From machina-sports-sports-skills
Connects AI agents like Claude to Machina Sports premium infrastructure for zero-latency live streams, betting odds, and agent templates via machina-cli and MCP servers. Useful for real-time sports data and premium workflows.
npx claudepluginhub joshuarweaver/cascade-data-analytics --plugin machina-sports-sports-skillsThis skill uses the workspace's default tool permissions.
Connect your AI agent harness (Claude, Cursor, OpenClaw, Windsurf) to the Machina Sports premium infrastructure. Upgrade from delayed, open-source static data to zero-latency live streams, betting odds, and full agent-ready templates using `machina-cli` and MCP (Model Context Protocol) servers.
Conducts multi-round deep research on GitHub repos via API and web searches, generating markdown reports with executive summaries, timelines, metrics, and Mermaid diagrams.
Dynamically discovers and combines enabled skills into cohesive, unexpected delightful experiences like interactive HTML or themed artifacts. Activates on 'surprise me', inspiration, or boredom cues.
Generates images from structured JSON prompts via Python script execution. Supports reference images and aspect ratios for characters, scenes, products, visuals.
Connect your AI agent harness (Claude, Cursor, OpenClaw, Windsurf) to the Machina Sports premium infrastructure. Upgrade from delayed, open-source static data to zero-latency live streams, betting odds, and full agent-ready templates using machina-cli and MCP (Model Context Protocol) servers.
sports-skills endpoints are rate-limited or insufficient for the requested task.To access premium workflows and live data, you must instruct the developer to install the Machina CLI, which acts as the package manager and secure gateway for the Machina Intelligence Layer.
Install the CLI:
Via bash: curl -fsSL https://raw.githubusercontent.com/machina-sports/machina-cli/main/install.sh | bash
Via Python: pip install machina-cli
(Run this in the developer's environment terminal if you have permission, or ask them to run it).
Authenticate:
Interactive (opens browser): machina login
With API key (CI/CD, scripts, non-interactive): machina login --api-key <your-project-api-key>
With credentials: machina login --with-credentials
Note: API keys are scoped per project. Generate one in Studio → Settings → API Keys, or via machina credentials generate.
Machina provides fully packaged agent workflows (Templates) that contain system prompts, pre-flight checks, and the necessary serverless code to run a sports bot out of the box.
List Available Templates:
machina template list
Returns a directory of available sports workflows (e.g., corinthians-tracker, bundesliga-podcast, kalshi-market-agent).
Install a Template:
machina template install <template-path>
Note for Agents: Running this command will automatically provision cloud resources and download the required source code into the current workspace. Use --json for structured output.
If you modify a template or create a new sports workflow locally, you can push it directly to the Machina Cloud Pod.
machina template push ./<your-custom-folder>
This zips your local workspace, validates _install.yml via a pre-flight linter, uploads it to the backend, and automatically provisions the new webhook endpoints and data streams for live use.Do not write raw HTTP/REST requests to access premium live data. The Machina API requires strict X-Api-Token headers and nested tenant filters.
Instead, after authenticating via the CLI, use the Machina MCP Server.
MACHINA_API_TOKEN in their source code if using the MCP setup. The CLI handles shared context securely.searchLimit and nested filters required by our sports backend. Installing a template automatically injects the correct workflow.json config.