agility-cms-automation
npx machina-cli add skill ComposioHQ/awesome-claude-skills/agility-cms-automation --openclawAgility CMS Automation via Rube MCP
Automate Agility CMS operations through Composio's Agility CMS toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/agility_cms
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Agility CMS connection via
RUBE_MANAGE_CONNECTIONSwith toolkitagility_cms - Always call
RUBE_SEARCH_TOOLSfirst 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.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitagility_cms - If connection is not ACTIVE, follow the returned auth link to complete setup
- Confirm connection status shows ACTIVE before running any workflows
Tool Discovery
Always discover available tools before executing workflows:
RUBE_SEARCH_TOOLS
queries: [{use_case: "Agility CMS 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 Agility CMS task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["agility_cms"]
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_CONNECTIONSshows ACTIVE status before executing tools - Schema compliance: Use exact field names and types from the search results
- Memory parameter: Always include
memoryinRUBE_MULTI_EXECUTE_TOOLcalls, 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 Agility CMS-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit agility_cms |
| 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
Source
git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/agility-cms-automation/SKILL.mdView on GitHub Overview
This skill automates Agility CMS operations by discovering current tool schemas via Rube MCP and then executing the appropriate tools through Composio’s agility_cms toolkit. It emphasizes always querying tool schemas first to avoid drift and ensure compatibility with the latest capabilities.
How This Skill Works
Connect to Rube MCP, verify the Agility CMS connection, and use RUBE_SEARCH_TOOLS to fetch current tool schemas. Select a tool slug from the search results, then run RUBE_MULTI_EXECUTE_TOOL with the discovered tool and its required arguments, including memory (even if empty). Reuse sessions to maintain continuity across steps and ensure the connection remains ACTIVE before execution.
When to Use It
- When you need to perform a specific Agility CMS operation discovered via RUBE_SEARCH_TOOLS (no hardcoding of tool slugs).
- When setting up or verifying the Agility CMS connection via RUBE_MANAGE_CONNECTIONS before running workflows.
- When you must always fetch up-to-date tool schemas prior to any workflow to avoid schema drift.
- When executing tools that require arguments derived from current schemas (tool_slug and exact field names from search results).
- When orchestrating multi-step workflows that reuse a session_id and include a memory parameter for RUBE_MULTI_EXECUTE_TOOL.
Quick Start
- Step 1: Verify Rube MCP is available with RUBE_SEARCH_TOOLS and fetch Agility CMS tool schemas.
- Step 2: Ensure the Agility CMS connection is ACTIVE via RUBE_MANAGE_CONNECTIONS.
- Step 3: Execute a discovered tool with RUBE_MULTI_EXECUTE_TOOL using the tool_slug and arguments from the search results (include memory: {}).
Best Practices
- Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas.
- Verify the connection status is ACTIVE via RUBE_MANAGE_CONNECTIONS before executing tools.
- Use exact field names and types from the search results; do not hardcode slugs or arguments.
- Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
- Reuse session IDs across steps to maintain workflow continuity and manage pagination if present.
Example Use Cases
- Discover a publish/edit workflow with RUBE_SEARCH_TOOLS and execute the chosen publish tool using arguments from the search results.
- Connect to Agility CMS, fetch a list of available tools, and run a bulk update tool for multiple content items using a single session.
- Validate a new field schema by retrieving the schema via search results, then running the corresponding update tool with exact field names.
- Complete a multi-step editorial workflow by reusing a session_id across discovery, connection check, and execution steps.
- Handle pagination in tool responses by continuing to fetch until completion and then executing the final tool with the accumulated results.
