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

workable-automation skill

safe

/workable-automation

This skill helps you automate Workable operations via Rube MCP by discovering tools before execution and ensuring active connections.

npx playbooks add skill composiohq/awesome-claude-skills --skill workable-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: workable-automation
description: "Automate Workable tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Workable Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["workable"]
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 Workable-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `workable` |
| 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 Workable operations through Composio’s Workable toolkit using Rube MCP. It provides a repeatable pattern to discover tools, verify connections, and execute Workable actions while enforcing schema compliance and session management. The goal is reliable, auditable automation for recruiting workflows and bulk operations.

How this skill works

Always start by calling RUBE_SEARCH_TOOLS to fetch current tool slugs, input schemas, and recommended execution plans. Verify the Workable connection with RUBE_MANAGE_CONNECTIONS and ensure status is ACTIVE. Execute one or more discovered tools via RUBE_MULTI_EXECUTE_TOOL (including a memory object and session ID) or use RUBE_REMOTE_WORKBENCH for bulk runs; follow schema fields exactly and handle pagination and session reuse.

When to use it

Automating candidate creation, update, or job-posting tasks in Workable
Running bulk operations or scripted recruiting workflows against Workable
Integrating Workable actions into multi-tool agent workflows with Composio
When you need repeatable, schema-driven automation with connection checks
When tool schemas may change and you must always discover live schemas first

Best practices

Always call RUBE_SEARCH_TOOLS first to get live tool slugs and input schemas; never hardcode fields
Confirm RUBE_MANAGE_CONNECTIONS shows the workable toolkit connection as ACTIVE before executing
Include a memory object (even empty {}) in RUBE_MULTI_EXECUTE_TOOL calls and reuse session IDs inside a workflow
Follow exact field names and types returned by the search response to avoid schema errors
Check for pagination tokens in responses and iterate until all data is retrieved
Generate new sessions for distinct workflows and reuse sessions for steps within the same workflow

Example use cases

Discover the current Workable API actions, then create a batch of candidate records using RUBE_MULTI_EXECUTE_TOOL
Verify the Workable connection and run a job posting workflow that creates and publishes a job via discovered tool slugs
Run periodic syncs: search tools, fetch job listings with pagination, and update local ATS records
Execute a multi-step hiring pipeline: create candidate, attach resume, schedule interview using the toolkit's stepwise tools
Run large bulk updates from a spreadsheet via RUBE_REMOTE_WORKBENCH and composio run_composio_tool() calls

FAQ

What is the first call I must make before executing any Workable action?

Always call RUBE_SEARCH_TOOLS to retrieve current tool slugs, input schemas, and recommended plans; tool schemas can change.

What if the Workable connection is not active?

Call RUBE_MANAGE_CONNECTIONS with toolkit 'workable', follow the returned auth link to complete setup, then confirm status is ACTIVE before running tools.