home / skills / composiohq / awesome-claude-skills / share_point-automation

share_point-automation skill

/share_point-automation

This skill automates SharePoint tasks via Rube MCP, discovering tool schemas first and executing workflows across libraries, sites, and lists.

npx playbooks add skill composiohq/awesome-claude-skills --skill share_point-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
4.0 KB
---
name: share_point-automation
description: "Automate SharePoint tasks via Rube MCP (Composio): document libraries, sites, lists, and content management. Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# SharePoint Automation via Rube MCP

Automate SharePoint operations through Composio's SharePoint toolkit via Rube MCP.

**Toolkit docs**: [composio.dev/toolkits/share_point](https://composio.dev/toolkits/share_point)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active SharePoint connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `share_point`
- 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.

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

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS: queries=[{"use_case": "document libraries, sites, lists, and content management", "known_fields": ""}]
```

This returns:
- Available tool slugs for SharePoint
- Recommended execution plan steps
- Known pitfalls and edge cases
- Input schemas for each tool

## Core Workflows

### 1. Discover Available SharePoint Tools

```
RUBE_SEARCH_TOOLS:
  queries:
    - use_case: "list all available SharePoint tools and capabilities"
```

Review the returned tools, their descriptions, and input schemas before proceeding.

### 2. Execute SharePoint 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 SharePoint operations:

1. Search for all relevant tools: `RUBE_SEARCH_TOOLS` with specific use case
2. Execute prerequisite steps first (e.g., fetch before update)
3. Pass data between steps using tool responses
4. Use `RUBE_REMOTE_WORKBENCH` for bulk operations or data processing

## 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 `RUBE_MANAGE_CONNECTIONS` if connection expired

### Batch Operations
For bulk operations, use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` in a loop with `ThreadPoolExecutor` for parallel execution.

## Known Pitfalls

- **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 SharePoint 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 `RUBE_GET_TOOL_SCHEMAS` to load full input schemas when `schemaRef` is returned instead of `input_schema`.

## Quick Reference

| Operation | Approach |
|-----------|----------|
| Find tools | `RUBE_SEARCH_TOOLS` with SharePoint-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `share_point` |
| 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` |

> **Toolkit docs**: [composio.dev/toolkits/share_point](https://composio.dev/toolkits/share_point)

Overview

This skill automates SharePoint tasks using Rube MCP and Composio's share_point toolkit. It provides discovery-first workflows to list and manage sites, document libraries, lists, and content while ensuring connection and schema validity. The approach emphasizes searching tools first to avoid hardcoding and to adapt to changing schemas.

How this skill works

Before running any operation the skill calls RUBE_SEARCH_TOOLS to discover available SharePoint tool slugs, input schemas, and recommended execution plans. It manages SharePoint connections via RUBE_MANAGE_CONNECTIONS, executes operations with RUBE_MULTI_EXECUTE_TOOL, and supports bulk processing through RUBE_REMOTE_WORKBENCH and run_composio_tool(). Error checks, pagination handling, and schema validation are built into common patterns.

When to use it

  • Automate creation, update, or deletion of sites, lists, libraries, or list items
  • Bulk import or export content across SharePoint document libraries
  • Build multi-step workflows that fetch, transform, and write SharePoint data
  • Perform periodic audits or searches for existing resources before changes
  • Parallelize large batch operations with remote workbench and thread pools

Best practices

  • Always run RUBE_SEARCH_TOOLS first to discover current tool slugs and input schemas
  • Verify SharePoint connection status via RUBE_MANAGE_CONNECTIONS and complete auth until ACTIVE
  • Validate and strictly follow returned input_schema or call RUBE_GET_TOOL_SCHEMAS when schemaRef is returned
  • Search for existing resources before creating new ones to prevent duplicates
  • Handle pagination (next_cursor/page_token) and implement retry/backoff for rate limits

Example use cases

  • List all document libraries across a tenant, then export metadata to CSV via RUBE_REMOTE_WORKBENCH
  • Create a site collection, provision lists, and seed default list items using a multi-step RUBE_MULTI_EXECUTE_TOOL plan
  • Find and update document metadata in bulk with run_composio_tool() and parallel execution
  • Automate re-authentication when tokens expire by invoking RUBE_MANAGE_CONNECTIONS and resuming workflows after ACTIVE status
  • Paginate through large lists to compile audit reports and detect missing required metadata

FAQ

What must I do before executing any SharePoint tool?

Always call RUBE_SEARCH_TOOLS to discover current tool slugs and input schemas, and confirm your SharePoint connection is ACTIVE via RUBE_MANAGE_CONNECTIONS.

How do I handle large bulk operations?

Use RUBE_REMOTE_WORKBENCH with run_composio_tool() and a ThreadPoolExecutor for parallelism, and respect rate limits with backoff and retries.