單元測試

Framework for capturing, storing, and comparing AI evaluations to measure consistency and completeness.Use when: comparing reviews, measuring evaluation quality, running reproducibility tests,auditing AI outputs, validating findings across runs.Triggers: "compare evaluations", "measure consistency", "evaluation framework", "reproducible review","compare reviews", "validate findings", "audit evaluation".

Playwright testing with autonomous test agents (planner, generator, healer) and visual regression testing

Systematic refactoring with small-step discipline. Use when user says 'refactor', 'clean up', 'restructure', 'extract', 'rename', 'simplify', or mentions code smells. Enforces one change → test → commit cycle. For structural improvements, NOT style/formatting (use /lint). NOT for adding features or fixing bugs.

S16Z PMS shared library development skill. Use when creating or maintaining shared libraries in the libs/ directory. Covers configuration management with registerAs, DTO validation with class-transformer, HTTP client patterns with BaseHttpClient, Prisma transaction handling, and testing strategies. Triggers when working with libs/ directory, creating new libraries, implementing API clients, or setting up shared services.

Systematic debugging methodology - scientific approach to finding and fixing bugs using hypothesis testing, isolation, and root cause analysis. Based on the Arcanean principle that understanding precedes execution.

Generates package.json with all necessary dependencies, dev dependencies, and scripts. Fetches latest package versions from npm registry.

Fix test assertion failures, timeouts, and test suite failures from dependency updates. Use when Jest, pytest, unittest, or other test checks fail.

Creates test documentation (testing-strategy.md + tests/README.md). Establishes testing philosophy and Story-Level Test Task Pattern. L2 Worker in ln-100-documents-pipeline workflow.

This skill should be used when the user asks "refactor code", "improve code quality", "use refactor plugin", "run /refactor", or needs guidance on automated iterative code refactoring with test coverage, architecture review, and clean code improvements.

Generates live campaign ad headlines and bodies across urgency, discount, social proof, testimonial, and live-now motifs.

Automate test writing for AgentOS project with proper conventions. Applies layer-specific test patterns (Unit/E2E/Electron-E2E) based on code location and generates consistent test code following Given-When-Then structure.

Create or edit Codex execpolicy .rules files (allow/prompt/forbid commands, define prefix_rule patterns, add match/not_match tests) and validate them with codex execpolicy check. Use when a user mentions Codex rules, execpolicy, command policies, allowlists/denylists, or controlling which commands Codex can run, and when scope (global vs project) must be clarified.

This Claude Skill can be used to build, test, and automate iOS apps. 13 production-ready scripts including ultra token-efficient xcode build automation, log monitoring, intelligent simulator selection, and accessibility-driven UI simulator navigation.

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).

Comprehensive PR review using multi-agent swarm with specialized reviewers for security, performance, style, tests, and documentation. Provides detailed feedback with auto-fix suggestions and merge readiness assessment.

Spec-driven development methodology for ANY software project.USE WHEN developing features, fixing bugs, creating skills, or preparing releases.USE WHEN user mentions specs, testing, release process, change proposals, or deployment.Provides flexible spec tooling guidance but STRICT release discipline.

Before making any code changes, read AGENT.md/agent.md and changelog variants (CHANGELOG*.md, HISTORY.md, RELEASES.md). After changes, update both agent + changelog files with a "Raouf:" template entry. If blocked, search latest official developer docs and use all available tools/MCPs.

Testing suite with benchmarking for version-to-version performance comparison

Configure TraitorSim game parameters including regional rule variants (UK/US/Australia), recruitment mechanics, end-game modes, tie-breaking, and player counts. Use when setting up simulations, testing rule variants, comparing configurations, or when asked about game rules, regional variants, or simulation parameters.

Playwright E2E testing with Page Object pattern, web-first assertions, and proper locators. Triggers on playwright, e2e, page object, getByRole.