Enforces writing a failing test before implementation code for features and bugfixes.

Requires running verification commands and showing output before claiming work is complete or passing.

Replace unsafe as type assertions in tests with Shoehorn for partial test data.

Build features or fix bugs test-first using red-green-refactor cycles.

Benchmark coding agents like Claude Code, Aider, and Codex head-to-head on pass rate, cost, and time.

DB不要のサンドボックスAPIテストで、AIが書いたコードのリグレッションを自動検出する。

パフォーマンスの基準値を測定し、PR前後の回帰や技術スタックの比較を行う。

デプロイ後にブラウザ自動化でビジュアルテストとUI操作の検証を自動実行する。

Trace user-facing button flows to find bugs where features work alone but cancel out or leave inconsistent state.

Escribir pruebas E2E estables con Playwright, Page Object Model y ejecución en CI/CD.

Evaluar sesiones de Claude Code con un marco formal de evals orientado a desarrollo.

Escribir pruebas Go con tablas, benchmarks, fuzzing y cobertura siguiendo TDD.

Escribir pruebas Kotlin con Kotest, MockK, coroutines, propiedades y cobertura con Kover.

Desarrollar en Laravel guiado por pruebas con PHPUnit o Pest, factories y fakes.

Verificar proyectos Laravel con linting, análisis estático, cobertura y escaneos de seguridad.

Escribir pruebas Python con pytest, fixtures, mocks, parametrización y cobertura exigida.

Test-drive Quarkus 3.x features and bug fixes using JUnit 5, Mockito, and REST Assured.

Write Rust unit, integration, async, property-based, and mocked tests with coverage, TDD-style.

Test-drive Spring Boot features with JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo coverage.

Enforce test-driven development with 80%+ coverage across unit, integration, and E2E tests.

Test local web apps with Playwright, checking UI behavior, capturing screenshots, and reading browser logs.

Tests and debugs browser apps via Chrome DevTools, inspecting DOM, console, network, and performance.

Drives code changes through red-green-refactor tests to prove behavior and catch regressions early.

Drive a real browser to take screenshots, read console and network output, and verify pages interactively.

Write QA acceptance criteria and manual validation plans with explicit pass/fail evidence for a feature.

Drives a real browser for signed-in sites, forms, screenshots, web QA, and scraping.

Runs manual QA and a single gate review of completed work before PR handoff.

Runs visual QA with HIG checklists, light and dark captures at multiple widths, and PASS/FAIL verdicts.

Design A/B and multivariate experiments with clear hypotheses and implementation plans for growth.

Diagnose and improve conversion rates on marketing pages and lead capture forms.

Plan and document method validation under ICH, USP, and ISO 17025 for lab analytical procedures.