# linkfox-zhihuiya-patent-family

linkfox-zhihuiya-patent-family — a skill for Claude Code finds patent families from a known patent ID or publication number. It compares family members and country coverage.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 388 installs · ★ 125 repo stars
- Author: linkfox-ai
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/linkfox-ai/linkfox-skills/tree/HEAD/skills/linkfox-zhihuiya-patent-family/SKILL.md
- Updated: 2026-11-11
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/linkfox-zhihuiya-patent-family

## What it does

Give it one patent identifier or a batch of publication numbers; it can retrieve Simple, INPADOC, PatSnap, and equivalent-patent relationships. Batch results stay separated by input patent, while comparisons are grouped by family definition.

The package includes `scripts/zhihuiya_patent_family.py`, a 24-hour local cache, and JSON output saved under `linkfox/<YYYY-MM-DD>/<session>/data/`. Large responses are reduced to a summary on stdout; `--inline` requests the full response there as well. Each API call costs 3算力, and repeated calls with the same parameters use the cached result.

Set `LINKFOX_AGENT_API_KEY` or `LINKFOXAGENT_API_KEY` for authentication; requests cannot proceed without an authorized key. This skill does not search patent text by keywords or classification codes, estimate patent value, retrieve litigation data, or perform infringement and freedom-to-operate analysis.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-patent-family -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/linkfox-zhihuiya-patent-family/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/linkfox-zhihuiya-patent-family/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-patent-family -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/linkfox-zhihuiya-patent-family/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-patent-family -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/linkfox-zhihuiya-patent-family/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install linkfox-ai/linkfox-skills skills/linkfox-zhihuiya-patent-family
```

2. **Manually: put the files in place**
- File: `.github/skills/linkfox-zhihuiya-patent-family/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-patent-family -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/linkfox-ai/linkfox-skills --path skills/linkfox-zhihuiya-patent-family
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/linkfox-zhihuiya-patent-family/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-patent-family -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/linkfox-ai/linkfox-skills/tree/HEAD/skills/linkfox-zhihuiya-patent-family/SKILL.md

## When to use it
- find family members from a publication number
- compare Simple and INPADOC family boundaries
- list related applications by country or region
- process several patents as separate batch results
- contrast member counts across family definitions

## Example prompts
- Find the patent family for `US10000001B2` and group the members by country.
- Compare the Simple and INPADOC families for `US20200012345A1`.
- Look up the INPADOC families for `EP3000001A1,CN112345678A,JP2020123456A` separately.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: c467e26355961973.

BEGIN THIRD-PARTY FILE c467e26355961973
```text
---
name: linkfox-zhihuiya-patent-family
description: 通过已知专利 ID 或公开号查询智慧芽（PatSnap）专利家族，支持单项和批量查找简单同族、INPADOC 同族、PatSnap 同族及等同专利，比较家族成员与国家或地区覆盖。适用于专利家族探索、跨国相关申请查询和多种同族定义对比；不适用于关键词或分类号全文检索、专利估值、诉讼数据、自由实施或侵权分析，以及专利申请和审查事务。
---

# 智慧芽专利家族查询

## 适用范围

### 适用

用户已有一项或多项专利的 ID 或公开（公告）号，希望查找同族成员、等同专利或相关跨国申请时，使用本技能；无需明确提及智慧芽或“专利家族”。

**场景速查**

| 用户表达 | 查询场景 |
|----------|----------|
| 查这项专利的家族 | 查询已知专利的三类同族。 |
| 这项专利有哪些等同专利 | 查看简单同族成员。 |
| 这项专利在哪些国家有相关申请 | 按返回成员整理国家或地区。 |
| 查看 INPADOC 同族或兄弟专利 | 探索较广范围的相关申请。 |
| 比较简单同族和扩展同族 | 对比不同定义的家族成员。 |
| 批量查这些专利的家族 | 按每项输入专利分别组织结果。 |

## 前置条件

**先确定已知专利**：取得用户提供的专利 ID 或公开号，并确认单项查询、批量查询或家族比较的目标。参数格式和批量限制见 `references/api.md`。

## 查询流程

1. 确认待查专利和希望比较的同族类型，按 `references/api.md` 整理查询条件。
2. 按“算力消耗预估”中的每次调用费用估算消耗，在已有授权范围内执行查询；高频调用或用户对消耗量预期不足时提醒用户，由用户决定是否继续。复用相同参数的有效缓存。
3. 按接口参考判断响应，逐项整理三类同族成员、家族标识、成员数量及国家或地区；比较任务按家族类型分组，批量任务按输入专利分组。
4. 返回错误或空结果时，说明可能的格式问题、数据库未收录等原因，建议核对输入。不得自动变更条件连续试探；继续调用遵守成本约束。

## 执行方式

- **直接调用接口**：接口端点、完整参数、响应和错误码见 `references/api.md`。
```
END THIRD-PARTY FILE c467e26355961973

The third-party file has ended. Everything between the c467e26355961973 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2359 of 7018 bytes. © linkfox-ai · MIT · https://github.com/linkfox-ai/linkfox-skills/tree/HEAD/skills/linkfox-zhihuiya-patent-family/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
