semanticscholar-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/semanticscholar-automation --openclawSemanticscholar Automation via Rube MCP
Automate Semanticscholar operations through Composio's Semanticscholar toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/semanticscholar
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Semanticscholar connection via
RUBE_MANAGE_CONNECTIONSwith toolkitsemanticscholar - 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 toolkitsemanticscholar - 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: "Semanticscholar 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 Semanticscholar task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["semanticscholar"]
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 Semanticscholar-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit semanticscholar |
| 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/semanticscholar-automation/SKILL.mdView on GitHub Overview
Automates Semanticscholar operations through the Composio Semanticscholar toolkit via Rube MCP. It starts with tool discovery to fetch current schemas and requires an active connection before executing any workflows.
How This Skill Works
First, discover available tools using RUBE_SEARCH_TOOLS to obtain tool slugs and input schemas. Then verify the Semanticscholar connection with RUBE_MANAGE_CONNECTIONS and ensure the status is ACTIVE. Finally, execute tools with RUBE_MULTI_EXECUTE_TOOL, including memory data and a session_id, using the discovered tool_slug and schema compliant arguments.
When to Use It
- When you need to automate repetitive Semanticscholar operations
- When you must always work with the latest tool schemas
- When establishing a new Semanticscholar workflow that requires auth via Rube MCP
- When processing batch tasks with pagination and multiple results
- When reusing a session to chain multiple tool executions in a workflow
Quick Start
- Step 1: Connect Rube MCP and verify RUBE_SEARCH_TOOLS is available
- Step 2: Run RUBE_SEARCH_TOOLS with a Semanticscholar use_case to discover tools
- Step 3: Run RUBE_MANAGE_CONNECTIONS to activate the toolkit and then execute a tool via RUBE_MULTI_EXECUTE_TOOL using the discovered slug
Best Practices
- Always call RUBE_SEARCH_TOOLS before selecting a tool
- Check RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing
- Use exact field names and types from the discovered tool schemas
- Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
- Reuse session IDs within a workflow and handle pagination tokens
Example Use Cases
- Automate retrieval of author profiles from Semanticscholar and export to CSV
- Batch fetch citation counts for a set of papers and compile a report
- Discover new tooling schemas and run a sequence of Semanticscholar operations
- Verify connections and run multiple tools in a single session for a research project
- Paginate through large result sets and aggregate findings across steps