單元測試

Screenshot-based regression testing with Playwright. Compares rendered pixels against baseline PNGs. Use when working with stories, *.visual.spec.ts files, or baseline screenshots. Auto-apply when editing files in stories/ or *.visual.spec.ts.

This skill should be used when the user asks to "modify OAPS internals", "add a new subsystem", "understand OAPS architecture", "add a CLI command", "write OAPS tests", "create builtin hooks", "add a hook rule", "debug OAPS", "fix OAPS bug", "extend OAPS", "navigate the OAPS codebase", "understand the spec system", "understand hooks", "OAPS CI failing", or when working on src/oaps/ code, oaps.cli._commands, oaps.hooks, oaps.spec, oaps.config, oaps.repository, or oaps.artifacts packages.

Breaks features into 3-8 manageable phases with clear deliverables and success criteria. Use when planning feature implementation to create testable, independently committable work units.

Guide for implementing features using Test-Driven Development (TDD) methodology. Use when: (1) User requests to implement a feature using TDD, (2) User asks to write tests first before implementation, (3) User mentions Red-Green-Refactor cycle, (4) Starting a new feature that requires systematic testing. This skill provides step-by-step TDD workflows, concrete test patterns, and best practices for writing tests before implementation in TypeScript/React projects using Vitest.

Follow these patterns when implementing quant domain resources like Dataset, Signal, Alpha, Portfolio, Strategy, Universe, Backtest, or MonitoringRun in OptAIC. Use for creating DB models, DTOs, services, and tests for trading-specific entities.

A comprehensive skill for the Go Gin web framework including routing, middleware, binding, and testing

Comprehensive code quality verification workflow that checks linting, formatting, type safety, tests, and build before committing code. Uses parallel agent execution for maximum speed. Non-destructive - only reports issues without making changes.

State-of-the-art debugging agent with hypothesis-driven analysis, automatic code instrumentation, git worktree isolation, and browser automation. Use when debugging errors, stack traces, unexpected behavior, performance issues, failed tests, race conditions, or hard-to-reproduce bugs.

Generate GitHub Actions workflows for CI and internal testing track deployment (Option D - Split Workflows)

Build production Rust CLIs with Clap: subcommands, config layering, validation, exit codes, shell completions, and testable command surfaces

Use when building web UIs with Next.js 15+ and React 19 - covers Server Components, App Router, testing with Vitest and Playwright, and accessibility standards

Run dotnet test, capture failed test cases, and generate a rerun filter plus a markdown failure summary. Use when test runs fail and you need a focused rerun command or a compact failure report.

Testing patterns and utilities for PepMetrics. Use when writing or debugging tests.

Maestro E2E testing patterns for React Native. Use when implementing end-to-end tests.

Test and debug webhook integrations on localhost using Hookdeck CLI. Use when developing webhook handlers, testing webhook delivery locally, debugging webhook failures, or setting up team webhook development workflows.

Generate adversarial inputs, edge cases, and boundary test payloads. Use when testing input robustness, finding edge case failures, or stress-testing LLM boundaries.

Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts. Use when writing, creating, authoring, generating, or developing bash scripts, shell scripts, or automation. Also triggers for learning bash best practices, understanding defensive programming patterns, implementing error handling, ensuring portability, following shellcheck recommendations, or applying production-grade bash standards. Helps with CI/CD scripts, system utilities, deployment automation, and production bash code.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Build async APIs with FastAPI, including endpoints, dependency injection, validation, and testing. Use when creating REST APIs, web backends, or microservices.

Comprehensive guide for building functional tools for LiveKit voice agents using the @function_tool decorator. Use when creating tools for LiveKit agents to enable capabilities like API calls, database queries, multi-agent coordination, or any external integrations. Covers tool design, RunContext handling, interruption patterns, parameter documentation, testing, and production best practices.