MCPInstall

linkfox-zhihuiya-patent-image-search

基于智慧芽的专利图片相似度搜索,支持通过图片URL检索外观设计专利。当用户提到专利图片搜索、外观设计专利侵权检查、外观专利搜索、视觉专利查询、以图搜专利、专利相似度检测、专利图片匹配、洛迦诺分类搜索、检查产品设计是否侵犯已有专利、patent image search, design patent search, patent reverse image search, design patent lookup, PatSnap, patent similarity时触发此技能。即使用户未明确提及"智慧芽"或"专利图片",只要其需求涉及通过图片查找相似外观专利或排查外观专利风险,也应触发此技能。本技能仅支持外观设计专利,实用新型专利检索请使用 linkfox-zhihuiya-utility-patent-image-search。

Installs
403
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-patent-image-search
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads linkfox-zhihuiya-patent-image-search automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Zhihuiya Patent Image Search

This skill guides you on how to perform image-based patent similarity searches using the Zhihuiya patent database, helping users identify potentially similar design patents. This skill supports design patents only; for utility model patents use linkfox-zhihuiya-utility-patent-image-search.

Core Concepts

Patent Image Search uses visual AI models to compare a given product or design image against a global patent image database. It returns a ranked list of similar patents, enabling users to evaluate infringement risks or conduct prior-art research.

This skill supports design patents only:

TypeCodeDescription
Design PatentDProtects the ornamental appearance of a product

Search models for design patents:

Model IDStrategyRecommendation
1Intelligent AssociationRecommended for design patents (default)
2Search This ImageExact visual match

Utility model patents (model 3/4) are not supported by this skill. Use linkfox-zhihuiya-utility-patent-image-search instead.

Scoring logic: A higher score value means greater visual similarity. When presenting results, sort by score in descending order (highest similarity first) so users can prioritize the most relevant patents for review.

Parameter Guide

Required Parameters

ParameterDescriptionExample
urlThe image URL to search againsthttps://example.com/product.jpg
patentTypePatent type, fixed to D (design) by this skillD
modelSearch model ID: 1 (recommended) or 21

Common Optional Parameters

ParameterDescriptionDefault
countryPatent authority country codes, comma-separated (e.g., CN,US,JP)All countries
locLocarno classification codes, connectable with AND/OR/NOTNone
legalStatusLegal status codes, comma-separatedNone
simpleLegalStatusSimple legal status: 0 (expired), 1 (active), 2 (pending)None
assigneesApplicant / patent holder nameNone
applyStartTimeApplication start date (yyyyMMdd)None
applyEndTimeApplication end date (yyyyMMdd)None
publicStartTimePublication start date (yyyyMMdd)None
publicEndTimePublication end date (yyyyMMdd)None
limitNumber of results to return (1-100)10
offsetPagination offset (0-1000)0
fieldSort field: SCORE, APD, PBD, ISDSCORE
orderSort order: desc or asc (for APD/PBD/ISD)desc
langTitle language preference: original, cn, enoriginal
preFilterEnable country/LOC pre-filtering: 1 (on) / 0 (off)1
stemmingEnable stemming: 1 (on) / 0 (off)0
mainFieldSearch within title, abstract, claims, description, publication number, application number, applicant, inventor, IPC/UPC/LOCNone
includeMachineTranslationInclude machine-translated data in searchNone
scoreExpansionEnable score expansionNone
isHttpsReturn HTTPS image URLs: 1 (yes) / 0 (no)0
returnImgIdReturn image IDs in resultsfalse

Commonly Used Country Codes

CodeCountry/Region
CNChina
USUnited States
JPJapan
KRSouth Korea
EPEuropean Patent Office
WOWIPO
DEGermany
GBUnited Kingdom
FRFrance
AUAustralia

调用方式

  • API 端点:POST /zhihuiya/patentImageSearch(完整参数/响应/错误码见 references/api.md)
  • Python 脚本:python scripts/zhihuiya_patent_image_search.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-patent-image-search-<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。

Local Image Upload

This tool requires a publicly accessible image URL. If the user provides a local image file path (e.g., C:\Users\...\photo.png, /home/.../image.jpg), you must upload it first to obtain a public URL.

Run the upload script:

python scripts/upload_image.py /path/to/local/image.png

The script will return a public URL (valid for 24 hours) that can be used as the image URL parameter.

