka Bibliography?

由 linkfox-ai(@linkfox-ai)开发并维护,当前版本 v1.0.0。

💬 留言讨论