tally-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/tally-automation --openclawTally Automation via Rube MCP
Automate Tally operations through Composio's Tally toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/tally
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Tally connection via
RUBE_MANAGE_CONNECTIONSwith toolkittally - 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 toolkittally - 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: "Tally 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 Tally task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["tally"]
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 Tally-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit tally |
| 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/tally-automation/SKILL.mdView on GitHub Overview
This skill automates tally operations through Composio's Tally toolkit via Rube MCP. It emphasizes always discovering current tool schemas with RUBE_SEARCH_TOOLS to avoid stale tool slugs or args. By coordinating discovery, connection status, and multi tool execution, it enables repeatable tally workflows.
How This Skill Works
Technically, you first run RUBE_SEARCH_TOOLS to fetch up-to-date tally tool schemas, then verify the Rube MCP connection with RUBE_MANAGE_CONNECTIONS. Once a tool slug is chosen, execute it using RUBE_MULTI_EXECUTE_TOOL and pass the schema-compliant arguments, always including a memory object and the active session_id. This pattern ensures you are running current tools in a valid session with proper connection status before any workflow.
When to Use It
- Automating recurring tally operations while ensuring the latest tool schemas are used by always calling RUBE_SEARCH_TOOLS first.
- When establishing or revalidating a Rube MCP connection for the tally toolkit before running any workflow.
- When you need to discover available tools and their input schemas for a specific tally task, such as invoice creation or report generation.
- For bulk or chained tally tasks, using RUBE_MULTI_EXECUTE_TOOL in a single session with a known sequence.
- When tool slugs or required fields may change, requiring you to re-fetch schemas rather than hardcoding values.
Quick Start
- Step 1: Ensure Rube MCP is configured and RUBE_SEARCH_TOOLS responds.
- Step 2: Discover tally tools with RUBE_SEARCH_TOOLS using a tally use_case to get tool slugs and input schemas.
- Step 3: Check the tally connection with RUBE_MANAGE_CONNECTIONS and run a chosen tool via RUBE_MULTI_EXECUTE_TOOL using memory: {} and a session_id.
Best Practices
- Always search first to get current tool schemas.
- Check the connection status and ensure it is ACTIVE before executing tools.
- Use exact field names and types from the search results; avoid hardcoding.
- Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
- Reuse session IDs within a workflow and create a new session only for new workflows.
Example Use Cases
- Find tools for a Create Invoice tally task, connect to tally, and execute with arguments from the schema.
- Automate a recurring tally report by discovering the relevant tool, reusing the session_id, and executing with generated arguments.
- Perform bulk tally ops by discovering multiple tools and running them in sequence via RUBE_MULTI_EXECUTE_TOOL.
- If a tool slug changes, re-run RUBE_SEARCH_TOOLS to fetch the latest slug before execution.
- Paginate tool schema responses and continue fetching until you have complete input schemas before executing.
