單元測試

Use when looking up information from the latest Docusaurus documentation at https://docusaurus.io/docs

Testing patterns for Composable Svelte. Use when writing tests, using TestStore, mocking dependencies, or testing reducers and effects. Covers the send/receive pattern, mock implementations, testing composition strategies, and testing best practices.

Automatically applies when evaluating LLM performance. Ensures proper eval datasets, metrics computation, A/B testing, LLM-as-judge patterns, and experiment tracking.

Use when integrating Paddle payments, setting up subscriptions, configuring webhooks, or debugging billing issues. Covers sandbox testing and production deployment.

Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales. Use when uncertain about scalability, edge cases unclear, or validating architecture for production volumes.

Use this skill when VSCode extensions fail to build in nix configuration, when adding new VSCode extensions, or when debugging extension-related build errors. Handles systematic search across nixpkgs, vscode-marketplace, and open-vsx sources with incremental testing.

Deploys ProAgentic DfX (H2 Tank Designer) using the full CI/CD pipeline. Runs all quality gates (lint, typecheck, tests, coverage, E2E) then deploys to Vercel. Use when deploying to staging or production, or when running the full CI pipeline locally.

Automatically invoked when running tests, analyzing test results, or verifying code changes. Ensures tests are run appropriately and results are interpreted correctly.

Coordinate parallel agent execution using ACE Framework for LiveMetro React Native development. Use when implementing features with 3+ independent subtasks (UI + API + Firebase + Tests).

ALWAYS apply this skill for ANY software development task. Triggers: implement, create, build, add, write, code, function, class, component, API, feature, fix, bug, debug, refactor, improve, clean, review, check, design, architect, structure, test, endpoint, module, service, handler, controller, model, schema, migration, deploy, configure. This skill enforces kadoppe's development principles for all coding work.

Run tests for the Nomos provider project with comprehensive coverage reporting. Use this when asked to run tests, check code quality, or verify test coverage.

Git ignore configuration patterns for MetaSaver monorepos. Includes 10 required pattern categories (dependencies, build outputs, environment files with security-critical .env and .npmrc exclusions, logs, testing, IDE, OS, database, cache, temporary files). Use when creating or auditing .gitignore files to prevent secret leakage and repository pollution.

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.

Audit or critique a plan for feasibility, risks, missing steps, and test coverage. Use when the user asks to review, audit, or critique a plan or process.

Guides evaluation-driven development (EDD) process for agent skills. Use when setting up skill testing workflows, creating skill evaluation scenarios, or establishing Claude A/B feedback loops for skill validation. Provides development methodology, not content guidance.

Maintain and improve code quality using PHPInsights without decreasing quality thresholds. Use when PHPInsights fails, cyclomatic complexity is too high, code quality drops, or when refactoring for better maintainability. Always maintains 93% complexity for src/ and 95% for tests/, plus 100% quality/architecture/style scores.

Enforce strict TDD workflow for all development tasks. Use when implementing new features, fixing bugs, or refactoring code. Ensures comprehensive test coverage (unit, integration, e2e) before writing implementation code. Activates automatically for all coding tasks unless explicitly authorized to skip testing.

Automated QA testing for Radulator's 18 medical calculators across radiology, hepatology/liver, and urology specialties. Tests accuracy, collects browser diagnostics, generates Playwright tests, and manages three-branch Git workflow (dev1→test1→main). Use when testing Radulator calculators, reviewing PRs with qa label, verifying medical formulas, generating test reports, or creating comprehensive test suites.

Phase 2 of disciplined development. Creates implementation plans based onapproved research. Specifies file changes, function signatures, test strategy,and step sequence. Requires human approval before implementation.

Analyzes algorithmic trading backtest results from Jupyter notebooks and generates summary reports. Use when the user wants to analyze or summarize backtest notebooks.