持續整合/部署

Generates clear, concise git commit messages in Japanese from staged changes. Use when the user asks to create a commit, write a commit message, or review staged changes for committing.

Automatically troubleshoot unexpected results OR command/script errors without user request. Triggers when: (1) unexpected behavior - command succeeded but expected effect didn't happen, missing expected errors, wrong output, silent failures; (2) explicit failures - stderr, exceptions, non-zero exit, SDK/API errors. Applies systematic diagnosis using error templates, hypothesis testing, and web research for any Stack Overflow-worthy issue.

Continuously observes development patterns to identify automation opportunities. Always active in background. Detects repeated patterns, suggests skills/hooks/commands, auto-creates automations at threshold (3 occurrences).TRIGGERS - Keywords: patterns, learnings, observations, automation, repeated tasks, /learn:review, /learn:implement, /analyze-patterns, pending automations, skill suggestions, hook suggestions, command suggestions, optimization opportunities.TRIGGERS - Phrases: "analyze patterns", "review learnings", "what have you learned", "create automation", "automate this", "I keep doing this", "repeated task", "optimize workflow", "suggest improvements", "pending suggestions".TRIGGERS - Automatic: After file modifications (via hook), before git commits, at session end, when dependencies added, after task completion.

Guides test creation for Polibase following strict testing standards. Activates when writing tests or creating test files. Enforces external service mocking (no real API calls), async/await patterns, test independence, and proper use of pytest-asyncio to prevent CI failures and API costs.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Deploy event-driven automation with EventSource, EventBus, and Sensor configuration. Complete setup guide for production Argo Events on Kubernetes clusters.

로컬 AI CLI에 작업을 아웃소싱할 때 자동 활성화. Use when the task is complex, requires specialized AI capabilities, or benefits from distributing work to different AI models

Template for creating new Claude Code skills following official specification. Provides structure, YAML frontmatter format, and best practices for skill development.

Build immersive 3D web experiences with Three.js - WebGL/WebGPU library for scenes, cameras, geometries, materials, lights, animations, loaders, post-processing, shaders (including node-based TSL), compute, physics, VR/XR, and advanced rendering. Use when creating 3D visualizations, games, interactive graphics, data viz, product configurators, architectural walkthroughs, or WebGL/WebGPU applications. Covers OrbitControls, GLTF/FBX loading, PBR materials, shadow mapping, post-processing effects (bloom, SSAO, SSR), custom shaders, instancing, LOD, animation systems, and WebXR.

Standard library Python argparse examples with subparsers, choices, actions, and nested command patterns. Use when building Python CLIs without external dependencies, implementing argument parsing, creating subcommands, or when user mentions argparse, standard library CLI, subparsers, argument validation, or nested commands.

Run and manage long-running background tasks in the shell. Use for starting processes in background, monitoring output, listing active tasks, and killing processes. Essential for dev servers, watch modes, builds, and any non-blocking operations.

Clean Architecture and SOLID principles implementation including dependency injection, layer separation, domain-driven design, hexagonal architecture, and code quality patterns

Mobile UI patterns, gestures, animations, and platform-specific design.

Generate 3D printable STL files for woodworking jigs and fixtures using CadQuery. Use when the user requests lampshade jigs, circle cutting guides, angle wedges, spacing blocks, alignment fixtures, router jigs, or any custom 3D-printed woodworking aid. Optimized for Elegoo Neptune 4 Pro (225x225x265mm build volume, 0.2mm layer height). Always use metric measurements.

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

Implement secure, consistent input validation on both client and server sides. Use this skill when validating form inputs, API request bodies, or user-provided data. When sanitizing input to prevent injection attacks (SQL, XSS, command injection). When writing allowlist-based validation, type checking, or business rule validation. When providing field-specific error messages to users.

Phase 1 of disciplined development. Deep problem understanding before design.Maps existing systems, identifies constraints, surfaces risks, and producesa research document for human approval before proceeding.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

Use when understanding external libraries, frameworks, or dependencies - provides workflows for finding and reading official documentation via Context7 instead of web search or source code reading

Repository type detection for identifying library vs consumer repositories. Analyzes directory structure, package.json dependencies, and monorepo indicators to classify repositories and detect multi-mono relationships. Returns metadata about workspace type, monorepo tool (Turborepo, nx, lerna, pnpm-workspace), and library consumption patterns. Use when agents need to adapt behavior based on repository type or validate architecture-specific patterns.