Execute markdown validation with taxonomy-based classification and custom rules. Use when validating markdown compliance with LLM-facing writing standards or when generating structured validation reports.
Manages practice rules. Use when user states a preference or approach, or asks to add/modify rules for coding, architecture, tooling, or best practices.
Run J-Star code review on staged changes. Analyze, fix P0/P1 issues, and iterate until clean.
Review integrated code for semantic and design issues. Use after merging task branches to detect inconsistencies. Triggers on: review integration, semantic review, check design consistency.
Run the local "ready for review" gate before asking for human review or opening a PR. Use to (1) run the repo’s lint/typecheck/tests (prefer the same commands CI runs), then (2) run `codex review` as a final automated review pass, and optionally (3) run CodeRabbit CLI (`coderabbit --prompt-only`) to catch additional issues and reduce GitHub Actions feedback loops.
Comprehensive code review for commits and pull requests. Covers security, TDD, code quality, and documentation standards.
Use when fixing lint warnings, refactoring complex functions, or understanding ESLint rules. Covers complexity limits, refactoring patterns, and when to suppress rules.
Code comment guidelines based on industry best practices. Use when reviewing code, writing new code, or when asked about comment quality. Applies to all languages but specializes in TypeScript/JavaScript. Enforces "JSDoc for public APIs only, no redundant comments" principle. Automatically suggests comment additions, removals, or refactoring alternatives.
Maintain consistent code formatting, naming conventions, and structure across the entire codebase with automated tools and clear standards. Use this skill when writing any code in any language or framework. When naming variables, functions, classes, or files. When formatting code with proper indentation and line breaks. When refactoring code to remove duplication or extract reusable functions. When running linters or formatters to ensure consistency. When removing dead code, unused imports, or commented-out blocks. When applying DRY principles to avoid code duplication. This skill applies universally to all programming tasks.
Load your coding preferences and project conventions. Use when the user says "use Superwiser", "load preferences", "load my rules", "check coding conventions", or when starting significant work on a feature.
Use when writing or modifying any code. Enforces naming conventions, function design, and code clarity principles.
編輯程式碼時的安全檢查技能。當使用者編輯檔案、修改程式碼、或進行 code review 時自動啟用。監控命令注入、XSS、eval 使用、敏感資料外洩、不安全的 postMessage 等安全風險。靈感來源於 Anthropic 官方 security-guidance plugin。Security checking skill that monitors for potential security issues when editing code, including command injection, XSS, eval usage, credential exposure, and unsafe postMessage patterns. Inspired by Anthropic's official security-guidance plugin.
Use when creating or modifying Firebase Cloud Functions in /functions directory. Enforces function structure and error handling patterns.
To format Dart code consistently, run `dart format .` on the given roots to apply standard formatting.
Validate, format, and work with JSON configuration files
Validate Jupyter notebooks (.ipynb files) for production readiness. Checks smart links consistency, layout structure, transition cells with action cards, numbered part flow, cell ordering, and overall quality. Use when validating notebooks, checking notebook structure, testing smart links, verifying action cards, or preparing notebooks for production deployment. Keywords include ipynb validation, notebook structure, smart links, action cards, transitions, part flow, production ready.
Detect squatters: modules and packages that occupy namespace positions they do not semantically own. Identifies utility dumps, stuttery siblings, axis violations, layer bleeding, and semantic diffusion — common structural smells introduced by agentic programming.
Audit identifiers and namespaces for lexical-semantic and ontological correctness. Detect semantic role misalignment (agent/tool/process/artifact), derivational misuse (e.g., -er agent nouns), and category errors between modules, packages, classes, functions, and data artifacts. Output a single Markdown report with actionable fixes.
Use when reviewing code for production readiness. Identifies critical issues causing production failures: data loss, security breaches, race conditions, performance degradation. Focuses on measurable impact, not style preferences. Triggers: reviewing code changes, verifying code safety/correctness, pre-commit reviews, after implementing significant changes.
Conventions for package.json, README.md, coding & testing styles
定義程式碼品質標準、防止幻覺 (Anti-Hallucination) 與官方文件查證流程。確保所有程式碼皆為最新、穩定且符合最佳實踐。
Pragmatic Rust conventions to keep code readable, testable, and performant for this project.
Architectural code analysis for Python design quality. Evaluates simplicity (Rich Hickey), functional core/imperative shell (Gary Bernhardt), and coupling (Constantine & Yourdon). Use for design review or architectural assessment of Python code.
