Linkfox Zhihuiya Claim Data

Zhihuiya Patent Claims Data

This skill guides you on how to retrieve and present patent claims data from the Zhihuiya (PatSnap) patent database, helping IP professionals, patent analysts, and R&D teams quickly access the claims section of any patent.

调用方式

• API 端点：POST /zhihuiya/claimData（完整参数/响应/错误码见 references/api.md）
• Python 脚本：python scripts/zhihuiya_claim_data.py '<JSON 参数>' [--inline]
• 成本约束：本工具会消耗积分；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-claim-data-<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。

解决认证和积分问题

发生以下异常情况时，采用以下措施来处理：

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
• 响应提示积分或余额不足：消息含"积分余额不足/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。

措施

• 优先采用skill内的 onboarding.md 引导解决问题。
• 如找不到 onboarding.md 文件，则加载 /linkfox-onboarding 这个skill并根据它的引导来处理。如未安装请先安装：
  • 下载 https://agent-files.linkfox.com/skills/linkfox-onboarding/release.zip，解压后安装这个skill。如需用户授权才可下载，要询问用户获得授权，你不能自己放弃下载。
• 兜底措施：仅当前面两个措施经过所有努力都走不通时，才提示用户依据 https://skill.linkfox.com/linkfoxskills/guide.htm 指引获取API Key，或去 https://os.linkfox.com/ 补充积分。

Core Concepts

Patent claims define the legal scope of protection granted by a patent. They are the most critical part of a patent document for infringement analysis, freedom-to-operate assessments, and prior art comparisons. This tool retrieves the full set of claims for one or more patents by their patent ID or publication number.

Family substitution: When a patent's claims are unavailable in the database, you can optionally request that claims from a related family member patent be returned instead. This is controlled by the replaceByRelated parameter.

Data Fields

Parameter Guide

Required (at least one)

You must provide at least one of the following two parameters. If both are provided, patentId takes priority.

Optional

How to Choose Between patentId and patentNumber

• Use patentNumber when the user provides a publication or grant number (e.g., CN115000000A, US11234567B2). This is the most common scenario.
• Use patentId when the user provides an internal Zhihuiya identifier, typically obtained from a previous Zhihuiya search result.
• When the user provides both, pass both and the API will prefer patentId.

Usage Examples

1. Single patent by publication number

{"patentNumber": "CN115000000A"}

2. Multiple patents by publication number

{"patentNumber": "CN115000000A,US20230001234A1,EP4000000A1"}

3. Single patent by patent ID

{"patentId": "98a1b2c3-xxxx-xxxx-xxxx-xxxxxxxxxxxx"}

4. With family substitution enabled

{"patentNumber": "CN115000000A", "replaceByRelated": "1"}

5. Batch query with family substitution

{"patentNumber": "CN115000000A,JP2023100000A", "replaceByRelated": "1"}

Display Rules

1. Present claims clearly: Display claims in a numbered list preserving the original claim numbering. Use indentation or formatting to distinguish independent claims from dependent claims where possible.
2. Highlight claim count: Always state the total number of claims returned for each patent.
3. Family substitution notice: If pnRelated is present in a result, explicitly inform the user that the claims shown are from a family member patent and provide the family member's publication number.
4. Batch results: When multiple patents are queried, organize results by patent with clear headings showing the publication number.
5. Error handling: When a query fails, explain the reason based on the response and suggest the user verify the patent number format or try enabling family substitution.
6. No subjective analysis: Present the raw claim text without legal interpretation unless the user specifically requests analysis.

Important Limitations

• At least one identifier required: Either patentId or patentNumber must be provided; omitting both will result in an error.
• Batch limit: A maximum of 100 patents can be queried in a single request.
• Claims availability: Not all patents have claims data available. Use replaceByRelated = 1 to attempt family member substitution when claims are missing.
• Claim object structure: The individual claim objects within the claims array may vary in structure depending on the patent office and data source.

User Expression & Scenario Quick Reference

Applicable -- Patent claims retrieval and analysis:

Not applicable -- Needs beyond patent claims data:

• Patent search or discovery (finding patents by keyword/topic)
• Patent legal status or prosecution history
• Patent citation or reference analysis
• Patent full-text beyond claims (abstract, description, drawings)
• Freedom-to-operate or infringement opinions (legal advice)

积分消耗规则

按动态规则计费：消耗积分 = 81 × 返回data条数。每条为 1 条专利权利要求结果

重要：本技能的服务按倍数动态计算，可能一次性消耗大量积分，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.