單元測試

Use when tests fail intermittently. Replace arbitrary timeouts with condition polling. Eliminates flaky tests caused by timing assumptions.

Write and debug Bun tests with proper mocking, coverage, and isolation. Use when writing tests, debugging test failures, setting up test infrastructure, mocking fetch/modules, or improving test coverage.

Write failing unit tests for feature requirements (TDD style)

Ensure code quality before commits. Run lint, format, test, build. Use npm scripts: npm run lint, npm run format, npm test, npm run build. CRITICAL: All tests must pass, no lint errors, code must be formatted before committing.

Use PROACTIVELY when validating Claude Code skills before sharing or public release. Automated testing framework using multiple isolation environments (git worktree, Docker containers, VMs) to catch environment-specific bugs, hidden dependencies, and cleanup issues. Includes production-ready test templates and risk-based mode auto-detection. Not for functional testing of skill logic or non-skill code.

UX research and design toolkit including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use for user research, persona creation, journey mapping, and design validation for the PrayerMap app.

Review code changes (diffs, PRs, patches) and provide structured, actionable feedback on correctness, maintainability, and test coverage. Use when the user asks for a code review, requests feedback on a patch/PR, or wants an assessment of changes.

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization

Test quality validation detecting mesa-optimization, happy-path bias, vacuous assertions, and error-swallowing anti-patterns. Use when reviewing test files for quality issues, evaluating test meaningfulness, or ensuring tests validate behavior rather than passing trivially. Supports JavaScript, TypeScript, and Python test frameworks.

Implementation Agent: Full TDD workflow in a single context window. Writes tests, implements code, and iterates until all tests pass.

Modern Node.js backend stack: NestJS/Hono, Drizzle ORM, Vitest, TypeScript.Use when: building Node.js APIs, TypeScript backends, or serverless functions.Triggers: "nestjs", "node backend", "express", "hono", "drizzle", "vitest","typescript api", "node api", "bun".

Runs and debugs Detox E2E tests for MigraineTracker React Native app. Use when the user asks to run E2E tests, debug test failures, or investigate UI test issues. Automatically captures logs, analyzes screenshots, and diagnoses common failure patterns. Kills tests early on first failure to save time.

Enforce elite code quality standards for F3 Workout Builder. Use when writing code, reviewing changes, fixing bugs, or creating new features. Keywords: code quality, TypeScript, testing, coverage, lint, types.

This skill should be used when generating detailed experimental procedures from LA-Bench format JSONL files. It orchestrates multiple subagents to parse input data, fetch reference materials, generate procedures, validate outputs, refine results, and produce final formatted outputs. Triggered by requests to process LA-Bench data or generate experimental protocols from data/public_test.jsonl or data/private_test_input.jsonl files.

Follow these patterns when extending the OptAIC Python SDK with new domain operations. Use for adding client methods for datasets, signals, portfolios, backtests, and other resources. Covers async/sync interfaces, uploads, and long-running operations.

Bitcoin trading simulation with technical analysis (EMA/RSI/Bollinger), Monte Carlo projections, and Telegram alerts. Cambodian market focus (USD/KHR 4050).TRIGGERS: BTC backtesting, indicator calculations, Fear & Greed integration, crypto strategy development, CoinGecko/Alternative.me APIs, portfolio simulation, trailing stop optimization, Sharpe/drawdown metrics.ENTRY POINTS: btc_trader.py (365d backtest), btc_simulation.py (60d Monte Carlo), backtest_runner.py (advanced metrics).

Use when tests are failing, test quality issues were identified, or user wants to fix/improve specific tests. Accepts green-mirage-audit reports, general instructions, or can run tests and fix failures automatically. Lighter-weight than implement-feature, focused on test remediation.

Generates comprehensive unit tests and integration tests for code with test coverage analysis and edge cases

Ability to design, implement, test, deploy, and maintain software systems that meet defined requirements. Includes translating specifications into executable code, applying appropriate programming and design practices, managing changes over time, and operating software in production environments. Applies across application, platform, and infrastructure-adjacent contexts and is independent of specific languages, frameworks, or tools. Work may be performed individually or collaboratively and may be supported by automation or artificial intelligence, with human accountability retained for correctness, security, and outcomes.

테스트 생성 전체 워크플로우. "00 테스트 만들어줘", "새 테스트 추가해줘" 요청 시 자동 실행. 2개 Agent 순차 호출로 2중 검증.