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

perigon-automation skill

safe

/perigon-automation

This skill automates Perigon tasks via Rube MCP, prioritizing tool discovery and schema freshness to ensure accurate workflow execution.

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

# Perigon Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["perigon"]
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 Perigon-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `perigon` |
| 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 Perigon tasks through Composio's Perigon toolkit via the Rube MCP interface. It provides a safe, repeatable pattern: discover tools, verify Perigon connection, and execute schema-compliant operations with RUBE_MULTI_EXECUTE_TOOL. Follow the built-in checks to avoid schema drift and failed runs.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to discover current tool slugs and input schemas for the requested Perigon use case. It then validates the Perigon connection using RUBE_MANAGE_CONNECTIONS and executes one or more tools with RUBE_MULTI_EXECUTE_TOOL, always supplying memory and a session_id. For bulk or scripted flows, it can orchestrate remote workbench runs and fetch full schemas via RUBE_GET_TOOL_SCHEMAS.

When to use it

Automating Perigon workflows that require live tool schemas
Running multi-step Perigon operations that must reuse a session_id
Executing bulk operations through Composio tools via Rube MCP
Building reproducible automation scripts that must handle schema changes
Situations where connection status must be validated before executing actions

Best practices

Always call RUBE_SEARCH_TOOLS first — do not hardcode tool slugs or argument shapes
Verify Perigon connection with RUBE_MANAGE_CONNECTIONS and ensure status is ACTIVE
Use exact field names and types from returned schemas to avoid validation errors
Include a memory object in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
Reuse session_ids within the same workflow; create a new session_id for new workflows
Check pagination tokens on search responses and fetch until complete

Example use cases

Query available Perigon ingestion tools, then run a chosen ingestion workflow with RUBE_MULTI_EXECUTE_TOOL
Validate and renew a Perigon connection before running scheduled data syncs
Run a multi-tool orchestration: search tools, get schemas, execute parsing then enrichment tools in one session
Perform bulk transformations using RUBE_REMOTE_WORKBENCH and run_composio_tool() for large datasets
Fetch full schemas with RUBE_GET_TOOL_SCHEMAS before generating typed arguments programmatically

FAQ

Do I need API keys to use Rube MCP?

No. Add https://rube.app/mcp as an MCP server in your client configuration; no API keys are required for the MCP endpoint.

What if tool schemas change mid-workflow?

Always call RUBE_SEARCH_TOOLS before execution to get current schemas; if a schema changed, adapt arguments and rerun the search for accurate fields and types.