單元測試

React Testing Strategy. Use when writing tests, reviewing test coverage, or setting up testing.

Use when testing plans or decisions for blind spots, need adversarial review before launch, validating strategy against worst-case scenarios, building consensus through structured debate, identifying attack vectors or vulnerabilities, user mentions "play devil's advocate", "what could go wrong", "challenge our assumptions", "stress test this", "red team", or when groupthink or confirmation bias may be hiding risks.

Design, validate, and orchestrate development tools with reusable patterns, composition rules, and evidence-backed tests.

Validates test coverage and quality by checking behavior focus, identifying gaps, and ensuring >80% statement coverage. Use when task file is in testing/ directory and requires test validation before marking complete. Adds minimal tests for genuinely missing edge cases.

Use when you have implemented an equivariant model and need to verify it correctly respects the intended symmetries. Invoke when user mentions testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if model is actually equivariant, or diagnosing why equivariant model isn't working. Provides verification tests and debugging guidance.

Run the complete test suite for connectrpc-axum. Use when the user asks to run tests, verify changes, or check if the code works.

Use proactively when you need to implement features or fix bugs using strict Test-Driven Development (TDD) methodology. This agent should be activated for any coding task that requires writing new functionality, refactoring existing code, or ensuring comprehensive test coverage, but should not be used for any design-related tasks. The agent excels at breaking down complex requirements into testable increments and maintaining high code quality through disciplined TDD cycles. Use this agent proactively or if the user mentions 'TDD', 'tdd' or 'Test Driven Development'.

E2E testing with Playwright MCP for browser automation, test generation, and UI testing. Use when discussing E2E tests, Playwright, browser testing, UI automation, visual testing, or accessibility testing. Supports TypeScript tests and Go/HTMX web applications.

Create test cases for functions and modules. Use when implementing TDD or improving coverage.

Test agent delegation patterns to verify hierarchy and escalation paths. Use after modifying agent structure.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Stratégie de Tests Python. Use when writing tests, reviewing test coverage, or setting up testing.

Use to stress-test predictions by assuming they failed and working backward to identify why. Invoke when confidence is high (>80% or <20%), need to identify tail risks and unknown unknowns, or want to widen overconfident intervals. Use when user mentions premortem, backcasting, what could go wrong, stress test, or black swans.

Provides test design patterns, coverage strategies, and best practices for comprehensive test suite development

MANDATORY when: tests fail, CI fails, CI/CD fails, ci.yml fails, user provides CI log URL. Investigates failures, fixes iteratively until passing.

Use when making predictions or judgments under uncertainty and need to explicitly update beliefs with new evidence. Invoke when forecasting outcomes, evaluating probabilities, testing hypotheses, calibrating confidence, assessing risks with uncertain data, or avoiding overconfidence bias. Use when user mentions priors, likelihoods, Bayes theorem, probability updates, forecasting, calibration, or belief revision.

Use when starting technical work requiring structured approach - writing tests before code (TDD), planning data exploration (EDA), designing statistical analysis, clarifying modeling objectives (causal vs predictive), or validating results. Invoke when user mentions "write tests for", "explore this dataset", "analyze", "model", "validate", or when technical work needs systematic scaffolding before execution.

[CLAUDE CODE ONLY] Leverage Codex CLI for AI peer review, second opinions on architecture and design decisions, cross-validation of implementations, security analysis, and alternative approach generation. Requires terminal access to execute Codex CLI commands. Use when making high-stakes decisions, reviewing complex architecture, or when explicitly requested for a second AI perspective. Must be explicitly invoked using skill syntax.

Use Codex CLI in full-auto mode to fix issues iteratively until tests pass. Autonomous debugging and test-fixing loop with sandbox safety.

Generate production-ready project boilerplates with linting, testing, and minimal dependencies for common stacks.