buildkite-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/buildkite-automation --openclawBuildkite Automation via Rube MCP
Automate Buildkite operations through Composio's Buildkite toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/buildkite
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Buildkite connection via
RUBE_MANAGE_CONNECTIONSwith toolkitbuildkite - 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 toolkitbuildkite - 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: "Buildkite 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 Buildkite task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["buildkite"]
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 Buildkite-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit buildkite |
| 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/buildkite-automation/SKILL.mdView on GitHub Overview
Buildkite Automation via Rube MCP enables programmatic control of Buildkite operations using Composio's toolkit. It relies on RUBE_SEARCH_TOOLS to fetch current tool schemas before each run and requires an active Buildkite connection. This approach minimizes schema drift and keeps workflows aligned with available tools.
How This Skill Works
First, discover available Buildkite tools with RUBE_SEARCH_TOOLS, using the 'Buildkite operations' use case. Next, verify the Buildkite connection is ACTIVE via RUBE_MANAGE_CONNECTIONS, then execute the chosen tool with RUBE_MULTI_EXECUTE_TOOL, including a memory object and the session_id. Tool slugs and required arguments are obtained from the discovery response and must be used exactly.
When to Use It
- You want to automate a Buildkite task identified by a current tool slug from Rube MCP.
- You need to validate and establish a Buildkite connection before running workflows.
- You want to execute a discovered Buildkite tool with schema-compliant arguments.
- You must handle pagination and dynamic tool schemas during discovery.
- You aim to automate multiple Buildkite tasks in a single session with session reuse.
Quick Start
- Step 1: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed.
- Step 2: Verify MCP availability with RUBE_SEARCH_TOOLS (Buildkite use_case) and note discovered tool slugs and schemas.
- Step 3: Establish a connection with RUBE_MANAGE_CONNECTIONS for toolkits ['buildkite'], then run RUBE_MULTI_EXECUTE_TOOL with a discovered slug and memory: {}.
Best Practices
- Always call RUBE_SEARCH_TOOLS before executing any workflow to get the latest tool schemas.
- Verify the Buildkite connection is ACTIVE via RUBE_MANAGE_CONNECTIONS before running tools.
- Use exact field names and types from the discovery results; do not hardcode slugs or args.
- Include a memory parameter in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
- Reuse session IDs within a workflow and fetch new ones only for new workflows; watch for pagination tokens.
Example Use Cases
- Discover Buildkite tools with RUBE_SEARCH_TOOLS, pick a slug for a deployment pipeline, and execute it with schema-compliant arguments.
- Establish the Buildkite toolkit connection via RUBE_MANAGE_CONNECTIONS and run a status-check or trigger tool.
- Execute multiple Buildkite tasks in sequence within a single session using RUBE_MULTI_EXECUTE_TOOL and memory to preserve state.
- Handle tool schema changes by re-running RUBE_SEARCH_TOOLS and adapting arguments accordingly.
- Bulk operate Buildkite tasks by combining RUBE_MULTI_EXECUTE_TOOL calls and managing pagination results from discovery.
