持續整合/部署

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.

Manages permanent memory storage for decisions, blockers, context, preferences, and procedures. Use when user says "remember", "save this decision", "what did we decide", "recall", "search memories", "any blockers", or when making important architectural decisions. Provides SDAM compensation through external memory.

Create custom Claude Code subagents with proper structure and best practices. Supports project (.claude/agents/) and global (~/.claude/agents/) scopes. Activated when users mention "create agent", "new subagent", "add agent", "agent 만들기", or need to build specialized AI assistants.

Use when testing React Native Web applications. Provides patterns for Jest, React Native Testing Library, component testing, and web-specific testing strategies.

This skill should be used when the user asks about [X], needs to [Y], or mentions [Z]. Use when queries involve [key terms, file types, specific actions]. Be specific about trigger words and scenarios.

Git and GitHub conventions for commits, branches, and PRs in Pantas Green projects.Use when: committing code, creating branches, making PRs, fixing CI failures, git operations.Triggers: commit, push, PR, pull request, branch, git, gh, GRE-, autopep8, CI, merge, rebase

Gather design feedback from AI consultants (Gemini and Codex). Use for architecture decisions, design review, or when you want multiple expert perspectives on SENTINEL development.

Create sophisticated, interactive data visualizations using D3.js. Use for custom charts, network visualizations, or when Recharts/charting libraries are insufficient.

Use when search queries need better recall through query expansion - generates multiple query variants, retrieves with each, and fuses results using RRF for improved retrieval quality especially with ambiguous or under-specified queries

World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, and modern data stack. Includes data modeling, pipeline orchestration, data quality, and DataOps. Use when designing data architectures, building data pipelines, optimizing data workflows, or implementing data governance.

Spec-First Development with OpenSpec for Spring Boot.Align on specifications before implementation begins.

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.

Kelvin Garr's personal AICA brand identity and implementation framework. Use ONLY when building Kelvin's personal sites, portfolio, or AICA-branded projects. Features fixed visual identity (black glass + gold circuits + Space Grotesk) and Next.js 14 implementation guide. For client work with AICA methodology but their branding, use design-guide-updated instead.

Expert assistant in free and open-source licenses (FOSS). Helps users choose the most suitable free/open license for their creations through a guided questionnaire. Use when user asks about open-source licensing, GPL, MIT, Apache, Creative Commons, copyleft, permissive licenses, or wants to make their project open-source. Covers software licenses, Creative Commons for creative works, and region-specific licenses like CeCILL. Responds in the user's language.

RAN deployment management with Kubernetes integration, cognitive consciousness, and intelligent orchestration for scalable network deployment. Use when deploying RAN services, managing Kubernetes clusters, implementing CI/CD pipelines, or enabling intelligent deployment orchestration in 5G networks.

Write detailed product and technical specification documents for OrbitCove. Use when creating PRDs, architecture docs, data models, or UX flows.

Test-driven development with Result types. Red-green-refactor cycles using vitest-mock-extended, explicit deps mocking, and Result assertions.

This skill automatically generates a comprehensive glossary of terms from a learning graph's concept list, ensuring each definition follows ISO 11179 metadata registry standards (precise, concise, distinct, non-circular, and free of business rules). Use this skill when creating a glossary for an intelligent textbook after the learning graph concept list has been finalized.

Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpoint recommendations for overfitting.

Use when an experienced animator needs a quick reminder of the 12 principles without basic explanations