Zhihuiya Patent Simple Bibliography

This skill guides you on how to query simple bibliographic data for patents using the Zhihuiya patent database, helping users retrieve structured patent metadata efficiently.

Core Concepts

The Zhihuiya Simple Bibliography tool retrieves basic bibliographic (front-page) information for patents. Given one or more patent IDs or publication numbers, it returns structured metadata including title, abstract, applicants, inventors, assignees, classification codes, filing dates, priority claims, and citation references.

Lookup modes: You can look up patents by either patentId (Zhihuiya internal patent ID) or patentNumber (public publication/grant number). If both are supplied, patentId takes priority. Multiple values are separated by commas, with a maximum of 100 per request.

Parameter Guide

Priority rule: When both patentId and patentNumber are present, the API uses patentId and ignores patentNumber.

Response Data Fields

调用方式

• API 端点：POST /zhihuiya/simpleBibliography（完整参数/响应/错误码见 references/api.md）
• Python 脚本：python scripts/zhihuiya_simple_bibliography.py '<JSON 参数>' [--inline]
• 成本约束：本工具会消耗算力；同一会话同一参数组合默认只调用一次，脚本带 24h 本地缓存。失败/空结果不得自动换关键词、翻页或改邮编连续试探；需要继续检索时先向用户说明会产生额外消耗。

输出策略（脚本默认行为）：

• 始终将完整响应写入 <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-zhihuiya-simple-bibliography-<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）
• 响应体 ≤ 8 KB：落盘后把完整 JSON 打印到 stdout
• 响应体 > 8 KB：落盘后 stdout 只输出摘要（顶层字段、常见计数如 total/costToken、最大列表字段的长度 + 前 3 条样本）
• 加 --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。

解决认证和算力问题

发生以下异常情况时，采用 references/onboarding.md 引导解决问题：

异常情况

• 未配置API Key：环境变量未配置 LINKFOX_AGENT_API_KEY，也未配置 LINKFOXAGENT_API_KEY。
• 响应401或402状态码
• 响应提示算力或余额不足：消息含"算力余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值"，或类似含义的内容。

Usage Examples

1. Look up a single patent by publication number

User: "Show me the bibliographic info for patent US11234567B2."
Action: Call with patentNumber = "US11234567B2"

2. Look up multiple patents by publication number

User: "Get the basic info for CN115000000A, EP4000000A1, and JP2023100000A."
Action: Call with patentNumber = "CN115000000A,EP4000000A1,JP2023100000A"

3. Look up patents by Zhihuiya patent ID

User: "Retrieve bibliography for patent IDs abc123 and def456."
Action: Call with patentId = "abc123,def456"

4. Retrieve inventor and applicant information

User: "Who are the inventors and applicants for patent US20230001234A1?"
Action: Call with patentNumber = "US20230001234A1", then extract the inventors and applicants fields from the response.

5. Check patent classification codes

User: "What IPC and CPC codes does patent EP3999999B1 have?"
Action: Call with patentNumber = "EP3999999B1", then present ipcMain, ipcFurther, cpcMain, and cpcFurther from the response.

6. Get patent abstract and citation references

User: "Show me the abstract and cited patents for CN114000000B."
Action: Call with patentNumber = "CN114000000B", then display abstractContent and citedPatents.

Display Rules

1. Present data clearly: Show bibliographic results in well-structured tables or grouped sections. For a single patent, use a key-value layout. For multiple patents, use a table with the most relevant columns.
2. Selective display: When results contain many fields, prioritize showing title, publication number, applicants, inventors, application date, publication date, IPC/CPC main codes, and abstract. Show additional fields only when the user specifically asks.
3. List fields: For array fields (inventors, applicants, assignees, classification codes, citations), present them as comma-separated values or bulleted lists depending on length.
4. Empty fields: Omit fields that are null or empty from the display rather than showing blank entries.
5. Error handling: When a query fails, explain the reason based on the error message and suggest the user verify the patent number or ID format.
6. Batch result notice: When querying many patents at once, remind the user that the maximum is 100 per request.

Important Limitations

• Maximum batch size: Up to 100 patent IDs or publication numbers per request.
• At least one identifier required: Either patentId or patentNumber must be provided; omitting both will cause an error.
• patentId takes priority: If both parameters are supplied, only patentId is used.
• Data scope: This tool returns simple bibliographic data only. It does not return full-text claims, detailed descriptions, legal status, or patent family information.

User Expression & Scenario Quick Reference

Applicable -- Patent bibliographic data retrieval:

Not applicable -- Needs beyond simple bibliographic data:

• Full-text patent claims or detailed description
• Patent legal status or prosecution history
• Patent family / equivalents analysis
• Patent valuation or landscaping
• Freedom-to-operate or infringement analysis
• Patent search by keyword or semantic query (this tool requires specific patent identifiers)

算力消耗规则

按动态规则计费：消耗算力 = 81 × 返回data条数。每条为 1 条简版专利著录项结果

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:

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, set LinkFox Skills.