Skill UI

Automates the complex pre-development workflow for large-scale system transformations, such as major rewrites, migrations, or overhauls. This skill performs comprehensive project analysis, task decomposition, planning document generation, and sets up detailed progress tracking across multiple phases, ensuring a structured approach before any coding begins. It supports adaptive control and integrates robust task tracking via GitHub or local files.

This powerful tool utilizes Playwright to record high-quality, professional web application demo videos. It simulates natural user interactions, injecting a visible cursor overlay and adhering to specific pacing guidelines. It is ideal for creating comprehensive tutorials, feature walk-throughs, or documentation for stakeholders.

This skill provides a systematic, four-phase workflow for diagnosing and recovering from AI agent failures. It guides the agent to first capture the failure state, diagnose the root cause (e.g., loop, context overflow, state drift), apply minimal containment recovery actions, and finally generate a detailed introspection report, minimizing the need for human intervention.

A conversational onboarding skill designed to deeply understand the user and define the core identity of an AI partner. Through adaptive, multi-phase dialogue, it extracts key behavioral traits, motivations, and relationship dynamics, culminating in the generation of a comprehensive SOUL.md file that governs the AI's personality and interaction style. Use this skill when setting up, personalizing, or updating your AI agent.

This tool enables deep inspection and validation of web applications by connecting to the browser's DevTools Protocol (MCP). It allows agents to perform tasks like DOM inspection, capturing console logs, monitoring network requests, profiling performance, and taking screenshots in a live environment. Essential for debugging UIs, validating API integrations, and performing end-to-end automated testing.

Controls BrowserWing-based browsers via HTTP endpoints to navigate pages, interact with elements (click/type/select), capture accessibility snapshots, run JavaScript, take screenshots, and execute batch sequences for data extraction workflows.

Generates professional documentation for software projects, covering READMEs, API references, architecture guides, inline comments, and changelogs, adapting style and scope to the codebase and user request.

Guides writing documentation and ADRs to capture why architectural or API choices were made, when to comment, and how to structure README/API info so future engineers and agents understand the rationale and trade-offs.

A comprehensive guide for integrating Firebase Crashlytics into Flutter applications. It teaches how to capture fatal, non-fatal, and isolate errors, customize reports with user identifiers, custom keys, and logs, and manage opt-in data collection to ensure robust crash monitoring in production environments.

Accelerates GitHub cloning, release/raw/archive downloads, and other resource access for Mainland China users by rewriting URLs through githubproxy.cc or fallback ghfast.top, with an optional URL converter script for quick adaptation.

Guides Flutter/Dart teams on using Mockito for generating mocks, stubbing behavior, verifying interactions, capturing arguments, and managing fake versus real objects so tests stay predictable and maintainable.

This guide details the OpenViking long-term memory plugin, which enhances conversational AI by automatically capturing key facts and preferences from past interactions. It utilizes auto-capture modes (semantic or keyword) to store memories and automatically recalls relevant context before generating a response, ensuring continuity and personalization across long conversations. Provides tools for retrieval, manual storage, and memory deletion.