
linkfox-1688-search-by-image
1688平台以图搜图,通过商品图片精准检索外观相似或同款的1688货源,返回标题、价格、起批量、月销量、复购率、交易评分等核心数据。当用户提到1688以图搜图、1688找货源、以图找同款、跨境找工厂、1688识图、图片找货源、找相似货源、image search 1688、find supplier by image时触发此技能。即使用户未明确提及"以图搜图",只要用户提供了图片URL并希望在1688上查找匹配或相似的货源商品,也应触发此技能。
- Installs
- 370
- 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-1688-search-by-image- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads linkfox-1688-search-by-image automatically when relevant.
- 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.
1688 Image-Based Product Search
This skill performs visual product searches on the 1688 platform using an image URL, helping cross-border sellers find visually similar supplier products for sourcing.
Core Concepts
1688 Image Search uses visual recognition to find products with similar appearance on the 1688 wholesale marketplace. It returns supplier product data including title, price, minimum order quantity, monthly sales, repurchase rate, trade score, and seller identity badges.
Data Fields
| Field | Description |
|---|---|
| offerId | Product ID on 1688 |
| title | Product title |
| imageUrl | Product main image |
| price | Wholesale price (CNY) |
| consignPrice | Dropship price (CNY) |
| salesQuantity | Monthly sales volume |
| estimatedSalesAmount | Estimated monthly revenue |
| quantityBegin | Minimum order quantity |
| repurchaseRate | Repurchase rate |
| tradeScore | Product trade score |
| compositeServiceScore | Composite service experience score |
| sellerIdentities | Seller identity (超级工厂/实力商家/诚信通会员) |
| offerIdentities | Product badge (严选) |
| sendGoodsAddressText | Shipping origin |
| deliveryTime | Delivery time (24/48 hours) |
| isOnePsale | Supports dropshipping (是/否) |
| isJxhy | Premium sourcing (是/否) |
| hasPromotion | Has promotion (是/否) |
| isPatentProduct | Patent product (是/否) |
Parameter Guide
Image Rules:
- JPEG and PNG are passed through unchanged. WebP is detected from its real file bytes and transparently converted to JPEG before the 1688 call.
- Base64 string must be pure encoded content WITHOUT the
data:image/jpeg;base64,prefix. - Image source — one of imageUrl, imageBase64, or imageId must be provided (at least one required).
| Parameter | Required | Default | Description |
|---|---|---|---|
| imageUrl | Conditional | - | Public image URL (max 1000 chars). JPEG/PNG pass through; WebP is converted automatically |
| imageBase64 | Conditional | - | Pure Base64 without a data URL prefix. JPEG/PNG pass through; WebP is converted automatically |
| imageId | Conditional | - | 1688 image ID from previous search result (speeds up pagination) |
| page | No | 1 | Page number, starting from 1 |
| pageSize | No | 20 | Results per page (1-50) |
| priceStart | No | - | Min price filter (CNY) |
| priceEnd | No | - | Max price filter (CNY) |
| filter | No | - | Filter conditions, comma-separated (see supported filters below) |
| sort | No | {"monthSold":"desc"} | Sort as JSON: {field: direction} (see supported sort fields below) |
| keyword | No | - | Keyword to further filter results |
| productCollectionId | No | - | Product collection ID (see supported IDs below) |
Supported Filters
Multiple filters can be combined with commas (e.g. 1688Selection,totalEpScoreLv1,qrr0).
