Skill UI

This skill ensures AI models generate complete, unabridged code and files without placeholders, TODOs, or skipped sections. It enforces strict completeness for deliverables like full implementations or exhaustive lists. It prevents shortcuts like '...' or descriptions instead of code, ensuring every requested item is fully realized within token limits.

This skill detects and recovers text accidentally typed using the Taiwanese Bopomofo keyboard while the input method was stuck in English mode. It maps garbled keystrokes like su3cl3a8 back to Traditional Chinese characters using a decoder script and context analysis. It is designed for Taiwanese developers who forget to switch input methods when prompting AI, ensuring requests are understood without retyping. It excludes technical strings like code or URLs.

Shared vocabulary and principles for designing deep modules with small interfaces, clean seams, and testable, AI-navigable codebases.

Answer factual and how-to questions about Nightingale (n9e) platform including UI navigation, business groups, subscription rules, notification pipeline, categraf plugin fields, metric names, config syntax, and source code implementation details. Uses official documentation and embedded source code corpus as evidence sources. Every concrete fact must be verified from docs or code.

This skill statically inspects local JavaScript, Electron, native binary, .NET, and CUDA applications to explain feature functionality with file and line evidence. It supports analyzing packaged .asar files, ELF/PE binaries, EVM bytecode, and CUDA programs without execution. Users must be authorized to study the target. It helps understand or reimplement features safely by parsing code and metadata, refusing requests to bypass security mechanisms or DRM.

This skill retrieves up-to-date documentation for third-party APIs, SDKs, and libraries using the chub tool. It ensures code accuracy by fetching current references instead of relying on outdated pre-trained knowledge. Use it when users request tasks involving external services like OpenAI or Stripe. Follow chub instructions to search, fetch, and annotate documentation for better future sessions.

This skill performs PR code reviews identifying decay risks, design smells, and maintainability issues. It structures findings as Symptom, Source, Consequence, and Remedy based on twelve classic engineering books. It triggers on code review requests, diffs, or pasted code feedback. Topics include refactoring, clean architecture, SOLID principles, and Brooks's Law. It excludes syntax questions or writing code from scratch.

Gives AI agents a dedicated email address to send, receive, reply, and wait for replies or verification codes over MCP or HTTP, with self-service onboarding and API key management.

This skill runs drift detection on design documents to verify consistency with actual code. It identifies missing features, incomplete models, and architectural divergences. It generates a detailed report listing discrepancies between specifications and implementation. Use this when checking if code matches design documents or READMEs in a directory.

Faber is an experimental statically typed language for coding agents and human authors. It features clear mechanical grammar, explicit static types, and math-oriented operators. Programs compile to Rust, TypeScript, Go, Swift, and more. This skill helps write, check, and run Faber programs, explain diagnostics, and emit code to other languages. Always verify compiler versions and follow live documentation.

This skill analyzes a codebase to identify specific moments where motion would genuinely benefit the user experience. It proposes precise animation recipes based on Emil Kowalski's philosophy, focusing on restraint and purpose. It evaluates candidates against a strict gate regarding frequency, purpose, speed, and function, rejecting unnecessary animations. It does not implement code but provides actionable strategies for frontend development.