Loading...
Loading...
Found 147 Skills
Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.
Use when implementing any feature or bugfix, before writing implementation code
Take a GitHub issue, an open PR, or a plan file from plans/ and drive it to a merge-ready PR — reproduce with a failing test first, implement the fix (bugs) or feature (plans), verify against the repo's gates, and open or update the PR. Use when asked to fix an issue, implement or execute a plan, finish or land an open PR, or work through plans/issues/.
Build features and bug fixes test-first around meaningful behavior.
Use this for development.
Validate implementation plans against DRY, YAGNI, TDD principles and best practices. Use when reviewing plans from pocket-planning or another planning workflow to identify gaps, anti-patterns, and improvement opportunities before execution.
Implementiert alle offenen GitHub Issues eines Repositories vollautomatisch in einem Rutsch. Issues, die voneinander unabhängig sind, werden parallel über Subagents abgearbeitet; abhängige Issues laufen sequenziell. Jede Implementierung wird per `/tdd` test-getrieben entwickelt, über Playwright-MCP verifiziert, bei Fehlern mit `/diagnosing-bugs` analysiert und nach Caveman-Prinzipien (`/caveman`) vereinfacht. Erfolgreiche Implementierungen werden committet, der User bekommt erst nach Abschluss aller Issues eine Sammelmeldung. Nutze diesen Skill IMMER, wenn der User sagt "implementiere alle issues", "alle gh issues", "issues aus github abarbeiten", "batch implementation", "parallel issues bearbeiten", "alle offenen tickets" oder ähnliches — auch ohne explizite Nennung von Playwright/TDD/Caveman, da diese Werkzeuge zum Standard-Workflow gehören.
Implements a feature in a codebase
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the Task tool for architecturally enforced context isolation. Supports Jest, Vitest, pytest, Go test, cargo test, PHPUnit, and RSpec.
Pair programming with the AI on an already refined story. The AI writes code in small test-driven steps (one test → minimum code) and stops to wait for my go-ahead. Never commits.
Generate red-phase acceptance test scaffolds using the TDD cycle. Use when the user says "lets write acceptance tests" or "I want to do ATDD"
Drive a change through a red-green-refactor loop - failing test first, minimal code to pass, then clean up. Use when implementing a feature or fixing a bug where correctness matters and a test can pin the behavior. Says "TDD", "test first", "red green refactor", "write the test first".