Loading...
Loading...
Found 42 Skills
Used when implementing any feature or fixing bugs, before writing the implementation code
Use test-driven development for behavior-changing feature or fix work, and whenever the user mentions TDD, test-first, red-green-refactor, tracer bullets, integration tests, or public-interface behavior tests. Skip for docs-only, path-only rename, formatting-only, or purely mechanical chores unless explicitly requested.
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.
Red-green-refactor development methodology requiring verified test coverage. Use for feature implementation, bugfixes, refactoring, or any behavior changes where tests must prove correctness.
Structured TDD workflow that decomposes features into small specs and implements them one at a time through the strict red/green/refactor cycle. Use this skill whenever the user wants to build, implement, or fix something using TDD, test-driven development, or a test-first approach. Also trigger when the user says "red green refactor", "write tests first", "one test at a time", "failing test first", or asks to develop something incrementally with tests driving the design. Even if the user just says "use TDD" or "do it test-driven" alongside a feature request, this skill applies. Do NOT trigger for: running existing tests, adding tests after the fact to untested code, fixing a single failing test, or test infrastructure setup.
QA validation and fix loop workflow — validates implementation completeness then iterates fix cycles until all acceptance criteria pass and quality gates clear
TDD: enforce RED-GREEN-REFACTOR, tests before code.
Automates mock test creation for C++ projects using Google Mock (GMock) framework with consistent software testing patterns. Use when creating tests with mocked dependencies, interface mocking, behavior verification, or when the user mentions mocks, stubs, fakes, or GMock.
Test software in the style of James Bach, pioneer of exploratory testing and context-driven testing. Emphasizes skilled human investigation, heuristics-based test design, and adapting to context rather than following rigid scripts. Use when designing test strategies, performing exploratory testing, or building thinking testers.
Находит неочевидные корнеры задачи через пересечение состояний, данных, порядка действий, сбоев и параллельных изменений; превращает их в ожидаемое поведение и проверяемые сценарии. Использовать перед реализацией или ревью нетривиальной продуктовой, UX- или технической задачи; при изменении stateful/async-поведения, сохранения, синхронизации, прав, интеграций и многошаговых флоу; когда пользователь просит продумать edge cases, corner cases, крайние случаи или проверить полноту постановки. Не использовать для мелких механических правок и до выбора самой задачи или масштаба решения — сначала nodumb.
Write the minimal production code needed to make all existing failing tests pass. No extra features, no test modifications, no refactoring. Use after tests are written and confirmed failing.
Methodology for effective AI-assisted software development. Use when helping users build software with AI coding assistants, debugging AI-generated code, planning features for AI implementation, managing version control in AI workflows, or when users mention "vibe coding," Cursor, Windsurf, or similar AI coding tools. Provides strategies for planning, testing, debugging, and iterating on code written with LLM assistance.