Skill UI

This skill provides comprehensive intelligence across finance and media. Users can search real-time news, analyze media bias across multiple dimensions, get live stock/crypto data with AI forecasts, price financial options using ML models, and synthesize balanced perspectives on current events. It is ideal for deep research, investment analysis, and media literacy.

This skill provides a comprehensive, structured workflow for managing projects, issues, and team workflows within the Linear platform. It supports natural-language project management, allowing users to perform tasks like sprint planning, bug triage, and workload balancing by interacting with the Linear MCP server and various specialized tools.

This comprehensive skill provides expert guidance for integrating with Google NotebookLM programmatically, covering both the `nlm` Command Line Interface (CLI) and Measurement/Control Plane (MCP) tools. Use it to automate workflows, manage notebooks, add diverse sources (URLs, YouTube, Drive), and generate various complex content types, such as reports, quizzes, mind maps, and videos. Essential for developers building upon NotebookLM's advanced research capabilities.

This skill provides comprehensive security auditing for Model Context Protocol (MCP) servers and their associated tool metadata. It is designed to detect sophisticated supply chain attacks, including tool poisoning (indirect prompt injection), Server-Side Request Forgery (SSRF), tool shadowing, and unauthenticated exposure. It is essential for securing AI agent stacks before integrating new tools or during CI/CD processes.

This skill provides comprehensive access to the Hugging Face Hub ecosystem via MCP server tools. Users can search for state-of-the-art models, datasets, and research papers, retrieve detailed repository information, fetch documentation, run compute jobs on GPU/CPU, and interact with Gradio Spaces as fully functional AI tools. Ideal for ML development, research, and application prototyping.

This skill guides users through the complete lifecycle of data quality incident management using Monte Carlo MCP tools. It performs detailed investigation, including root cause analysis and blast radius assessment. It then coordinates various external tools (APIs, CLI) to propose and execute appropriate remediation actions, ensuring all data incidents are resolved with full context.

This skill provides comprehensive guidance on choosing and creating the appropriate Neon Postgres branch for development and testing workflows. Users must decide between a 'Normal' branch (for realistic migration testing with live data) or a 'Schema-Only' branch (for highly sensitive data environments). It details the decision rules, tool selection (CLI/MCP), and procedures for branch creation and resetting.

This harness transforms standard code environments into fully persistent, autonomous agent systems. It leverages native features like scheduled tasks (Crons), remote dispatching, and structured memory storage (MCP) to enable continuous, self-directing automation. Ideal for building AI assistants that require long-term context, recurring workflows, and complex, multi-step operations, eliminating the need for external agent frameworks like AutoGPT.

Code Health MCP provides structural maintainability feedback and design-level health scores, going beyond standard linting. It is crucial for AI-assisted coding workflows, allowing users to review code quality, verify score deltas after changes, and gate commits or pull requests to prevent codebase regression. Use it when refactoring, updating legacy modules, or ensuring the integrity of large diffs.

This tool audits the token consumption across all components (agents, skills, rules, MCP servers) within a Claude Code session. It analyzes token overhead, identifies bloat (e.g., overly long descriptions, redundant components), and generates a detailed context budget report. Use it to maintain optimal context window usage, improve performance, and prevent context saturation.

This skill fetches the latest, live documentation and code examples for specific libraries and frameworks (e.g., Next.js, React, Prisma). Instead of relying on static or outdated training data, it utilizes the Context7 MCP to provide accurate, up-to-date answers for setup questions, API references, and code generation based on current best practices.

Performs a pure, read-only static security scan of a harness's declared MCP surfaces. It analyzes policy, permission, and dependency issues by reading manifest files (e.g., .mcp/servers.json and .harness/claims.json) without executing any underlying tools. Designed for integration into CI/CD pipelines to enforce security policies and ensure compliance.