Skill UI

Delegate bounded coding tasks to the Grok Build CLI while the orchestrator keeps review and commit ownership. Covers writing briefs, dispatching runs, polling results, re-verifying gates, and landing changes.

Automate routine HelpDesk tasks using the dedicated Rube MCP toolkit. This skill allows users to list, browse, and paginate through support tickets, manage predefined agent views, retrieve canned responses, and inspect custom field definitions, streamlining entire support workflows and improving operational efficiency.

Automates HubSpot CRM workflows through Rube MCP and Composio, orchestrating contact, company, deal, ticket, and custom property tasks while enforcing batch limits and schema-aware validation.

Explore and extract Hugging Face datasets using the Dataset Viewer API. Perform read-only operations like validating datasets, listing splits, previewing rows, paginating, searching text, filtering, retrieving parquet links, and getting statistics. Ideal for data exploration and retrieval tasks.

Run Python workloads on Hugging Face Jobs using managed CPUs, GPUs, and TPUs. Supports batch inference, data processing, and recurring tasks without local setup. Securely persist results to the Hugging Face Hub with integrated secrets management for authentication.

Build reusable command line scripts and utilities around the Hugging Face API and hf CLI, supporting chaining, piping and intermediate processing for automated Hub tasks with HF_TOKEN auth.

This skill helps users find the best AI models for specific tasks by querying Hugging Face benchmark leaderboards. It analyzes hardware constraints like GPU VRAM or CPU memory to filter compatible models. The output includes a comparison table with benchmark scores, parameter sizes, licenses, and device compatibility status. It also suggests whether models can run locally or require API access.

This skill enables users to build reusable command-line scripts and utilities for interacting with the Hugging Face API. It supports chaining API calls, automating repetitive tasks, and processing model or dataset data efficiently. Scripts utilize HF_TOKEN for authentication and can leverage the hf CLI for advanced repository interactions.

A powerful tool for deterministic and reproducible retrieval of evidence from specialized academic and policy corpora. It supports searching arXiv (preprints), PubMed/PMC (biomedical literature), and US policy documents. Users can check corpus freshness, retrieve stable metadata, and fetch full-document Markdown for high-reliability research tasks.

This skill enables you to execute specific work tasks derived from a Product Requirement Document (PRD) or a set of issues. It involves translating requirements into actionable code or deliverables, following best practices like Test-Driven Development (TDD) where applicable. You should run typechecking and tests regularly, commit changes to the current branch, and use the review skill afterwards. It is essential for bridging the gap between planning and execution in software development projects.

This comprehensive skill guides users through automating complex Jira operations using the Rube MCP framework. Capabilities include searching and filtering issues via JQL, creating and editing tasks, managing agile sprints and boards, adding comments, and managing users and projects. It provides a systematic approach to integrating Jira workflows into automated processes.

Delegate bounded coding tasks to the Kimi Code CLI, then review and land the diff yourself. The orchestrator writes a brief, dispatches the headless Kimi implementer, awaits completion, verifies the resulting changes, and commits only after gates pass.