Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Breezy HR Automation via Rube MCP

agent hr skill risk: medium

Breezy HR Automation via Rube MCP

Instructs the model to automate Breezy HR operations through Composio's toolkit via Rube MCP by first calling RUBE_SEARCH_TOOLS, verifying ACTIVE connections with RUBE_MANAGE_CONNE…

  • External action: medium

SKILL 1 file

SKILL.md
---
name: breezy-hr-automation
description: "Automate Breezy HR tasks via Rube MCP (Composio). Always search tools first for current schemas."
---
# Breezy HR Automation via Rube MCP

Automate Breezy HR operations through Composio's Breezy HR toolkit via Rube MCP.

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["breezy_hr"]
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 Breezy HR-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `breezy_hr` |
| 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)*

REQUIRED CONTEXT

  • RUBE_SEARCH_TOOLS availability
  • active breezy_hr connection via RUBE_MANAGE_CONNECTIONS

TOOLS REQUIRED

  • RUBE_SEARCH_TOOLS
  • RUBE_MANAGE_CONNECTIONS
  • RUBE_MULTI_EXECUTE_TOOL
  • RUBE_REMOTE_WORKBENCH
  • RUBE_GET_TOOL_SCHEMAS

ROLES & RULES

  1. Always search tools first for current schemas.
  2. Always call RUBE_SEARCH_TOOLS first to get current tool schemas.
  3. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds.
  4. Call RUBE_MANAGE_CONNECTIONS with toolkit breezy_hr.
  5. If connection is not ACTIVE, follow the returned auth link to complete setup.
  6. Confirm connection status shows ACTIVE before running any workflows.
  7. Always discover available tools before executing workflows.
  8. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS.
  9. Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools.
  10. Use exact field names and types from the search results.
  11. Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
  12. Reuse session IDs within a workflow. Generate new ones for new workflows.
  13. Check responses for pagination tokens and continue fetching until complete.

EXPECTED OUTPUT

Format
markdown
Constraints
  • always search tools first
  • verify active connection before execution
  • reuse session IDs within workflows

SUCCESS CRITERIA

  • Discover tools using RUBE_SEARCH_TOOLS first
  • Verify active Breezy HR connection
  • Execute only with schema-compliant arguments
  • Include memory parameter on every RUBE_MULTI_EXECUTE_TOOL call

FAILURE MODES

  • Hardcoding tool slugs without first calling RUBE_SEARCH_TOOLS
  • Executing tools before connection status is ACTIVE
  • Using field names or types that differ from search results
  • Omitting the memory parameter from RUBE_MULTI_EXECUTE_TOOL

CAVEATS

Dependencies
  • Rube MCP connection (RUBE_SEARCH_TOOLS available)
  • Active Breezy HR connection via RUBE_MANAGE_CONNECTIONS
Missing context
  • Target audience or calling agent type
  • Error handling or retry strategy
Ambiguities
  • Session management mixes 'generate_id: true' and 'id: existing_session_id' without clear transition rules.
  • Does not specify desired output length or response format after tool execution.

QUALITY

OVERALL
0.74
CLARITY
0.78
SPECIFICITY
0.72
REUSABILITY
0.68
COMPLETENESS
0.82

IMPROVEMENT SUGGESTIONS

  • Replace inline placeholders like 'your specific Breezy HR task' with explicit template variables such as {{task_description}}.
  • Add a dedicated error-handling and pagination continuation section.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT