pdf-co-automation

通过 Rube MCP 自动处理 PDF 任务，如转换、提取、合并与数据整理。

来源

GitHub

更新于

2026-06-07

// 安全评估低风险

仅提示词，不执行代码
开源可审计

正在进行安全审计…

凭证密钥
网络外发
代码执行
数据访问
来源供应链

// 安装

复制安装指令，让 AI 自动完成配置 · 推荐新手

请帮我安装 askskill 上的 "pdf-co-automation" 技能：
1. 下载 https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/pdf-co-automation/SKILL.md
2. 保存为 ~/.claude/skills/pdf-co-automation/SKILL.md
3. 装好后重载技能，告诉我可以用了

// 下载

下载 SKILL.md机读安装清单 ↗

// 用法示例

批量提取发票数据

输入

使用 pdf-co-automation 处理这个发票文件夹。先搜索可用工具及当前 schema，再批量提取每份 PDF 中的发票号、日期、供应商名称、税额和总金额，输出为结构化表格。

预期产出

返回按字段整理的表格或 JSON，可直接用于对账或导入系统。

合并并压缩合同文件

输入

用 pdf-co-automation 将这批合同 PDF 按文件名顺序合并为一个文件，并在保证清晰可读的前提下压缩体积。开始前先搜索工具确认支持的参数和 schema。

预期产出

生成一个已合并且压缩后的 PDF 文件，并说明处理结果。

PDF 转 Excel 表格

输入

使用 pdf-co-automation 把这份包含表格的 PDF 转成 Excel。先搜索当前可用工具和 schema，再尽量保留原始列结构、表头和分页信息。

预期产出

输出可编辑的 Excel 文件，表格结构尽量接近原始 PDF。

// 文档

PDF co Automation via Rube MCP

Automate PDF co operations through Composio's PDF co toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/pdf_co

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active PDF co connection via RUBE_MANAGE_CONNECTIONS with toolkit pdf_co
Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit pdf_co
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "PDF co operations", known_fields: ""}]
session: {generate_id: true}

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

Core Workflow Pattern

Step 1: Discover Available Tools

RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific PDF co task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["pdf_co"]
session_id: "your_session_id"

Step 3: Execute Tools

RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"

Known Pitfalls

Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
Pagination: Check responses for pagination tokens and continue fetching until complete

Quick Reference

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with PDF co-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `pdf_co`
Execute	`RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs
Bulk ops	`RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`
Full schema	`RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef`