Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.
Generate Stylelint configuration files for CSS/SCSS linting and formatting. Triggers on "create stylelint config", "generate css linting", "stylelint setup", "css lint rules".
Organize Claude Code instructions into modular rule files in .claude/rules/. Use when setting up project standards, adding team conventions, creating domain-specific rules, or managing shared coding guidelines.
Guides TypeScript refactoring operations including moving files, moving symbols between files, and renaming symbols across the codebase. Use when user wants to reorganize code structure.
Comprehensive build error repair tool for C++, Rust, and Java projects using Soong, GN, Make, or CMake. Automatically fixes 30+ types of errors including headers, linking, APIs, and config.
Detect code smells including long methods, large classes, duplicated code, and deep nesting. Use when identifying code quality issues or planning refactoring.
Code editing, syntax highlighting, and visual programming for Composable Svelte. Use when implementing code editors, syntax highlighting, or node-based visual programming. Covers CodeEditor (CodeMirror), CodeHighlight (Prism), and NodeCanvas (SvelteFlow) from @composable-svelte/code package.
This skill should be used when the user asks to "check code quality", "analyze code metrics", "find dead code", "check style compliance", "measure complexity", "find unused imports", "check type hints", "run linting", "PEP8 compliance", or mentions code quality analysis.
Enforce TypeScript quality standards immediately after writing or modifying .ts/.tsx files. Run type checking and linting on each changed file for instant feedback. Use after creating/editing TypeScript files, or when quality checks, typecheck, lint, or validate are mentioned.
Detects violations of Clean Code principles and suggests refactorings. Use when reviewing code quality, improving readability, or refactoring methods, classes, and modules.
Use immediately when user mentions: "code review", "コードレビュー", "レビュー", "review", "品質", "quality", "チェック", "check", "lint", "format", "test", "type check", "pyright", "ruff", "pytest", "テスト", "フォーマット", "確認", "大丈夫". MUST USE this skill for: - Code review after implementation (data science focus) - Quality checks with ruff, pyright, pytest - Data leakage detection in ML code - Statistical validity verification - Architecture compliance checks
Interpretive guidance for shell script quality using shfmt and shellcheck. Use when linting shell files, configuring shell tools, troubleshooting shellcheck errors, or understanding formatting options.
Personal TypeScript/React code style preferences including naming conventions, formatting rules, and review severity labels. Use this skill when: (1) Writing new TypeScript/React code, (2) Reviewing code or PRs, (3) Refactoring existing code, (4) Setting up linting/formatting configuration.
Use when adding formatting, linting, and type checking to Python research code.
Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.
Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.
Code generation and file modification agent with delegation capabilities
Semantic code search using Mantic. Use when exploring codebases, finding feature implementations, understanding component functionality, locating definitions/references, or mapping architectural patterns. Use Mantic first before grep, find, or manual file exploration.
Expert TypeScript refactoring patterns for cleaner, type-safe code
Specialized knowledge for creating, configuring, testing, and publishing VS Code extensions. Use when creating a new VS Code extension from scratch, setting up extension infrastructure (package.json contributes, activation events, testing), configuring extension publishing (.vscodeignore, vsce, marketplace), debugging extension-specific issues (CI failures, marketplace rendering), or implementing extension best practices.
This skill should be used when agents need to provide clickable code references to users in reports, investigations, or bug findings. It ensures file references use the simple path:line_number format that Claude Code automatically converts to clickable links. Do not use for general documentation or conceptual explanations.
Proactively suggest and execute code refactoring to maintain clean architecture. Triggers: refactor, 重構, 優化程式碼, clean up, 整理程式碼.
Use this skill when the user wants to implement code with formal verification. This workflow discusses requirements, creates Idris2 specifications, reviews them, compiles for verification, then implements in the target language (Python, Rust, or TypeScript). Trigger when user mentions "formal spec", "idris2", or requests rigorous code implementation.
