← 返回 Skills 市场
529
总下载
2
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install image-search
功能描述
Visual image search using Google Lens via SerpAPI. Identify objects, landmarks, products, plants, animals, artwork, logos, or any visual entity from an image...
使用说明 (SKILL.md)
Image Search (Google Lens)
Identify anything from an image using Google Lens via SerpAPI.
Setup
Requires SERPAPI_KEY environment variable. Get a key at https://serpapi.com/ (100 free searches/month).
No pip dependencies needed — uses only Python stdlib (urllib, json, base64).
Usage
From CLI / Agent (exec tool)
# Search by image URL
python3 {baseDir}/scripts/lens_search.py "https://example.com/photo.jpg"
# Search by local file (auto-uploads to get a URL)
python3 {baseDir}/scripts/lens_search.py /path/to/image.png
# Refine with text query (e.g., find red version of a product)
python3 {baseDir}/scripts/lens_search.py "https://example.com/bag.jpg" --query "red"
# Product search (returns prices)
python3 {baseDir}/scripts/lens_search.py "https://example.com/sneakers.jpg" --type products
# Find exact matches (where this image appears online)
python3 {baseDir}/scripts/lens_search.py "https://example.com/photo.jpg" --type exact_matches
# Raw JSON output for programmatic use
python3 {baseDir}/scripts/lens_search.py "https://example.com/photo.jpg" --json
# Localized results (e.g., Japanese products with ¥ prices)
python3 {baseDir}/scripts/lens_search.py "https://example.com/laptop.jpg" --type products --country jp
Search Types
| Type | Use Case | Returns |
|---|---|---|
all (default) |
General identification | Entity name + visual matches + text |
visual_matches |
Find similar images | Visually similar results with sources |
exact_matches |
Find image origin | Pages containing this exact image |
products |
Shopping / price lookup | Products with prices and buy links |
about_this_image |
Image provenance | Metadata about the image's origin |
Output Format
The script outputs structured markdown:
## Identified Entity
- **Danny DeVito** — [link](https://...)
## Visual Matches (top 5)
- **Danny DeVito — Wikipedia** (Wikipedia) ✅ exact match
https://en.wikipedia.org/wiki/Danny_DeVito
- ...
Use --json for raw SerpAPI response when you need thumbnails, image dimensions, or other metadata.
Agent Decision Guide
When a user sends an image:
- Already identified by vision model? If the main model confidently recognizes the entity, skip reverse search.
- Uncertain identification? Run
lens_search.pyto verify. Compare model's guess with Lens results. - Need details beyond identification? First identify with Lens, then
web_searchfor deeper info. - Shopping intent? Use
--type productsto get prices and buy links directly. - Local file from user? The script handles local files by auto-uploading to get a searchable URL.
Combining with Other Tools
Typical multi-tool workflow:
1. User sends image → "What building is this?"
2. reverse_image_search → identifies "Cologne Cathedral"
3. web_search("Cologne Cathedral history architecture") → detailed info
4. Compose answer combining visual match + web knowledge
Limitations
- SerpAPI free tier: 100 searches/month. Paid plans from $50/month.
- Local file upload uses freeimage.host (free) or imgbb (needs IMGBB_API_KEY).
- Google Lens results vary by region; use
--countryfor localized results. - Some niche/long-tail entities may not return useful visual matches.
安全使用建议
This skill appears to implement Google Lens searches via SerpAPI (so SERPAPI_KEY is required) and the included Python script is self-contained. Before installing: (1) Understand that if users provide local images the script will automatically upload them to public image-hosting services (freeimage.host by default, or imgbb if you set IMGBB_API_KEY). That means sensitive images will be transmitted to third parties. (2) The metadata only lists SERPAPI_KEY as required, but the code optionally reads IMGBB_API_KEY — consider whether that undocumented env var is acceptable in your environment. (3) The script contains a hardcoded public API key for freeimage.host; review whether you want that dependency. (4) If you plan to use this skill in production, inspect the included script yourself, restrict usage to non-sensitive images, or run it in an isolated environment. If you need the skill but want tighter control over uploads, modify the script to disable automatic uploads or to require an explicit opt-in before sending local files off-host.
功能分析
Type: OpenClaw Skill
Name: image-search
Version: 1.0.0
The skill provides reverse image search functionality using Google Lens via SerpAPI. The core logic in `scripts/lens_search.py` is well-structured, uses only the Python standard library, and lacks any signs of obfuscation or malicious intent. It handles local files by uploading them to third-party image hosting services (freeimage.host or imgbb.com), which is a documented and necessary step for the Google Lens API to process the image. The script correctly manages API keys via environment variables (SERPAPI_KEY, IMGBB_API_KEY) and does not attempt to access unauthorized files or exfiltrate sensitive data beyond the provided image.
能力评估
Purpose & Capability
Name/description align with the code and declared requirement (SERPAPI_KEY). The included script calls SerpAPI's Google Lens engine and returns visual matches, products, and provenance as described.
Instruction Scope
SKILL.md and the script instruct the agent to auto-upload local image files to third-party image hosts (default freeimage.host; fallback imgbb.com). That means user images are transmitted to external services (freeimage.host and/or SerpAPI) — a privacy/exfiltration surface that is not obvious from 'identify this image' wording. The README and SKILL.md mention these uploads, but the runtime instructions will perform them automatically for local files.
Install Mechanism
No install spec; this is instruction-only plus an included Python script that uses only the stdlib. Nothing is downloaded at install time, and no extra packages are pulled in.
Credentials
The skill declares only SERPAPI_KEY as required (primary credential), which is appropriate for SerpAPI access. However, the script also optionally reads IMGBB_API_KEY to upload images to imgbb if present; that env var is mentioned in README/SKILL.md but is not listed in the declared requires.env metadata (inconsistency). The script also contains a hardcoded public API key for freeimage.host. You should be aware SERPAPI_KEY grants the skill the ability to make queries (and send image URLs) to SerpAPI; any local file will be uploaded to external hosts if used.
Persistence & Privilege
The skill is not always-on and is user-invocable. It does not request system-wide persistence or modify other skills. Autonomous invocation is allowed by default but is not combined here with broad unexpected privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install image-search - 安装完成后，直接呼叫该 Skill 的名称或使用
/image-search触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release: Google Lens visual search via SerpAPI. Zero Python dependencies.
元数据
常见问题
Image Search 是什么？
Visual image search using Google Lens via SerpAPI. Identify objects, landmarks, products, plants, animals, artwork, logos, or any visual entity from an image... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 529 次。
如何安装 Image Search？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install image-search」即可一键安装，无需额外配置。
Image Search 是免费的吗？
是的，Image Search 完全免费（开源免费），可自由下载、安装和使用。
Image Search 支持哪些平台？
Image Search 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Image Search？
由 TobiasLee（@tobiaslee）开发并维护，当前版本 v1.0.0。
推荐 Skills