Skill UI

This toolkit provides comprehensive automation capabilities for Confluence platforms via Rube MCP. It allows users to automate the entire documentation lifecycle, including creating and updating pages, performing advanced content searches using CQL, managing spaces, and applying labels efficiently. Ideal for teams needing to streamline knowledge base maintenance and content governance.

Helps produce Dockerfiles and a detailed containerization plan for ASP.NET .NET Framework projects running in Windows containers, covering configuration settings, IIS, dependencies, and deployment steps.

Converts text-based documentation into structured Markdown by following explicit instructions, documented options, or reference files, supporting header levels, patterns, platforms, and cleanup steps for polished technical documents.

Automates ConvertKit (Kit) email marketing operations using Composio's toolkit through Rube MCP, covering subscriber lookup, tagging, unsubscribes, broadcast listing, deletion, and stats once the connection is active and the current schemas are fetched.

Generates a copilot-instructions blueprint tailored to each repository by analyzing existing code patterns, versions, and architectural standards so GitHub Copilot stays aligned with project guidelines.

Build agentic applications with the Microsoft Copilot SDK in Python, TypeScript, Go, or .NET. Covers installation, quick start, streaming responses, sessions, custom tools, and MCP servers.

Guides an AI pair to document application needs, access patterns, and scaling concerns while producing Azure Cosmos DB NoSQL requirements and data model artifacts using established best practices in a structured workflow.

This guide outlines the structure and content guidelines for an AGENTS.md file. This file serves as a comprehensive 'README for agents,' providing detailed, technical context and operational instructions (such as setup, development workflow, testing procedures, and code style) that enable advanced AI coding agents to interact with and understand a codebase effectively. It greatly complements traditional READMEs by focusing purely on machine-readable technical requirements.

Generates an AI-ready Architectural Decision Record template with precise sections, coded bullet conventions, front-matter metadata, and sequential storage under /docs/adr to keep decision documentation structured for both machines and people.

Generates a concise, AI-optimized specification describing what an existing GitHub Actions workflow does, its triggers, requirements, inputs/outputs, and governance so teams can understand and maintain it without implementation details.

Automates creating a single GitHub feature issue from a specification file, checking existing issues first, filling title/description/labels per feature_request.yml, and including only spec-mandated changes.

Automates the creation of GitHub issues by parsing an implementation plan, verifying existing issues, and generating one issue per phase using feature or chore templates with structured titles and requirements.