Explorar skills

Use when Claude Code needs to refactor code, tests, docs, specs, or project structure while preserving active SpecDD behavior.

Create branded blog header images with strict layout rules, safe zones, and brand color application. Python/Pillow implementation with 75% safe zone rule for mobile-safe rendering.

Use when Claude Code needs to explain a SpecDD spec, target, behavior, or effective spec chain without editing it.

Write tests for the Travmaskinen codebase — backend (pytest, async, FastAPI), frontend (Vitest + React Testing Library), or E2E (Playwright). Use this skill whenever writing new tests, adding test coverage, implementing TDD red-green-refactor cycles, or when the user says "write tests", "add tests", "test this", "cover this", "TDD", or asks for test coverage on any module. Also triggers when imple

Test accountability policy. All failures belong to the current changeset. Commits must include test results. No failures on main.

Generate images with transparent backgrounds using difference matting technique. Use when creating assets with transparency, extracting alpha channels, batch generating transparent images via Vertex AI, or working with PNG transparency.

Esclareça o comportamento com tabelas de exemplos concretos antes ou durante a implementação. Use quando os requisitos contiverem termos vagos, o comportamento depender de múltiplas condições, surgirem casos de borda ou o usuário solicitar exemplos de uma funcionalidade.

Fetch Claude Code release notes and generate a personalized feature report (MD + HTML) based on your usage patterns. Use when asked about new features, latest updates, release notes, or feature recommendations. Invokable via /whatsnew.

Use when Claude Code needs to derive, add, update, or assess tests from active SpecDD specs.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when the user wants to prevent broken code from being pushed, block git push when tests fail, run tests before push, set up push protection, or add a safety net against pushing untested code. Covers any request to gate pushes on test results — whether they mention "hook", "pre-push", or just describe wanting to stop bad code from reaching the remote. Also handles auto-fix/auto-repair of test f

Revisar o branch atual em busca de bugs, adequação à intenção e cobertura de testes; executar ou escrever testes; fazer commits focados; abrir ou atualizar um PR.