Usage Examples

1. Basic design patent search (recommended starting point) Search for design patents similar to a product image across all countries:

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "limit": 20
}

2. Design patent search limited to specific countries Search only in China and the United States:

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "country": "CN,US",
  "limit": 20
}

3. Search with Locarno classification filter Narrow results to a specific product category (e.g., LOC 07-01 for tableware):

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "loc": "07-01",
  "preFilter": 1,
  "limit": 20
}

4. Search only active patents within a date range Find active design patents filed after 2020:

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "simpleLegalStatus": "1",
  "applyStartTime": "20200101",
  "limit": 30
}

5. Search by specific assignee Find patents held by a particular company:

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "assignees": "Apple Inc.",
  "limit": 20
}

6. Get results with Chinese-translated titles

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "lang": "cn",
  "limit": 20
}

Display Rules

  1. Sort by score: Always sort results by score in descending order (highest similarity first) to help users quickly identify the most relevant infringement risks.

  2. Show complete details: When summarizing results or generating reports, include ALL of the following for each patent -- do NOT omit or abbreviate:

    • Application number (apno)
    • Patent title in Chinese (use lang: cn or provide translation)
    • Inventor (inventor)
    • Patent drawing (the matched url image)
    • Every patent image in the image list
    • Patent abstract
    • Patent description
    • LOC classification information (loc)
    • Radar result (radarResult) if available
    • Patent specification
  3. Legal disclaimer: Always append a friendly reminder at the end of results:

    This search result was generated by LinkfoxAgent. It is recommended to consult a professional patent attorney for legal advice.

  4. Score explanation: Remind users that the score represents visual similarity -- a higher score indicates a closer match, but does not constitute a legal determination of infringement.

  5. Pagination guidance: When the total count exceeds the returned results, inform users about the total number of matching patents and guide them to use offset and limit for additional pages.

  6. Error handling: When a query fails, explain the reason and suggest adjustments (e.g., verify the image URL is publicly accessible, check country codes, adjust date formats).

User Expression & Scenario Quick Reference

Applicable -- Image-based patent similarity searches:

User SaysScenario
"Check if my product design infringes any patents"Design patent infringement check
"Search for similar design patents"Design patent similarity search
"Find patents that look like this image"Visual patent lookup
"Are there any patents similar to my product appearance"Appearance risk assessment
"Utility model patent search by image"Utility model search
"Check patent risks for this product in China and US"Multi-country patent check
"Find active design patents in this category"Filtered patent search
"Who holds patents similar to this design"Competitor patent discovery

Not applicable -- Needs beyond patent image search:

  • Text-based patent search (keyword/abstract/claim search)
  • Patent legal status monitoring or annuity management
  • Patent valuation or licensing negotiation
  • Freedom-to-operate (FTO) legal opinions
  • Patent family or citation analysis

算力消耗规则

消耗 81 算力。

用户会因算力消耗而支付费用。请充分评估:当需要高频调用本技能,或用户对算力消耗量预期不足时,务必提醒用户,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.

FAQ

What does the linkfox-zhihuiya-patent-image-search skill do?

基于智慧芽的专利图片相似度搜索,支持通过图片URL检索外观设计专利。当用户提到专利图片搜索、外观设计专利侵权检查、外观专利搜索、视觉专利查询、以图搜专利、专利相似度检测、专利图片匹配、洛迦诺分类搜索、检查产品设计是否侵犯已有专利、patent image search, design patent search, patent reverse image search, design patent lookup, PatSnap, patent similarity时触发此技能。即使用户未明确提及"智慧芽"或"专利图片",只要其需求涉及通过图片查找相似外观专利或排查外观专利风险,也应触发此技能。本技能仅支持外观设计专利,实用新型专利检索请使用 linkfox-zhihuiya-utility-patent-image-search。

How do I install linkfox-zhihuiya-patent-image-search?

Run npx skills add https://github.com/linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-patent-image-search in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/linkfox-zhihuiya-patent-image-search/ (personal) or .claude/skills/linkfox-zhihuiya-patent-image-search/ (project).

Which AI agents can use linkfox-zhihuiya-patent-image-search?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is linkfox-zhihuiya-patent-image-search safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains linkfox-zhihuiya-patent-image-search?

It is published by linkfox-ai in linkfox-ai/linkfox-skills. It has 403 recorded installs.

