單元測試

Post-training model validation workflow: gating, backtesting, walk-forward validation, deployment decisions. Trigger after GPU training completes.

Auto-load when writing tests. Provides TDD workflow, test structure patterns, and common testing idioms.

MCP (Model Context Protocol) server evaluation guide for creating comprehensive test suites with read-only, independent questions. Use when building MCP servers, creating evaluation frameworks, or testing LLM tool usage patterns.

Run and evaluate the Skillset smoke test (aliases, sets, and skill invocation) and interpret its JSON reports. Use this when validating $skill/$set behavior or checking Claude Code/Codex headless runs.

Orchestrates test execution for the Nomos monorepo following TESTING_GUIDE.md standards. Use this when running tests, debugging test failures, validating coverage, or executing verification checklists from AGENTS.md files.

Generate pytest tests for Python modules with parametrization, shared fixtures in conftest.py, and minimal mocking. Use when creating unit tests, test suites, or improving test coverage. Follows 1-1 file correspondence and real object testing principles.

Test and validate DyGram machines using CLI interactive mode. Step through execution, provide intelligent responses, debug behavior, and create test recordings.

Defines project-wide code conventions for magic number elimination, constant usage, performance optimization, and coordinate system separation. Use when implementing, testing, or reviewing code to ensure consistency across the codebase.

World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media), multiple output formats (XML/Claude/ChatGPT/Gemini), quality validation gates, and contextual best practices from OpenAI/Anthropic/Google. Supports both core and advanced modes with testing scenarios and prompt variations.

Test-driven development guidance for Tetris game logic. Use when writing tests, fixing test failures, improving test coverage, or implementing game mechanics. Auto-triggers on phrases like "write a test", "test this function", "improve coverage", "fix failing tests", or "add game logic". Emphasizes Result<T,E> pattern and property-based testing with fast-check.

Query and analyze logs using Loki and LogQL. Provides patterns for correlation ID tracing, error investigation, and service debugging using HuleEdu's structured logging. Integrates with Context7 for latest Loki documentation.

Safe database migration procedures with backward compatibility, backups, and rollback strategies. Use when creating, modifying, or dropping database schemas. Covers migration creation, testing, execution, and rollback.

Claude Code 작업 결과를 6개 영역(분석, 계획, 구현, 리뷰, 검증, 테스트)에서 평가하고 구체적인 피드백을 생성합니다. 결과 수집, 영역별 점수화, P0/P1/P2 우선순위 피드백, 자기비판, 성찰, 재평가 사이클을 통해 품질을 개선합니다. Use when evaluating code results, generating feedback, reviewing implementation quality, assessing test coverage.

API testing, documentation, and development tools

Evaluate WaveCap audio analysis and transcription accuracy. Use when the user wants to run regression tests, compare transcriptions against ground truth, calculate WER/CER metrics, or assess overall system quality.

Use when writing Vague (.vague) files - a declarative language for generating realistic test data with superposition, constraints, and cross-references

Start a single Gambit game client that connects to 127.0.0.1:1234. Use when the user wants to run a client, test client functionality, or manually connect to a server.

This skill should be used when working with xterm.js terminal implementations, React-based terminal applications, WebSocket terminal communication, or refactoring terminal-related code. It provides battle-tested patterns, common pitfalls, and debugging strategies learned from building production terminal applications.

Create a new feature branch, implement feature work, commit with commit-message, and open a PR with gh using standardized templates. Use when the user asks to develop a new feature, start a feature branch, or open a feature PR; also when asked to draft a feature PR based on the latest commit message.

Runs tests and handles failures. Triggered when: test execution, verification, test failures, CI checks.