taggun-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/taggun-automation --openclawTaggun Automation via Rube MCP
Automate Taggun operations through Composio's Taggun toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/taggun
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Taggun connection via
RUBE_MANAGE_CONNECTIONSwith toolkittaggun - 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 toolkittaggun - 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: "Taggun 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 Taggun task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["taggun"]
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 Taggun-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit taggun |
| 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/taggun-automation/SKILL.mdView on GitHub Overview
This skill automates Taggun operations through Composio's Taggun toolkit via Rube MCP. It emphasizes discovering current tool schemas before execution and maintaining an ACTIVE connection to Taggun. It guides setup, discovery, and execution of Taggun workflows using live schemas.
How This Skill Works
Connect to the Rube MCP endpoint (https://rube.app/mcp) as an MCP server, verify RUBE_SEARCH_TOOLS, and manage the Taggun connection with the taggun toolkit. Discover available tools first, ensure the connection is ACTIVE, and execute selected tools with RUBE_MULTI_EXECUTE_TOOL, supplying memory and the session_id as required by the discovered schemas.
When to Use It
- Automating recurring Taggun tasks without hardcoding tool details
- When tool schemas may change and you must fetch them first
- Before executing to verify the Taggun connection is ACTIVE
- For multi-step Taggun workflows that reuse a session across steps
- When processing large result sets and handling pagination in tool responses
Quick Start
- Step 1: Add RUBE MCP endpoint (https://rube.app/mcp) as an MCP server in your client.
- Step 2: Run RUBE_SEARCH_TOOLS with use_case: "Taggun operations" to fetch current tool schemas.
- Step 3: Run RUBE_MANAGE_CONNECTIONS for toolkit "taggun", then execute tools via RUBE_MULTI_EXECUTE_TOOL using the discovered tool slug and memory/session_id from the results.
Best Practices
- Always call RUBE_SEARCH_TOOLS first to obtain current tool schemas
- Verify RUBE_MANAGE_CONNECTIONS shows an ACTIVE status before executing tools
- Use exact field names and types from the search results; avoid hardcoding
- Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty
- Reuse session IDs within a single workflow and regenerate for new runs; monitor pagination
Example Use Cases
- Example 1: Discover a tool via RUBE_SEARCH_TOOLS for an invoice OCR task and run TOOL_SLUG_FROM_SEARCH with the required args.
- Example 2: Retrieve customer data from a receipt by executing TOOL_SLUG_FROM_SEARCH with discovery-provided arguments.
- Example 3: Validate document authenticity by executing a discovered tool slug with appropriate metadata fields.
- Example 4: Process a batch of documents by reusing a session ID and iterating TOOL_SLUG_FROM_SEARCH across items.
- Example 5: Handle large results by implementing pagination tokens in successive TOOL executions until completion.
