GitHub

Web Design Reviewer skill

github

This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then performs fixes at the source code level.

Excalidraw Diagram Generator skill

github

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

Refactor skill

github

Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

Prd skill

github

Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

Chrome Devtools skill

github

Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.

Penpot Uiux Design skill

github

Comprehensive guide for creating professional UI/UX designs in Penpot using MCP tools. Use this skill when: (1) Creating new UI/UX designs for web, mobile, or desktop applications, (2) Building design systems with components and tokens, (3) Designing dashboards, forms, navigation, or landing pages, (4) Applying accessibility standards and best practices, (5) Following platform guidelines (iOS, Android, Material Design), (6) Reviewing or improving existing Penpot designs for usability. Triggers: "design a UI", "create interface", "build layout", "design dashboard", "create form", "design landin

Agentic Eval skill

github

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Markdown To Html skill

github

Convert Markdown files to HTML similar to `marked.js`, `pandoc`, `gomarkdown/markdown`, or similar tools; or writing custom script to convert markdown to html and/or working on web template systems like `jekyll/jekyll`, `gohugoio/hugo`, or similar web templating systems that utilize markdown documents, converting them to html. Use when asked to "convert markdown to html", "transform md to html", "render markdown", "generate html from markdown", or when working with .md files and/or web a templating system that converts markdown to HTML output. Supports CLI and Node.js workflows with GFM, Commo

Meeting Minutes skill

github

Generate concise, actionable meeting minutes for internal meetings. Includes metadata, attendees, agenda, decisions, action items (owner + due date), and follow-up steps.

Workiq skill

github

Query Microsoft 365 Copilot for workplace intelligence - emails, meetings, documents, Teams messages, and people information. USE THIS SKILL for ANY workplace-related question where the answer likely exists in Microsoft 365 data. This includes questions about what someone said, shared, or communicated; meetings, emails, messages, or documents; priorities, decisions, or context from colleagues; organizational knowledge; project status; team activities; or any information that would be in Outlook, Teams, SharePoint, OneDrive, or Calendar. When in doubt about workplace context, try WorkIQ first.

Microsoft Docs skill

github

Query official Microsoft documentation to understand concepts, find tutorials, and learn how services work. Use for Azure, .NET, Microsoft 365, Windows, Power Platform, and all Microsoft technologies. Get accurate, current information from learn.microsoft.com and other official Microsoft websites—architecture overviews, quickstarts, configuration guides, limits, and best practices.

Git Commit skill

github

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

GitHub MCP server

GitHub

Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

Find hundreds of top AI tools in a massive GitHub list. Discover what developers use for art, coding, and productivity and see why this directory matters.

14,000+ stars on GitHub, this self-healing harness lets LLMs autonomously fix broken automation scripts. See why it's the future of web agents.

Unleash Mistral AI's new Vibe remote agents, powered by Medium 3.5, to offload complex coding tasks. Transform your workflow!

Ensuring emails land in inboxes, not spam folders, demands more than just hitting "send." It requires a deep understanding of infrastructure, compliance, and design—a challenge the `resend/email-best-practices` GitHub repository addresses head-on. This "agent skill" offers a comprehensive, productio

A complex data pipeline often requires a human engineer to meticulously orchestrate dozens of microservices, each with unique configurations and real-time interventions. AgentScope simplifies this by providing a unified framework for developers to build and deploy intelligent agents that reason, use

AI agents can now control and inspect live Chrome browsers, thanks to the public preview of Chrome DevTools MCP, introduced by Google AI. This Model-Context-Protocol (MCP) server integrates directly with popular coding assistants like Gemini, Claude, and Cursor, transforming web development workflow

Next.js empowers developers to build high-performance, full-stack React applications at scale, leveraging cutting-edge Rust-based tooling for lightning-fast builds. With over 139,000 stars on GitHub and used by more than 5 million developers, it extends React's capabilities to enable server-side ren

RAGFlow Fuses RAG & Agents for LLMs, Enhancing AI Context RAGFlow, an open-source Retrieval-Augmented Generation (RAG) engine, revolutionizes how Large Language Models (LLMs) access and utilize information by integrating advanced RAG with Agent capabilities. This powerful combination establishes a

Anthropic's Claude AI can now directly control your computer, clicking and typing to complete tasks on your behalf. This new capability, while powerful, requires precise configuration to truly unlock its potential. Enter Claude Code Templates, a command-line interface (CLI) tool that provides a comp

VoxCPM Delivers Tokenizer-Free, Lifelike Voice Cloning OpenBMB’s new VoxCPM system redefines speech synthesis by directly generating continuous speech from text, bypassing traditional discrete tokenization. This innovative approach enables context-aware speech generation and highly accurate zero-sh

The OpenPipe ART (Agent Reinforcement Trainer) project is revolutionizing how large language models (LLMs) learn complex, multi-step tasks by enabling direct "on-the-job training." This open-source framework allows developers to train AI agents using reinforcement learning, integrating sophisticated

VideoRAG Unlocks AI Chat for Hours-Long Videos A new open-source framework, VideoRAG, transforms how users interact with video content, enabling AI-powered conversations with clips spanning hundreds of hours. This technology, detailed in a forthcoming KDD 2026 paper, allows users to ask complex que