Awesome-claude-skills-cn google_search_console-automation
通过 Rube MCP(Composio)自动化 Google Search Console 任务:搜索效果、URL 检查、站点地图和索引状态。始终先搜索工具以获取当前架构。
install
source · Clone the upstream repo
git clone https://github.com/Athe1st3154/awesome-claude-skills-cn
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/Athe1st3154/awesome-claude-skills-cn "$T" && mkdir -p ~/.claude/skills && cp -r "$T/composio-skills/google_search_console-automation" ~/.claude/skills/athe1st3154-awesome-claude-skills-cn-google-search-console-automation-e6ee9d && rm -rf "$T"
manifest:
composio-skills/google_search_console-automation/SKILL.mdsource content
Google Search Console Automation via Rube MCP
Automate Google Search Console operations through Composio's Google Search Console toolkit via Rube MCP.
工具包文档: composio.dev/toolkits/google_search_console
前提条件
- Rube MCP 必须已连接(RUBE_SEARCH_TOOLS 可用)
- 通过
与工具包RUBE_MANAGE_CONNECTIONS
建立活动 Google Search Console 连接google_search_console - 始终首先调用
获取当前工具架构RUBE_SEARCH_TOOLS
设置
获取 Rube MCP: 在客户端配置中添加
https://rube.app/mcp 作为 MCP 服务器。 无需 API 密钥 — 只需添加端点即可使用。
- 通过确认
响应来验证 Rube MCP 可用RUBE_SEARCH_TOOLS - 使用工具包
调用google_search_consoleRUBE_MANAGE_CONNECTIONS - 如果连接不是 ACTIVE 状态,按照返回的授权链接完成设置
- 在运行任何工作流程前确认连接状态显示为 ACTIVE
工具发现
在执行工作流程前始终发现可用工具:
RUBE_SEARCH_TOOLS: queries=[{"use_case": "search performance, URL inspection, sitemaps, and indexing status", "known_fields": ""}]
This returns:
- Available tool slugs for Google Search Console
- Recommended execution plan steps
- Known pitfalls and edge cases
- Input schemas for each tool
Core Workflows
1. Discover Available Google Search Console Tools
RUBE_SEARCH_TOOLS: queries: - use_case: "list all available Google Search Console tools and capabilities"
Review the returned tools, their descriptions, and input schemas before proceeding.
2. Execute Google Search Console Operations
After discovering tools, execute them via:
RUBE_MULTI_EXECUTE_TOOL: tools: - tool_slug: "<discovered_tool_slug>" arguments: {<schema-compliant arguments>} memory: {} sync_response_to_workbench: false
3. Multi-Step Workflows
For complex workflows involving multiple Google Search Console operations:
- Search for all relevant tools:
with specific use caseRUBE_SEARCH_TOOLS - Execute prerequisite steps first (e.g., fetch before update)
- Pass data between steps using tool responses
- Use
for bulk operations or data processingRUBE_REMOTE_WORKBENCH
Common Patterns
Search Before Action
Always search for existing resources before creating new ones to avoid duplicates.
Pagination
Many list operations support pagination. Check responses for
next_cursor or page_token and continue fetching until exhausted.
Error Handling
- Check tool responses for errors before proceeding
- If a tool fails, verify the connection is still ACTIVE
- Re-authenticate via
if connection expiredRUBE_MANAGE_CONNECTIONS
Batch Operations
For bulk operations, use
RUBE_REMOTE_WORKBENCH 使用 run_composio_tool() in a loop with ThreadPoolExecutor for parallel execution.
已知陷阱
- Always search tools first: Tool schemas and available operations may change. Never hardcode tool slugs without first discovering them via
.RUBE_SEARCH_TOOLS - Check connection status: Ensure the Google Search Console connection is ACTIVE before executing any tools. Expired OAuth tokens require re-authentication.
- Respect rate limits: If you receive rate limit errors, reduce request frequency and implement backoff.
- Validate schemas: Always pass strictly schema-compliant arguments. Use
to load full input schemas whenRUBE_GET_TOOL_SCHEMAS
is returned instead ofschemaRef
.input_schema
快速参考
| 操作 | 方法 |
|---|---|
| 查找工具 | with Google Search Console-specific use case |
| 连接 | 使用工具包 |
| 执行 | 使用发现的工具标识符 |
| 批量操作 | 使用 |
| 完整架构 | 用于具有 的工具 |