Skill UI

A persistent file planning system for multi-step AI agent work. It saves task plans, findings, and progress to disk, acting as disk-based working memory. Includes lifecycle hooks for context injection and session recovery. Suitable for research or tasks requiring 5+ tool calls. No network upload path.

Scan installed skills, extract shared cross-domain principles, and distill them into reusable rules. Supports appending, revising, or creating rule files during regular maintenance or after skill inventory updates.

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.

MCPB is a specialized local server bundle that packages the entire runtime environment (Node.js or Python) alongside the server code. It allows developers to distribute and run complex MCP services directly on a user's machine without requiring the user to pre-install specific runtimes or toolchains. Use this when the server must interact with the local filesystem, desktop applications, or OS-level APIs.

A specialized skill for generating production-ready, SEO-optimized visual assets. It handles various use cases including OG social cards, blog hero images, product visuals, and infographics. The system ensures outputs adhere to best practices like specific aspect ratios, schema markup, and file naming conventions, making content publishable and discoverable by search engines.

Use the understand-diff skill to analyze git changes against the stored knowledge graph so you can quickly summarize modified files, affected components, and risk areas before reviewing or merging.

Provide step-by-step explanations of specific files, functions, or modules, leveraging the understand-explain workflow to map graph context, layer placement, internal structure, and data flow for developers needing deep clarity.

Creates a comprehensive onboarding guide for new teammates by extracting project context from the knowledge graph, layering architecture descriptions, guiding tours, and highlighting complex files so newcomers can ramp up quickly.

This skill enables AI agents to maintain persistent project planning using Markdown files on disk. It manages task_plan.md, findings.md, and progress.md to extend context window limits. Lifecycle hooks automatically inject planning content and prevent command execution in Markdown. Ideal for complex research tasks requiring over 5 tool calls, ensuring state persistence across sessions without network uploads.

Implements Manus-style file-based planning to organize complex tasks, enforcing persistent markdown plan/findings/progress files, enforcing read-before-decide and write-after-action rules, and enabling session recovery after /clear.

This skill acts as an anti-over-engineering guardrail, instructing AI coding agents to maintain strict scope control and minimalism. It guides the AI to only modify the files and lines explicitly requested by the user, avoiding unnecessary abstractions, unrequested refactors, or scope creep. Use it when you prefer the simplest, most direct solution and want to prevent the agent from 'grinding' the code base.

This skill provides a systematic pipeline for safely executing large-scale code refactors across multiple files or subsystems. It first performs parallel, dependency-aware analysis to map the entire scope, synthesizing a single, actionable plan. The process then breaks the work into independent 'work packets,' which are executed sequentially or in parallel by specialized worker agents, ensuring strict dependency management and behavior parity throughout the entire process.