Scripting

Review code against PRISM target architecture patterns from REFACTORING_DESIGN_DOCUMENT.md. This skill should be used during refactoring to ensure new Runner and Trainer classes follow AbstractRunner/AbstractTrainer patterns.

AI-powered enterprise Claude Code hooks orchestrator with intelligent automation, predictive maintenance, ML-based optimization, and Context7-enhanced workflow patterns. Use when designing smart hook systems, implementing AI-driven automation, optimizing hook performance with machine learning, or building enterprise-grade workflow orchestration with automated compliance and monitoring.

This skill provides context and examples for the enforced development workflow.

Sets up a new Python library project using uv in the current directory. Creates project structure, installs dev dependencies, and optionally configures git remote. Use when the user wants to initialise a Python library, package, or project with uv.

指导用户为 Claude Code 创建系统级 Agent Skills，支持多个业务子 Skill 的模块化设计。当用户想要创建、编写或设计系统级 Skill，或提到"生成 skills-list / 更新技能清单 / generate_skills_list"时使用。脚本 `scripts/generate_skills_list.py` 仅存放于本 skill-writer 目录，其他系统级 Skill 不需要复制；需要更新清单时由 skill-writer 脚本对目标 Skill 目录执行。

Context-efficient browser automation using Playwright scripts and subagent isolation. Use when you need to interact with web pages, extract data from websites, verify page elements, or automate browser tasks while avoiding context window pollution from verbose HTML/accessibility trees. Provides both direct script execution and a specialized subagent pattern for complex investigations that generate large intermediate responses.

Default Python stack for Lambda: uv + Astral tools, typed code, schemas, and Hypothesis.

Master data science fundamentals. Learn Python for data, statistics, pandas, data visualization, and exploratory data analysis.

Comprehensive Android device control via ADB (Android Debug Bridge). Use when user asks about: Android device management, app installation/uninstallation, APK operations, package management, file transfer (push/pull), screenshots, screen recording, input simulation (tap/swipe/text/keyevents), shell commands, logcat viewing, device info (battery/memory/storage), automation scripts, wireless ADB connection, scrcpy mirroring. Keywords: adb, android, phone, tablet, device, apk, install app, uninstall app, screenshot, screen record, tap, swipe, type text, keyevent, logcat, push file, pull file, shell, package, activity, intent, broadcast, dumpsys, getprop, settings, input, sendevent, monkey, am start, pm list, device info, battery status, wireless adb, connect device.

Load when reviewing code, writing code examples, or ensuring code quality.Contains coding standards for Python, JavaScript, SQL, and general bestpractices for publication-quality code.

AST-based bulk code transformations across codebase using ast-grep. Replace console.log with logger, update imports, modernize syntax (var to const). Semantic pattern matching ensures accurate transformations without breaking code.

Generates RBS type signatures from Ruby source files. Triggers when creating type definitions, adding types to Ruby code, or generating .rbs files for classes/modules without existing RBS signatures.

Comprehensive feature development workflow management with branching strategies, code reviews, testing automation, and deployment coordination.

Python 프로젝트 실행, 테스트, 문법 검사, 임포트 검증을 위한 스킬. `scripts/python-runner.sh`를 사용합니다.

Mandatory verification protocol after code changes for JavaScript/TypeScript projects. Use after any code modification to ensure quality.

A specialist skill that designs and implements a testing strategy for a codebase. This skill should be used after code development and before code review.

Enforce strict TypeScript type safety rules including no 'any' types, explicit return types, proper interfaces, and type guards. Use when writing TypeScript code, reviewing code, refactoring, or when user mentions TypeScript, types, interfaces, or type safety.

Writing TypeScript predicate functions (type guards, boolean checks, validation functions). Use when creating functions that return boolean or perform type narrowing. Follows Sitebender's curried, pure function patterns with named function declarations.

Universal polyglot linting capabilities for Python, JavaScript/TypeScript, Markdown, Shell, Ruby, YAML, and JSON files. Use when you need to lint files programmatically, understand tool selection logic, or invoke linting from commands/agents.

Python coding standards including line length (80 chars), naming conventions (snake_case, PascalCase), type hints, docstrings, exception handling, and logging patterns. Use when writing new Python code or reviewing code quality.