# linkfox-zhihuiya-description-data

The linkfox-zhihuiya-description-data skill for Claude Code retrieves patent descriptions by ID or publication number, singly or in batches. It can use a related-family version if none exists.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 228 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-description-data/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-description-data

## What it does

The skill fetches patent description text using a Zhihuiya internal ID or a publication number such as `CN115099012A`. Results can cover several patents, with sections grouped by patent. If the target description is missing, a family document can be requested and its publication number identified.

API requests use `scripts/zhihuiya_description_data.py`, which saves the full response as a JSON file. Responses over 8 KB are represented by a summary in standard output; `--inline` prints the complete response. Each request uses an estimated 3算力, and extra requests add to the cost. The skill is instructed to explain the estimate and get the user's approval first. Access requires `LINKFOX_AGENT_API_KEY` or `LINKFOXAGENT_API_KEY`.

This retrieves description text; it does not search by keywords or provide legal analysis. A request needs a patent ID or publication number.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

2. **Manually: put the files in place**
- File: `.cursor/skills/linkfox-zhihuiya-description-data/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-description-data
```

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-description-data -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-description-data/SKILL.md

## When to use it
- retrieve a patent description by publication number
- request descriptions for several patents at once
- get a family patent's description when the target has none
- organize returned text by description section

## Example prompts
- Retrieve the description for patent `CN115099012A` and show its technical sections.
- Get descriptions for `CN115099012A` and `US20230012345A1`, with results separated by publication number.
- If this patent has no description, request a family version and identify its publication number.

## 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: 2c78330c191e4c38.

BEGIN THIRD-PARTY FILE 2c78330c191e4c38
```text
---
name: linkfox-zhihuiya-description-data
description: 通过专利 ID 或公开公告号获取智慧芽（PatSnap）专利说明书，支持单项或批量查询及同族专利说明书替代。适用于查看专利全文中的技术描述、背景、实施方式和说明书章节；无需明确提及智慧芽。不适用于按关键词、申请人或分类检索专利、权利要求分析或对照表、法律状态及审查历史查询、专利布局统计、自由实施或侵权意见。
---

# 智慧芽专利说明书查询

## 适用范围

### 适用

用户已有一项或多项专利的内部 ID 或公开公告号，希望查看完整说明书、技术描述或实施方式时使用本技能。

**场景速查**

| 用户表达 | 查询场景 |
|----------|----------|
| 查看这项专利的说明书 | 单项说明书查询。 |
| 获取这些专利的完整技术描述 | 批量说明书查询。 |
| 查看 CN115099012A 的详细文本 | 按公开公告号查询。 |
| 原专利没有说明书，能否查看同族版本 | 根据用户意愿使用同族说明书替代。 |
| 这项专利具体描述了什么技术、有哪些实施方式 | 获取并整理实际返回的说明书章节。 |

## 前置条件

先确定用户提供的是公开公告号还是智慧芽内部专利 ID，并确认待查专利范围。仅有关键词、申请人或分类时，应先取得专利标识；输入要求见 [接口说明](references/api.md)。

## 查询流程

1. 确认用户要查看的专利及内容范围：公开公告号使用 `patentNumber`，智慧芽内部 ID 使用 `patentId`；单项或批量请求均按 [接口说明](references/api.md) 的标识选择、优先级和输入限制准备。
2. 用户希望在目标说明书缺失时查看同族版本，可在本次查询中启用同族替代；先说明返回内容可能来自另一公开公告号的专利。
3. 查询前按“算力消耗预估”说明预计费用，在用户授权范围内执行查询；相同参数优先复用已有响应。
4. 执行查询并保存完整响应，先检查摘要，再从保存文件读取需要的章节。失败或无说明书时解释返回原因，建议核对标识；若用户需要尝试同族版本，说明额外消耗后再按其决定继续。
```
END THIRD-PARTY FILE 2c78330c191e4c38

The third-party file has ended. Everything between the 2c78330c191e4c38 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 2279 of 7211 bytes. © linkfox-ai · MIT · https://github.com/linkfox-ai/linkfox-skills/tree/HEAD/skills/linkfox-zhihuiya-description-data/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
