Token导航 LogoToken导航

Agent Skill · 研究检索

linkfox-zhihuiya-claim-data(Linkfox 智慧芽索赔数据)

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围,避免把样本数据当全量事实;涉及敏感数据、导出文件或批量写回时,应先确认权限和脱敏边界。

linkfox-zhihuiya-claim-data 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 34,018。

总安装 2,277周安装 93GitHub Stars 公开资料未说明下载 737核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:linkfox-zhihuiya-claim-data(Linkfox 智慧芽索赔数据)
来源仓库:https://github.com/linkfox-ai/linkfox-zhihuiya-claim-data
安装命令:
openclaw skills install linkfox-zhihuiya-claim-data
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install linkfox-zhihuiya-claim-data

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

从智慧芽提取专利的权利要求文本与结构。提供独立与从属权利要求树状解析。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。适用于专利侵权比对与技术保护范围分析。注意权利要求解释可能受司法实践影响,建议咨询专业机构。

linkfox-zhihuiya-claim-data 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install linkfox-zhihuiya-claim-data;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

linkfox-zhihuiya-claim-data 怎么安装?

在终端执行 openclaw skills install linkfox-zhihuiya-claim-data。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

linkfox-zhihuiya-claim-data 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

linkfox-zhihuiya-claim-data 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

linkfox-zhihuiya-claim-data 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

linkfox-zhihuiya-claim-data 用的人多吗?

公开数据是累计安装 2,277 次,近一周安装 93 次,下载 737 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

linkfox-zhihuiya-claim-data 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
linkfox-zhihuiya-claim-data

Linkfox 智慧芽索赔数据 · 本页

2,277—需要联网MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
linkfox-zhihuiya-claim-data
description
从智慧芽(PatSnap)获取专利权利要求数据。当用户提到专利权利要求、权利要求文本、独立权利要求、从属权利要求、权利要求数量、权利要求树、权利要求分析、权利要求范围、权利要求语言、想查看特定专利的权利要求部分、patent claims, independent claims, dependent claims, claims text, PatSnap时触发此技能。即使用户未明确提及"智慧芽"或"PatSnap",只要其请求涉及通过专利ID或公开号获取或分析专利权利要求信息,也应触发此技能。

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.

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

FieldAPI NameDescriptionExample
Patent IDpatentIdInternal Zhihuiya patent identifier98a1b2c3-...
Publication NumberpnPublication or grant number of the patentCN115000000A
Related PNpnRelatedPublication number of the family member used as substitute (only present when family substitution occurred)US20230001234A1
ClaimsclaimsArray of claim objects containing the claim text and metadata[...]
Claim CountclaimCountTotal number of claims in the patent15

Parameter Guide

Required (at least one)

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

ParameterDescriptionFormat
patentIdOne or more Zhihuiya patent IDsComma-separated string, max 100 entries
patentNumberOne or more publication/grant numbersComma-separated string, max 100 entries

Optional

ParameterDescriptionValues
replaceByRelatedWhether to substitute with a family member's claims when the target patent's claims are unavailable1 = yes, 0 = no (default)

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:

User SaysScenario
"Show me the claims of patent XX"Single patent claims lookup
"Get the claim text for these patents"Batch claims retrieval
"How many claims does patent XX have"Claim count query
"What are the independent claims of XX"Claims retrieval + display
"Compare claims of patent A and patent B"Multi-patent claims retrieval
"The claims are not available, try a family member"Family substitution query
"Patent claim scope", "claim language"Claims retrieval

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)

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.*

平台分布

OpenClaw

74.55%
按下载量换算549

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills