Web fetch Google search — 网页 fetch Google 搜索

网页fetch Google Overview

This 技能 enables you to fetch content from Google 搜索 结果s based on a 查询.

Structuring This 技能

[TODO: Choose the structure that best fits this 技能's purpose. Common patterns:

• 工作流-Based (best for sequential processes)

Works well when there are clear step-by-step procedures Example: DOCX 技能 with "工作流 Decision Tree" -> "Reading" -> "Creating" -> "Editing" Structure: ## Overview -> ## 工作流 Decision Tree -> ## Step 1 -> ## Step 2...

• Task-Based (best for 工具 collections)

Works well when the 技能 offers different operations/capabilities Example: PDF 技能 with "Quick 启动" -> "Merge PDFs" -> "Split PDFs" -> "提取 Text" Structure: ## Overview -> ## Quick 启动 -> ## Task Category 1 -> ## Task Category 2...

• Reference/图形界面delines (best for standards or specifications)

Works well for brand 图形界面delines, coding standards, or requirements Example: Brand styling with "Brand 图形界面delines" -> "Colors" -> "Typography" -> "Features" Structure: ## Overview -> ## 图形界面delines -> ## Specifications -> ## Usage...

• Capabilities-Based (best for integrated 系统s)

Works well when the 技能 provides multiple interrelated features Example: Product Management with "Core Capabilities" -> numbered capability 列出 Structure: ## Overview -> ## Core Capabilities -> ### 1. Feature -> ### 2. Feature...

Patterns can be mixed and matched as needed. Most 技能s combine patterns (e.g., 启动 with task-based, 添加 工作流 for complex operations).

删除 this entire "Structuring This 技能" section when done - it's just 图形界面dance.]

Usage

To use this 技能, provide a 搜索 查询. The 技能 will 执行 the scripts/网页_搜索.py script with the 查询, which uses the 网页_搜索 工具 to fetch Google 搜索 结果s and return the content.

Example:

User: Fetch Google 搜索 结果s for 'OpenClaw 技能s'

The 技能 will then 执行 the script and fetch the 结果s.

Resources (optional)

创建 only the resource directories this 技能 actually needs. 删除 this section if no resources are required.

scripts/

Executable code (Python/Bash/etc.) that can be 运行 directly to perform specific operations.

Examples from other 技能s:

PDF 技能: fill_fillable_fields.py, 提取_form_field_信息.py - utilities for PDF manipulation DOCX 技能: document.py, utilities.py - Python 模块s for document processing

应用ropriate for: Python scripts, shell scripts, or any executable code that performs 自动化, data processing, or specific operations.

Note: Scripts may be 执行d without loading into 上下文, but can still be read by Codex for 补丁ing or 环境 adjustments.

references/

Documentation and reference material intended to be loaded into 上下文 to 信息rm Codex's process and thinking.

Examples from other 技能s:

Product management: communication.md, 上下文_building.md - detAIled 工作流 图形界面des Big查询: API reference documentation and 查询 examples Finance: 模式 documentation, company policies

应用ropriate for: In-depth documentation, API references, database 模式s, comprehensive 图形界面des, or any detAIled in格式化ion that Codex should reference while working.

as设置s/

Files not intended to be loaded into 上下文, but rather used within the 输出 Codex produces.

Examples from other 技能s:

Brand styling: PowerPoint template files (.pptx), 记录o files Frontend 构建器: HTML/React boilerplate project directories Typography: Font files (.ttf, .woff2)

应用ropriate for: Templates, boilerplate code, document templates, images, icons, fonts, or any files meant to be copied or used in the final 输出.

Not every 技能 requires all three types of resources.