Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →openteams-lab/prerender-automation
Automate Prerender tasks via Rube MCP (Composio). Always search tools first for current schemas.
Passed 14 of 19 test cases with the skill, and 6 of 19 without it.
and 11 more in the full report
10 fixed6 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
We discovered a tool slug 'prerender_recache_url' and want to run it via the multi-tool execution wrapper for 'https://app.example.com/dashboard'. We have no past memory state to pass. Provide the payload structure for running this execution.
| Checked | Without skill | With skill |
|---|---|---|
| Includes an explicit memory object in the RUBE_MULTI_EXECUTE_TOOL payload | Missed | Passed |
| Passes the target tool invocation details inside the tools array | Missed | Passed |
The instructions your model reads when the skill loads.
Automate Prerender operations through Composio's Prerender toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/prerender
RUBE_MANAGE_CONNECTIONS with toolkit prerenderRUBE_SEARCH_TOOLS first to get current tool schemasGet 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.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit prerenderAlways discover available tools before executing workflows:
RUBE_SEARCH_TOOLS
queries: [{use_case: "Prerender operations", known_fields: ""}]
session: {generate_id: true}
This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Prerender task"}]
test cases passed, vs 6 / 19 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.