IDE 與編輯器

Decision guide for code navigation. Teaches when to use gabb tools vs default tools (Grep/Read) for maximum efficiency. Applies to Python/TypeScript/Rust/Kotlin/C++.

Execute complex browser automation using Playwright Python. Use for video recording, multi-page navigation, data extraction. Triggers on "browser script", "record video of website", "extract data from webpage".

Designs multi-step agent workflows with tool usage, retry logic, state management, and budget controls. Provides orchestration diagrams, tool execution order, fallback strategies, and cost limits. Use for "AI agents", "agentic workflows", "multi-step AI", or "autonomous systems".

主要コードスタイルガイドの比較と適用を整理し、チーム規約の統一と移行を支援するスキル。 Airbnb/Google/Standardの選定、カスタマイズ、移行計画を扱う。 Anchors: • Clean Code (Robert C. Martin) / 適用: 命名と意図の明確化 / 目的: 可読性の向上 • Style Guide Comparison / 適用: ガイド選定 / 目的: 適合性評価 • Migration Patterns / 適用: 移行計画 / 目的: 変更影響の最小化 Trigger: Use when selecting or migrating style guides, unifying team conventions, or customizing linting rules. code style guide, ESLint config, Prettier rules, migration, coding conventions

This skill automates the setup of machine learning experiment tracking using tools like MLflow or Weights & Biases (W&B). It is triggered when the user requests to "track experiments", "setup experiment tracking", "initialize MLflow", or "integrate W&B". The skill configures the necessary environment, initializes the tracking server (if needed), and provides code snippets for logging experiment parameters, metrics, and artifacts. It helps ensure reproducibility and simplifies the comparison of different model runs.

Guide AI agents through Specification-Driven Development (SDD) + Test-Driven Development (TDD) integrated workflow. Use when implementing complex features, making architectural decisions, or conducting large-scale refactoring that requires clear specifications and test-first development.

R programming for data analysis, visualization, and statistical workflows. Use when working with R scripts (.R), Quarto documents (.qmd), RMarkdown (.Rmd), or R projects. Covers tidyverse workflows, ggplot2 visualizations, statistical analysis, epidemiological methods, and reproducible research practices.

Skill creation guidelines and protocols for high-fidelity, token-efficient specialized capabilities. Provides routing patterns, component selection criteria, and skill structure templates. Includes progressive disclosure patterns for routing vs reference separation. Scope: skill creation, skill structure, routing logic, template patterns. Excludes: agent creation, command creation (handled by component-specific skills). Triggers: skill, create a skill, edit skill, validate skill, new skill.

Backend standards for modern TypeScript applications covering Convex, Supabase, Drizzle ORM, Stripe, tRPC, and API design patterns. Load when implementing server-side code, database schemas, or API endpoints.

Guides creation of Product Requirements Prompts (PRPs) - comprehensive requirement documents that serve as the foundation for AI-assisted development

This skill allows Claude to conduct comprehensive security audits of code, infrastructure, and configurations. It leverages various tools within the security-pro-pack plugin, including vulnerability scanning, compliance checking, cryptography review, and infrastructure security analysis. Use this skill when a user requests a "security audit," "vulnerability assessment," "compliance review," or any task involving identifying and mitigating security risks. It helps to ensure code and systems adhere to security best practices and compliance standards.

This skill enables Claude to execute visual regression tests using tools like Percy, Chromatic, and BackstopJS. It captures screenshots, compares them against baselines, and analyzes visual differences to identify unintended UI changes. Use this skill when the user requests visual testing, UI change verification, or regression testing for a web application or component. Trigger phrases include "visual test," "UI regression," "check visual changes," or "/visual-test".

Systematically identify and remove unused imports, variables, and dead code from TypeScript/React projects using --noUnusedLocals and --noUnusedParameters compiler flags

Kubernetes debugging and troubleshooting best practices using MCP kubernetes tools. Use when: (1) Pods are failing, pending, or in CrashLoopBackOff/ImagePullBackOff states, (2) Services are unreachable or DNS resolution fails, (3) Deployments aren't rolling out, (4) Nodes are unhealthy or unschedulable, (5) Resource issues (OOM, CPU throttling), (6) Any "why isn't my Kubernetes workload working?" questions. Provides systematic debugging workflows using kubectl_get, kubectl_describe, kubectl_logs, exec_in_pod, and other MCP kubernetes tools.

This skill leverages the database-diff-tool plugin to compare database schemas, generate migration scripts, and provide rollback procedures. It is triggered when the user requests database schema comparisons, migration script generation, or database synchronization. Use this skill when asked to identify differences between database schemas (PostgreSQL or MySQL), create safe migration scripts with transaction safety, validate changes before deployment, or generate rollback procedures. The skill is activated by requests involving terms like "database diff", "schema comparison", "generate migration script", "database synchronization", or `/db-diff`.

Guide for implementing a new language parser in Codanna. Use when adding language support, implementing parsers, or extending language capabilities. Covers the six-file architecture (mod.rs, definition.rs, parser.rs, behavior.rs, resolution.rs, audit.rs), trait implementation patterns, resolution scope design, and integration workflow. Triggers on requests to add language support, implement new parser, extend language capabilities, or create language implementation.

This skill enables Claude to encrypt and decrypt data using various algorithms provided by the encryption-tool plugin. It should be used when the user requests to "encrypt data", "decrypt a file", "generate an encrypted file", or needs to secure sensitive information. This skill supports various encryption methods and ensures data confidentiality. It is triggered by requests related to data encryption, decryption, or general data security needs.

Use this skill when working on rpg-toolkit codebase - provides architecture patterns, testing guidelines, error handling, and D&D 5e combat mechanics knowledge

This skill should be used when the user asks to "create a component", "build a UI component", "generate a React component", "make a new component", "add a component", or mentions component types like "card", "button", "form", "input", "widget", "kpi card", "stat card", "dashboard widget". Provides comprehensive guidance for creating production-ready React components with TypeScript, Tailwind CSS, and modern best practices.

Industry-specific guide for implementing Fullstory in media, entertainment, and streaming applications. Covers subscription funnel optimization, content engagement tracking, video player UX, paywall optimization, and ad-supported vs subscription models. Includes detailed examples for streaming services, news sites, gaming platforms, and content creators.