Skill UI

Astro is a modern web framework designed specifically for building high-performance, content-heavy websites like blogs, documentation sites, and portfolios. Its core innovation is the Islands Architecture, which ships zero JavaScript by default, drastically improving performance and Core Web Vitals. It supports multi-framework components (React, Vue, Svelte) in a single project, making it ideal for content developers prioritizing speed and flexibility.

Automatically analyzes unfamiliar codebases to generate a comprehensive, structured onboarding guide. It systematically detects package manifests, framework fingerprints, architecture maps, key entry points, and coding conventions. Ideal for new developers joining a project or setting up a repository for the first time.

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.

A comprehensive 7-stage super workflow designed for advanced GitHub repository management. This tool automates deep audits to detect security secrets, junk files, and code quality issues. It further provides structured PR review capabilities, competitor benchmarking against similar projects, and synthesizes all findings into a prioritized, actionable plan, ensuring your repository is optimized and production-ready.

A robust, file-driven methodology for managing complex, multi-step projects and research tasks. By utilizing dedicated Markdown files (task_plan.md, findings.md, progress.md) as persistent 'disk memory,' this system helps users overcome the limitations of the context window, ensuring all critical decisions, findings, and workflow progress are permanently tracked and easily retrieved. Ideal for long-running development cycles and detailed research.

PydanticAI is a robust Python framework that integrates Pydantic's type-checking and validation capabilities into Large Language Models (LLMs). It allows developers to build production-ready AI agents that guarantee structured, validated outputs, moving beyond simple raw strings. Key features include supported tool calling, dependency injection for testability, and multi-model compatibility across major providers like OpenAI, Anthropic, and Gemini. Use this when reliability and correct data structure are paramount.

This skill provides guidance on implementing common architectural patterns and best practices within the PyTorch framework. It is designed for developers building sophisticated deep learning models, helping to improve structure, efficiency, and code maintainability when working with neural networks.

SvelteKit is the official full-stack framework built on Svelte, enabling developers to build fast, modern, and highly performant web applications. It provides comprehensive features including file-based routing, Server-Side Rendering (SSR), Static Site Generation (SSG), API routes, and progressive form actions, all while maintaining Svelte's zero runtime overhead. Use this skill when building complex, data-driven web platforms where performance and developer experience are paramount.

Provides CLI-driven access control for a Discord channel by reading/writing the shared JSON state. Use it to approve pairings, edit allowlists, set DM/group policies, and keep the channel server informed without touching Discord directly.

This skill systematically probes an AI model's core behavioral patterns across six critical dimensions, including reasoning, refusal, formatting, and grounding. It generates a comprehensive, styled HTML report with radar charts and actionable insights, allowing users to understand a model's true capabilities, compare different models, or perform compliance and red-team assessments without needing an external API key.

This guide assists developers in designing and architecting Model Context Protocol (MCP) servers that integrate deeply with LLMs like Claude. It is not a coding skill, but a comprehensive consultation process that guides users through use case interrogation, determines the optimal deployment model (e.g., Remote HTTP, MCPB), and selects the appropriate tool-design pattern for seamless, robust integration.

Handles IMO/Putnam/USAMO/AIME style problems by generating refined proofs, then running a fresh-context adversarial verifier to catch flaws, finally producing honest confidence reports and verified PDFs when possible.