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

recallai-automation skill

safe

/recallai-automation

This skill automates Recallai tasks via Composio's MCP, always discovering tool schemas first for up-to-date workflows.

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

# Recallai Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["recallai"]
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 Recallai-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `recallai` |
| 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 Recallai tasks through Composio’s Recallai toolkit using Rube MCP. It provides a reproducible workflow for discovering tools, validating connections, and executing operations safely. The skill emphasizes schema-driven calls so workflows remain resilient to changing tool definitions.

How this skill works

The skill always starts by calling RUBE_SEARCH_TOOLS to fetch current tool slugs, input schemas, and execution guidance. It then validates the Recallai connection via RUBE_MANAGE_CONNECTIONS and executes one or more tools with RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH, passing schema-compliant arguments and a memory object. Session IDs are reused for related runs and pagination is handled when search responses return tokens.

When to use it

Automate Recallai CRUD operations at scale
Build reproducible Recallai workflows that must adapt to changing tool schemas
Run bulk jobs or pipelines that call multiple Recallai tools
Integrate Recallai actions into broader agent-driven automation
Validate and manage Recallai connections programmatically

Best practices

Always call RUBE_SEARCH_TOOLS first — never hardcode tool slugs or input shapes
Check RUBE_MANAGE_CONNECTIONS and ensure the toolkit status is ACTIVE before execution
Pass the exact field names and types returned by the tool schema; use RUBE_GET_TOOL_SCHEMAS when needed
Include a memory object (even {}) with RUBE_MULTI_EXECUTE_TOOL calls
Reuse session IDs within a single workflow; generate new sessions for separate workflows
Handle pagination tokens from search results to ensure you discover all relevant tools

Example use cases

Discovery: fetch Recallai tool catalog and generate a dynamic UI for available operations
One-shot task: run a single Recallai tool for data retrieval or update after verifying connection
Batch pipeline: orchestrate multiple Recallai tools with RUBE_MULTI_EXECUTE_TOOL for ETL-style processing
Connection onboarding: programmatically establish and validate a Recallai connection during setup flows
Full audit: use RUBE_GET_TOOL_SCHEMAS and search results to log schema changes over time

FAQ

Do I need API keys to use Rube MCP?

No. Add https://rube.app/mcp as an MCP server in your client configuration; the MCP endpoint works without separate API keys.

What if a tool schema changes during execution?

Always call RUBE_SEARCH_TOOLS before executing. If a schema changes mid-workflow, re-run the search and adapt arguments to the new schema before calling execute.

Is memory required when executing tools?

Yes. Include a memory parameter in RUBE_MULTI_EXECUTE_TOOL calls; use an empty object ({}) when no memory is needed.