| Filter Value | Description |
|---|---|
| 1688Selection | 1688严选 |
| certifiedFactory | 认证工厂 |
| totalEpScoreLv1 | 综合体验分5星 |
| totalEpScoreLv2 | 综合体验分4星 |
| totalEpScoreLv3 | 综合体验分3星 |
| totalEpScoreLv4 | 综合体验分2星 |
| qrr0 | 无品质退款 |
| qrr1 | 品质退款率<1% |
| qrr5 | 品质退款率<5% |
| qrr10 | 品质退款率<10% |
| shipInToday | 当日发货 |
| shipIn24Hours | 24小时发货 |
| shipIn48Hours | 48小时发货 |
| noReason7DReturn | 7天无理由退货 |
| isOnePsale | 一件代发 |
| isOnePsaleFreePost | 一件代发包邮 |
| new7 | 7天内新品 |
| new30 | 30天内新品 |
| isQqyx | 全球严选 |
| JPFL | 日本专线 |
| USFL | 美国专线 |
| KRFL | 韩国专线 |
| VNFL | 越南专线 |
| SAFL | 沙特专线 |
| RUFL | 俄罗斯专线 |
| KZFL | 哈萨克斯坦专线 |
| HKFL | 香港专线 |
| MOFL | 澳门专线 |
| TWFL | 台湾专线 |
Supported Sort Fields
| Field | Direction | Description |
|---|---|---|
| price | asc/desc | Price ascending/descending |
| monthSold | asc/desc | Monthly sales ascending/descending |
| rePurchaseRate | asc/desc | Repurchase rate ascending/descending |
Sort format example: {"price":"asc"} for price low to high.
Supported Product Collection IDs
| ID | Usage |
|---|---|
| 262105288 | 跨境货盘 |
| 262105286 | 跨境货盘 |
| 262105253 | 跨境货盘 |
| 262105281 | 跨境货盘 |
| 262105280 | 跨境货盘 |
| 262105277 | 跨境货盘 |
| 262105276 | 跨境货盘 |
| 262105274 | 跨境货盘 |
| 262105269 | 跨境货盘 |
| 262185282 | 跨境货盘 |
调用方式
- API 端点:
POST /alibaba1688/imageSearch(完整参数/响应/错误码见references/api.md) - Python 解释器选择:调用前先选择一个真实可用的 Python 命令并在本次任务中始终复用,记为
<PYTHON>。Windows 按py -3、python、python3的顺序尝试,其他系统按python3、python的顺序尝试;候选命令必须执行<候选命令> -c "import sys; print(sys.executable)"后退出码为 0 且 stdout 含非空解释器路径,否则视为不可用(WindowsApps 的空输出占位命令不得选用)。 - Python 脚本:
<PYTHON> scripts/alibaba1688_image_search.py '<JSON 参数>' [--inline] - 无感图片预处理:必须通过上述脚本调用。JPEG/PNG 保持原逻辑;WebP 由 Agent 使用 Pillow 转成 JPEG 后再按原逻辑调用,不要求用户手工转换。
- Pillow 首次初始化:在当前运行环境第一次调用本 Skill 前,Agent 必须用
<PYTHON>执行<PYTHON> -c "from PIL import features; ok=features.check('webp'); print('WEBP_OK' if ok else 'WEBP_MISSING'); raise SystemExit(0 if ok else 1)"。只有退出码为 0 且 stdout 包含WEBP_OK才算检查通过。如果检查失败,静默执行<PYTHON> -m pip install --disable-pip-version-check "Pillow>=10.4,<13",然后用同一<PYTHON>重新检查一次。检查通过后再运行图搜脚本;第二次仍失败时停止并报告依赖初始化失败,不得进入收费接口,也不得循环安装或要求用户手工处理。后续调用检查通过即可直接执行,不重复安装。 - 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-1688-search-by-image-<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, 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 imageUrl parameter.
Usage Examples
1. Basic image search
在1688搜索与图片相似的商品,图片地址为 https://m.media-amazon.com/images/I/719mRAn2VrL._AC_SL1500_.jpg
2. Search with filters
在1688搜索与图片相似的商品,图片地址为 https://m.media-amazon.com/images/I/719mRAn2VrL._AC_SL1500_.jpg,查询第1页,筛选1688严选,并按价格从高到低排序
3. Search with sorting
在1688搜索与图片相似的商品,图片地址为 https://example.com/product.jpg,按价格从高到低排序
4. Paginated search
在1688搜索与图片相似的商品,图片地址为 https://example.com/product.jpg,查询第2页,每页50条
5. Price range filter
在1688搜索与图片相似的商品,图片地址为 https://example.com/product.jpg,价格区间10-100元
Display Rules
- Present data clearly: Show results in a structured table with key columns: product image, title, price, dropship price, monthly sales, minimum order quantity, repurchase rate, and seller identity
- Image display: When the response includes imageUrl for products, display them inline for visual comparison
- Price display: Always show price in CNY (¥) format
- Seller badges: Display seller identity badges (超级工厂/实力商家/诚信通会员) and product badges (严选) prominently
- Result count: Always inform the user of total results and current page/total pages
- Pagination hint: When more pages are available, suggest the user can request the next page
- Filter/sort limitation: If the user requests a sort or filter not in the supported list, do NOT attempt any workaround. Inform the user of the supported options
- No secondary processing: Results are real-time and not stored in a database, so secondary SQL/data processing is not available
Important Limitations
- Data real-time nature: Results are live searches, not stored in any database. Cannot use
_dataQuery_executeDynamicQueryfor secondary processing. - Logic constraint: If the user requests sort or filter conditions not in the preset supported list, do NOT call any other tool or logic to compensate.
- Image input: One of imageUrl, imageBase64, or imageId is required. For page > 1, prefer passing imageId from the first page result to speed up queries.
- Image format: JPEG/PNG follow the original path. The bundled script transparently converts WebP to JPEG before calling 1688. GIF and other formats retain their original behavior.
- Base64 format: The imageBase64 value must be the raw Base64 string only — do NOT include the
data:image/jpeg;base64,prefix. - Page size: Maximum 50 results per page.
User Expression & Scenario Quick Reference
Applicable -- Visual product sourcing scenarios on 1688:
| User Says | Scenario |
|---|---|
| "1688以图搜图" / "用图片找1688货源" | Basic image search |
| "帮我在1688找这个图片的同款" | Find same-style products |
| "跨境找工厂,图片是..." | Cross-border supplier sourcing |
| "这个Amazon产品在1688有没有货源" | Reverse sourcing from Amazon image |
| "筛选1688严选的相似商品" | Filtered image search |
| "按月销量排序找相似货源" | Sorted image search |
| "查看第2页结果" | Pagination |
Not applicable -- Needs beyond 1688 image search:
- Text/keyword-based 1688 search (use 店雷达-1688选品库)
- 1688 product rankings/trending (use 店雷达-1688商品榜单)
- Amazon image search (use 亚马逊前端-以图搜图)
- Image generation or editing
- Product review analysis
- Price history or trend analysis
Boundary judgment: When users say "找货源" or "找同款", if they provide an image URL and the intent is to find visually similar products on 1688, this skill applies. If they want keyword-based search or ranking data on 1688, use the 店雷达 tools instead.
算力消耗规则
消耗 5 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:
- The functionality or purpose described in this skill does not match actual behavior
- The skill's results do not match the user's intent
- The user expresses dissatisfaction or praise about this skill
- 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, visit LinkFox Skills.
FAQ
What does the linkfox-1688-search-by-image skill do?
1688平台以图搜图,通过商品图片精准检索外观相似或同款的1688货源,返回标题、价格、起批量、月销量、复购率、交易评分等核心数据。当用户提到1688以图搜图、1688找货源、以图找同款、跨境找工厂、1688识图、图片找货源、找相似货源、image search 1688、find supplier by image时触发此技能。即使用户未明确提及"以图搜图",只要用户提供了图片URL并希望在1688上查找匹配或相似的货源商品,也应触发此技能。
How do I install linkfox-1688-search-by-image?
Run npx skills add https://github.com/linkfox-ai/linkfox-skills --skill linkfox-1688-search-by-image 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-1688-search-by-image/ (personal) or .claude/skills/linkfox-1688-search-by-image/ (project).
Which AI agents can use linkfox-1688-search-by-image?
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-1688-search-by-image 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-1688-search-by-image?
It is published by linkfox-ai in linkfox-ai/linkfox-skills. It has 370 recorded installs.
More from linkfox-ai/linkfox-skills
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。
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。
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。
linkfox-mpstats-ozon-product-search
linkfox-ai/linkfox-skills
Open the skill to read its SKILL.md instructions.
linkfox-amazon-product-detail
linkfox-ai/linkfox-skills
Open the skill to read its SKILL.md instructions.
linkfox-sellersprite-product-search
linkfox-ai/linkfox-skills
Open the skill to read its SKILL.md instructions.
Popular media & creative skills
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-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.
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.
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.
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
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