技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
linkfox-zhihuiya-patent-forward-citation【数据与研究】从智慧芽专利数据库查询专利的前向引用详情。当用户询问专利引用、被引用专利、引用文献、专利参考文献、前向引用、在先技术引用或想查看特定专利在申请过程中引用了哪些专利、非专利文献、patent cited references, forward citations, patent references, citation analysis, PatSnap时触发此技能。当用户提供专利ID或公开号并需要引用信息时,即使未明确说"前向引用",任何关于专利引用了哪些参考文献的请求都适用。
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
This skill guides you on how to query patent forward citation data from the Zhihuiya patent database, helping users discover the patents and non-patent literature cited by specific patents during their application process.
Forward citation refers to the patents and non-patent literature that a given patent has cited in its application documents. This is a fundamental aspect of patent analysis — understanding what prior art a patent references helps assess its novelty, scope, and technological lineage.
citedPatents): Other patents referenced by the queried patent.citedOthers): Academic papers, technical reports, and other non-patent documents referenced by the queried patent.You must provide at least one of the following two parameters. If both are provided, patentId takes priority.
| Parameter | Type | Required | Description |
|---|---|---|---|
| patentId | string | Conditionally | Patent ID(s). Multiple values separated by commas. Maximum 100 entries. |
| patentNumber | string | Conditionally | Publication/announcement number(s). Multiple values separated by commas. Maximum 100 entries. |
Rules:
patentId or patentNumber must be provided.patentId is used preferentially.| Field | Type | Description |
|---|---|---|
| total | integer | Total number of records returned |
| data | array | List of patent citation results |
| data[].patentId | string | Patent ID of the queried patent |
| data[].pn | string | Publication/announcement number |
| data[].citedPatents | array | List of cited patent documents |
| data[].citedOthers | array | List of cited non-patent literature |
| columns | array | Column definitions for rendering |
| costToken | integer | Tokens consumed by the query |
| type | string | Rendering style hint |
POST /zhihuiya/patentForwardCitation(完整参数/响应/错误码见 references/api.md)python scripts/zhihuiya_cited_references.py '<JSON 参数>' [--inline]输出策略(脚本默认行为):
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-zhihuiya-patent-forward-citation-<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)total/costToken、最大列表字段的长度 + 前 3 条样本)--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。
发生以下异常情况时,采用 references/onboarding.md 引导解决问题:
LINKFOX_AGENT_API_KEY,也未配置 LINKFOXAGENT_API_KEY。1. Query forward citations by publication number
Look up the forward citations for patent US10000000B2.
Parameters: {"patentNumber": "US10000000B2"}
2. Query forward citations for multiple patents
Find all citations for patents US10000000B2, US9876543B1, and EP3456789A1.
Parameters: {"patentNumber": "US10000000B2,US9876543B1,EP3456789A1"}
3. Query forward citations by patent ID
Retrieve the cited references for patent ID 12345678.
Parameters: {"patentId": "12345678"}
4. Query forward citations using both identifiers
Look up citations for patent ID 12345678 (publication number US10000000B2).
Parameters: {"patentId": "12345678", "patentNumber": "US10000000B2"} (patentId takes priority)
Applicable -- Patent citation queries:
| User Says | Scenario |
|---|---|
| "What patents does XX cite" | Forward citation lookup |
| "Show me the references for patent XX" | Citation detail retrieval |
| "What prior art is cited by XX" | Prior art reference query |
| "List the cited literature for XX" | Non-patent literature lookup |
| "Citation analysis for patent XX" | Combined patent + literature citation |
| "What documents does patent XX reference" | General citation query |
Not applicable -- Needs beyond forward citation data:
按动态规则计费:消耗算力 = 81 × 返回data条数。每条为 1 条专利引证文献结果
重要:本技能的服务按倍数动态计算,可能一次性消耗大量算力,必须提醒用户,由用户决定是否继续。
Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply:
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.