More from linkfox-ai/linkfox-skills

View all →

linkfox-multimodal-recognize-image

linkfox-ai/linkfox-skills

基于多模态AI的图片识别与分析。当用户想分析、描述、从图片URL中提取信息、image recognition, image analysis, image description, image content understanding, OCR text recognition, visual Q&A时触发此技能。当用户提到图片识别、图片分析、图片描述、识别图片内容、分析产品图、从图片中读取文字、描述图片、提取视觉内容或理解照片内容时触发。当用户提供图片URL并就其视觉内容提问时,即使未明确说"图片识别",也应触发此技能。

Media & Creative1.2K installs

linkfox-amazon-search

linkfox-ai/linkfox-skills

模拟真实用户在亚马逊前台搜索,获取实时关键词排名和搜索结果页数据。当用户提到亚马逊商品搜索、搜索结果抓取、关键词在搜索页的排名、ASIN排名位置查询、竞品发现、搜索页价格对比、广告商品分析、新品监控、前台搜索模拟、Amazon search, keyword ranking, search results, ASIN ranking position, competitor discovery, price comparison, sponsored product analysis, real-time search, new product monitoring时触发此技能。即使用户未明确提及"搜索模拟",只要其需求涉及实时亚马逊搜索结果、商品排位数据或前台SERP分析,也应触发此技能。

DevOps & Cloud472 installs

linkfox-dld-product-search

linkfox-ai/linkfox-skills

在中国1688批发平台(阿里巴巴国内B2B市场)上搜索和分析商品,用于找货源、供应商发现和选品。当用户提到1688商品搜索、1688找货源、在1688上找供应商、批发商品查询、工厂货源、一件代发供应商搜索、1688关键词选品、批发价格对比、按销量筛选、任何1688平台上的选品调研、1688 search, 1688 product selection, find suppliers, factory lookup, wholesale pricing, supplier search, domestic sourcing, 1688 products时触发此技能。即使用户未明确说"1688",只要其需求涉及搜索批发商品、寻找国内供应商或从国内市场采购,也应触发此技能。

Business & Finance457 installs

linkfox-mpstats-ozon-product-search

linkfox-ai/linkfox-skills

MPSTATS Ozon 俄罗斯站商品搜索与反查。按俄语关键词或 SKU 在 MPSTATS 数据库中检索 Ozon 商品,返回商品 ID、标题、品牌和卖家信息,是 Ozon 选品与竞品链路的起点。当用户提到 Ozon 选品、Ozon 商品搜索、俄罗斯电商选品、Ozon 关键词搜索、Ozon SKU 查询、MPSTATS Ozon、Ozon product search, MPSTATS Ozon, Russian marketplace, Ozon SKU lookup, Ozon keyword search 时触发此技能。即使用户未明确提到"MPSTATS",只要其意图是在 Ozon 俄罗斯站按关键词或 SKU 发现或反查商品,也应触发此技能。

449 installs

linkfox-amazon-product-detail

linkfox-ai/linkfox-skills

通过ASIN获取亚马逊商品详细信息,包括标题、图片、五点描述、规格参数、A+页面、价格、评分评论、变体等;可在取得原始HTML时尝试提取Item Highlights(商品亮点)。当用户提到亚马逊商品详情、ASIN查询、商品页面数据、Listing分析、五点描述提取、Item Highlights提取、标题补充信息、商品图片获取、变体查看、竞品Listing研究、价格查询、评论拆解、商品规格查询、Amazon product details, ASIN lookup, listing analysis, bullet points, variant info, product pricing, ratings and reviews, A+ content, product specifications, product images时触发此技能。即使用户未明确说"商品详情",只要其需求涉及通过ASIN获取亚马逊商品页面的结构化数据,也应触发此技能。

Frontend & Design446 installs

linkfox-sellersprite-product-search

linkfox-ai/linkfox-skills

Open the skill to read its SKILL.md instructions.

435 installs

Popular media & creative skills

View category →

hyperframes

heygen-com/hyperframes

Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.

Media & Creative1.2M installs

media-use

heygen-com/hyperframes

Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.

Media & Creative1.1M installs

hyperframes-registry

heygen-com/hyperframes

About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.

Media & Creative1M installs

hyperframes-creative

heygen-com/hyperframes

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.

Media & Creative916.5K installs

ai-video-generation

101-skills/superpowers

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

Media & Creative881.5K installs

ai-image-generation

101-skills/superpowers

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

Media & Creative880.3K installs