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

apiflash-automation skill

/apiflash-automation

This skill automates Apiflash tasks via Rube MCP, continuously discovering current tool schemas and ensuring active connections before execution.

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

# Apiflash Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["apiflash"]
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 Apiflash-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `apiflash` |
| 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 Apiflash browser capture tasks through Composio’s Apiflash toolkit using the Rube MCP orchestration layer. It guides discovery, connection management, and tool execution so you can run schema-compliant Apiflash operations reliably. Use it to integrate Apiflash screenshots and rendering into larger automated workflows.

How this skill works

The skill first queries Rube MCP for available Apiflash tool schemas via RUBE_SEARCH_TOOLS to fetch current tool slugs, inputs, and execution recommendations. It then verifies or establishes an Apiflash connection with RUBE_MANAGE_CONNECTIONS and runs selected tools using RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk jobs), always passing a session_id and memory object. It enforces schema compliance and session reuse to prevent runtime errors.

When to use it

  • Automate website screenshot capture and rendering at scale
  • Integrate Apiflash output into CI/CD or reporting pipelines
  • Run bulk site captures or scheduled screenshot jobs
  • Prototype workflows that combine Apiflash with other Composio toolkits
  • When you need up-to-date tool schemas before executing any Apiflash operation

Best practices

  • Always call RUBE_SEARCH_TOOLS first — tool slugs and schemas change frequently
  • Verify connection status with RUBE_MANAGE_CONNECTIONS and ensure it is ACTIVE before execution
  • Supply exact field names and types from the returned schema — avoid hardcoded arguments
  • Include memory in RUBE_MULTI_EXECUTE_TOOL calls even if empty ({}), and reuse session_id within a workflow
  • Handle pagination tokens in search and result responses to fetch complete data

Example use cases

  • Capture homepage screenshots for visual regression testing across deployments
  • Generate thumbnail images of user-submitted URLs for a content platform
  • Run nightly bulk captures of a site cluster and store results in cloud storage
  • Embed Apiflash rendering into automated QA reports with step-level screenshots
  • Create a serverless job that takes URL lists and returns screen capture artifacts

FAQ

Do I need API keys to use Rube MCP?

No API keys are required to add the Rube MCP endpoint; add https://rube.app/mcp as an MCP server in your client configuration.

What if RUBE_SEARCH_TOOLS returns a different schema than expected?

Treat the returned schema as authoritative: update arguments to match exact field names/types and repeat RUBE_SEARCH_TOOLS before each workflow if needed.

Can I run bulk operations?

Yes. Use RUBE_REMOTE_WORKBENCH and run_composio_tool() for bulk or parallelized Apiflash runs, following the search-and-verify pattern.