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

capsule_crm-automation skill

/capsule_crm-automation

This skill automates Capsule CRM tasks via Rube MCP, discovering current tool schemas before execution to ensure accurate, compliant operations.

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

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

Files (1)
SKILL.md
4.1 KB
---
name: capsule_crm-automation
description: "Automate Capsule CRM tasks via Rube MCP (Composio): contacts, opportunities, cases, tasks, and pipeline management. Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Capsule CRM Automation via Rube MCP

Automate Capsule CRM operations through Composio's Capsule CRM toolkit via Rube MCP.

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

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Capsule CRM connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `capsule_crm`
- 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 `capsule_crm`
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": "contacts, opportunities, cases, tasks, and pipeline management", "known_fields": ""}]
```

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

## Core Workflows

### 1. Discover Available Capsule CRM Tools

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

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

### 2. Execute Capsule CRM 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 Capsule CRM 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 Capsule CRM 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 Capsule CRM-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `capsule_crm` |
| 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/capsule_crm](https://composio.dev/toolkits/capsule_crm)

Overview

This skill automates Capsule CRM tasks using Rube MCP (Composio) to manage contacts, opportunities, cases, tasks, and pipelines. It guides tool discovery, connection management, and execution patterns so agents can run single-step or multi-step CRM workflows reliably. Always search available tools first to get current schemas and avoid hardcoding tool slugs.

How this skill works

The skill uses RUBE_SEARCH_TOOLS to discover current Capsule CRM tool slugs, capabilities, and input schemas before any action. After discovery, it runs operations via RUBE_MULTI_EXECUTE_TOOL and coordinates multi-step flows by passing responses between steps or using RUBE_REMOTE_WORKBENCH for bulk work. Connection state is verified through RUBE_MANAGE_CONNECTIONS and re-authenticated when needed.

When to use it

  • Automate contact creation, updates, and deduplication in Capsule CRM
  • Synchronize opportunities, pipeline stages, and forecast data across systems
  • Process cases and tasks programmatically or run recurring cleanup jobs
  • Run bulk imports, exports, or parallel updates using the remote workbench
  • Build multi-step workflows that fetch, transform, and persist CRM data

Best practices

  • Always call RUBE_SEARCH_TOOLS first to get live tool slugs and input schemas
  • Verify Capsule CRM connection is ACTIVE via RUBE_MANAGE_CONNECTIONS before executing tools
  • Search for existing resources before creating new ones to avoid duplicates
  • Use pagination tokens (next_cursor/page_token) to fully retrieve lists
  • Validate inputs against returned schemas or call RUBE_GET_TOOL_SCHEMAS when schemaRef is provided
  • Implement retry/backoff and check rate-limit responses; parallelize bulk work via ThreadPoolExecutor in RUBE_REMOTE_WORKBENCH

Example use cases

  • Create or update contacts after importing leads; search first to dedupe
  • Advance multiple opportunities through pipeline stages based on external triggers
  • Bulk-close completed tasks and generate summary reports via remote workbench
  • Fetch case details, attach notes, and assign follow-up tasks in a multi-step flow
  • Run scheduled syncs between Capsule CRM and another sales system, handling pagination and rate limits

FAQ

What is the first API call I should make?

Always run RUBE_SEARCH_TOOLS with a Capsule CRM use case to discover available tool slugs and input schemas before any execution.

How do I handle expired connections?

Call RUBE_MANAGE_CONNECTIONS to check status; follow the returned auth link if not ACTIVE and confirm ACTIVE before proceeding.

Can I run bulk operations safely?

Yes—use RUBE_REMOTE_WORKBENCH and run_composio_tool() for bulk tasks. Parallelize carefully and respect rate limits with retries and backoff.