Skill UI

Designs a minimal expense claim register and approval workflow for SMEs, producing CSV, SQL, JSON or Notion templates on request. Covers claim fields, approval limits, receipts, cost centres and reimbursement status.

Creates a minimal mentorship program setup with mentor-mentee pairs, departments, focus areas, goals, session tracking, ratings, and progress notes. Recommends workflows and generates CSV, SQL, JSON, or Notion artifacts on request.

This skill fetches public webpages and converts them into clean Markdown format suitable for AI agents. It allows users to read, summarize, quote, or cite webpage content while preserving the original source URL. The workflow involves sending a GET request to a specific endpoint to retrieve the rendered content. It is designed for read-only access and does not support private pages or content modification.

Generate validated architecture, workflow, sequence, data-flow, ERD, class and timeline diagrams as explorable standalone HTML with themes and export, plus one-page explainers.

Prove data/AI workflows end-to-end on tiny samples, find cost-saving wins, then scale within budget using cost-gated steps. Ideal for multi-stage pipelines involving paid compute like LLM tokens or warehouse credits.

A step-by-step workflow for UI work: understand the project, choose the right plan (new screen, dashboard, polish, simplify, review), then render, fix, and re-check until the result looks right. It helps agents build real, polished interfaces and avoid AI slop.

Manage multi-agent pipelines on Grok Build using Ruflo-style team bus and MCP tools. Ideal for coordinating feature development workflows like architect-to-reviewer chains or replacing Claude SendMessage. Includes CLI fallback for team creation, planning, and subagent spawning with isolation controls.

This skill ensures browser automation reliability by anchoring actions to stable DOM selectors and semantic roles rather than screen coordinates. It helps workflows survive layout shifts, A/B tests, and viewport changes. Users should inspect the DOM, prioritize data-testid attributes, verify selectors match exactly one element, and wait on state instead of fixed time. It includes error handling for modals and navigation races.

Reviews AI-assisted Word/DOCX workflows for operational integrity before professional reliance: preserves originals, tracked changes, comments, numbering, sections, edit identity, structure, save/verify cycles, and human acceptance; returns PASS, REVIEW, or BLOCK.

This skill covers building, extending, and reviewing Model Context Protocol (MCP) servers using the Python FastMCP library. It includes guidance on managing API versions, defining tools, resources, and prompts, handling errors, and configuring transports. It also details how to evaluate agent workflows and test server capabilities against client requirements.

Generate deduplicated FAQ question-answer pairs from source content, topics, or support logs for SEO and content workflows. Creates structured data when requested, flags missing policies, and preserves facts without fabricating answers.