技能 google-image-api-skill
🖼️

google-image-api-skill

低风险 ⚡ 包含脚本🌐 网络访问🔑 环境变量

Extract Google Images data with country and language filtering

Manual image research is slow and inconsistent. This skill automates Google Images data extraction with structured metadata including titles, thumbnails, source logos, and click-through URLs, filtered by country and language.

支持: Claude Codex Code(CC)
📊 69 充足
1

下载技能 ZIP

2

在 Claude 中上传

前往 设置 → 功能 → 技能 → 上传技能

3

开启并开始使用

测试它

正在使用“google-image-api-skill”。 Search for 'electric vehicles' in Japan and show me the top 20 results

预期结果:

Found 20 image results for 'electric vehicles' in Japan (country: jp, language: ja):

1. Tesla Model 3 Charging - thumbnail available, source: tesla.com
2. BYD Electric SUV - thumbnail available, source: byd.com
3. Nissan Leaf 2024 - thumbnail available, source: nissan.co.jp

Total results: 20 | Products detected: 12 | Click-through links: Available

正在使用“google-image-api-skill”。 Extract competitor product images for 'running shoes' from US and UK markets

预期结果:

Extracted competitor visual data for 'running shoes':

US Market (country: us):
- Nike Air Zoom (product listing detected)
- Adidas Ultraboost (product listing detected)
- New Balance Fresh Foam

UK Market (country: gb):
- Nike Air Max (product listing detected)
- Asics Gel-Kayano
- Under Armour HOVR

Total competitors tracked: 6 | Product listings: 4

安全审计

低风险
v1 • 4/28/2026

Static analysis flagged 76 potential issues, but after semantic evaluation, all are false positives. The skill makes legitimate API calls to BrowserAct (api.browseract.com) to extract Google Images data. Environment access (BROWSERACT_API_KEY) is for authentication only, not exfiltration. External command detections in SKILL.md are markdown formatting syntax, not actual shell execution. No malicious intent detected.

2
已扫描文件
213
分析行数
7
发现项
1
审计总数

高风险问题 (1)

Environment Variable Access Pattern
The skill reads BROWSERACT_API_KEY from environment. This is legitimate credential handling for API authentication - the key is only used to authenticate with BrowserAct service, not exfiltrated.
中风险问题 (2)
Documentation Contains Command Examples
SKILL.md contains bash command examples with backtick syntax for formatting. The static analyzer detects backticks as shell execution patterns, but these are markdown formatting, not actual code execution.
Network Requests to External API
The skill makes HTTP requests to api.browseract.com. This is legitimate API integration for Google Images data extraction - the network access is necessary for the skill's core functionality.
低风险问题 (1)
Hardcoded API URLs
The script contains hardcoded API base URL and workflow template ID. These are configuration constants for the BrowserAct service, not sensitive credentials.
审计者: claude

质量评分

45
架构
100
可维护性
87
内容
50
社区
68
安全
83
规范符合性

你能构建什么

Market research and competitor analysis

Extract product images and visual trends from different countries to understand how competitors appear in local markets.

Visual content sourcing for creative teams

Find and gather images for specific keywords across multiple regions to support design and content creation workflows.

SEO keyword visualization tracking

Check what images rank for target keywords in different countries to inform SEO and content strategy.

试试这些提示

Basic image search
Search Google Images for [keyword] and give me the results with titles and source links
Localized search by country
Find images for [keyword] in Japan (country: jp) and show me the results in Japanese
Competitor visual monitoring
Extract image data for [brand name] products from US and UK markets. I want to see thumbnails, titles, and click-through links for product listings.
Bulk visual research
Search for [topic] images across US, Germany, France, and Japan. Return structured data with thumbnails, titles, and source logos. Extract up to 50 results per country.

最佳实践

  • Set BROWSERACT_API_KEY as an environment variable before running the skill
  • Start with default parameters (5 scrolls, 50 results) before adjusting for larger datasets
  • Check for 'Invalid authorization' errors first - they indicate expired or invalid API keys

避免

  • Do not run multiple image extraction tasks simultaneously - the script polls for completion and may conflict
  • Do not ignore timeout errors - if the task takes longer than 5 minutes, check your BrowserAct dashboard
  • Do not skip API key validation - the skill will fail silently without proper authentication

常见问题

How do I get a BrowserAct API key?
Go to https://www.browseract.com/reception/integrations and copy your API key. Set it as the BROWSERACT_API_KEY environment variable before running the skill.
Why is the task taking so long?
The script uses automated browser operations which can take several minutes. The script will continuously output status logs like '[14:30:05] Task Status: running' while executing.
What countries are supported?
Supported country codes include us, gb, ca, au, de, fr, es, jp, and kr. Use the country parameter to filter results by region.
What languages are supported?
Supported languages include en (English), zh-CN (Simplified Chinese), zh-TW (Traditional Chinese), ja (Japanese), ko (Korean), fr (French), de (German), and es (Spanish).
What data does the extraction return?
Results include is_product flag, click-through link, title, source_logo URL, source site name, thumbnail URL, related_content_id, and result index.
How do I handle API key errors?
If you see 'Invalid authorization' in the output, do not retry. Instead, guide the user to check their BrowserAct API key at https://www.browseract.com/reception/integrations.