數據與 AI

Queries cached external documentation and blog content for authoritative, up-to-date information. Sources include Claude Code docs, engineering blog, and configured knowledge bases with 24-hour TTL caching. Use when you need current information about Claude Code features, hooks, or best practices. Do NOT use for general coding questions - rely on training knowledge or web search instead.

Validates audit evidence artifacts for completeness, timeliness, relevance, and authenticity. Reviews screenshots, logs, configurations, and policies against control requirements.

Verifies code follows Clean Architecture principles in Polibase. Activates when creating or modifying src/domain, src/application, src/infrastructure, or src/interfaces files. Checks dependency rules, entity independence, repository patterns, DTO usage, and type safety.

Create, manage, and apply database migrations using Doctrine ODM for MongoDB. Use when modifying entities, adding fields, managing database schema changes, creating repositories, or troubleshooting database issues.

Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini operations.

Zero-copy deserialization, async I/O patterns, lifetime management, memory-efficient parsing, and safe handling of unsafe code for SSTable parsing. Use when working with performance optimization, memory efficiency, async/await, borrowing/lifetimes, zero-copy patterns, or memory usage under 128MB target.

Implement technical plans methodically with phase-by-phase execution and verification checkpoints. Use this skill when following a detailed implementation plan that has phased changes and success criteria. The skill guides through each phase, verifies completion, and pauses for human confirmation before proceeding to the next phase.

Create OpenCode plugins using @opencode-ai/plugin SDK. Use when user wants to BUILD a plugin in .opencode/plugin/ or ~/.config/opencode/plugin/ - for custom tools, event hooks, LLM parameter control, auth providers, or tool execution interception. DO NOT use when modifying OpenCode source code (packages/plugin, packages/opencode, etc.) or working on OC internals - those are core development, not plugin creation.

Enterprise JavaScript for Node.js and browser: Node.js 22.11.0 LTS (Jod), npm 11.x, ES2025 features, async operations, module systems, package management; activates for server-side development, scripting, tooling, package management, and runtime optimization.

Best practices for Ruby on Rails development across models, controllers, services, and background jobs

Collect a single Schwab MCP data snapshot (accounts, quotes, indicators, option chains) with a five-minute cache so trading agents can reuse consistent inputs. Use whenever an options persona needs fresh risk, market, or chain data before recommending trades.

Automatically assigns GitHub issues to appropriate GitHub Copilot agents based on issue type, labels, and content. Triggers on "assign agent", "who should work on this", "route this issue", or after creating issues via github-mcp-orchestrator.

제조업 SME 입찰 프로세스 자동화 - 공고 수집, AI 매칭, 제안서 생성

Use when text contains vague language ("many", "substantially"), passive voice overuse, or lacks quantitative specificity - provides 30+ before/after examples for active voice, precise terminology, and appropriate hedging

Expert guide for testing Next.js applications with Playwright, Jest, and React Testing Library. Use when writing tests, debugging test failures, or setting up test infrastructure.

Comprehensive test writing, execution, and failure analysis. Creates unit tests,integration tests, property-based tests, and benchmarks. Analyzes test failuresand improves test coverage.

Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files for Claude 4.5 models - applies documented Anthropic best practices systematically instead of inventing improvements

Create properly formatted Claude Code skills with YAML frontmatter, directory structure, and best practices. Use when creating new skills, converting documentation to skills, or learning how to write skills.

Multi-agent coordination, tier approvals, decision logging

Expert knowledge for deploying and operating Composable Rust applications in production. Use when setting up database migrations, configuring connection pools, implementing backup/restore procedures, tuning performance, setting up monitoring and observability, or handling operational concerns like disaster recovery and production database management.