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

dovetail-automation skill

safe

/dovetail-automation

This skill automates Dovetail operations via Composio's Rube MCP, always discovering current tool schemas before execution to ensure accurate workflows.

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

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

Files (1)

SKILL.md

2.9 KB

---
name: dovetail-automation
description: "Automate Dovetail tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Dovetail Automation via Rube MCP

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

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

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Dovetail connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `dovetail`
- 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 `dovetail`
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: "Dovetail 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 Dovetail task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["dovetail"]
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 Dovetail-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `dovetail` |
| 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` |

---
*Powered by [Composio](https://composio.dev)*

Overview

This skill automates Dovetail tasks through Composio’s Dovetail toolkit using the Rube MCP. It provides a clear workflow for discovering tools, validating connections, and executing operations reliably. The guidance emphasizes always searching tools first to handle changing schemas and avoid errors.

How this skill works

The skill uses RUBE_SEARCH_TOOLS to discover available Dovetail tool slugs, input schemas, and recommended execution plans. It then verifies an active Dovetail connection via RUBE_MANAGE_CONNECTIONS and runs operations with RUBE_MULTI_EXECUTE_TOOL (including memory and session_id). For bulk or complex runs, it supports RUBE_REMOTE_WORKBENCH and fetching full schemas via RUBE_GET_TOOL_SCHEMAS.

When to use it

Automate ingestion, tagging, or export workflows in Dovetail
Run repeatable analysis or reporting tasks that use Dovetail data
Integrate Dovetail operations into larger agent-driven pipelines
Trigger multi-step processes that require session reuse and pagination handling
Perform bulk operations or remote workbench executions

Best practices

Always call RUBE_SEARCH_TOOLS first to obtain current tool slugs and exact input schemas
Verify the Dovetail connection is ACTIVE with RUBE_MANAGE_CONNECTIONS before executing tools
Pass memory (even empty {}) and a session_id in RUBE_MULTI_EXECUTE_TOOL calls
Use schemaRef or RUBE_GET_TOOL_SCHEMAS when complex inputs are required
Handle pagination tokens on responses and reuse session IDs for a single workflow
Never hardcode field names, types, or tool slugs — rely on the search response

Example use cases

Create and tag large sets of research excerpts in Dovetail using discovered tool schemas
Export project data from Dovetail and push to downstream analytics in a single multi-execute run
Run a nightly workbench job to normalize and bulk-update interview metadata via run_composio_tool()
Build an agent that queries Dovetail for insights, paginates results, and composes summary reports
Onboard a new Dovetail workspace: manage connections, confirm ACTIVE status, and run validation scripts

FAQ

What should I call first when starting a workflow?

Always call RUBE_SEARCH_TOOLS first to retrieve current tool slugs and exact schemas before any execution.

What if the connection shows INACTIVE?

Follow the auth link returned by RUBE_MANAGE_CONNECTIONS to complete the connection flow and confirm ACTIVE status before running tools.