Explorar skills

Esta skill abrangente cobre a acessibilidade WCAG 2.1/2.2 AA, incluindo auditorias, remediação, padrões ARIA, testes com leitores de tela, contraste de cores, navegação por teclado, acessibilidade móvel e cognitiva, conformidade legal e pipelines de teste CI/CD.

Write high-quality GitHub issues following a consistent structure. Use when creating or rewriting GitHub issues for any project. The skill enforces a standard format with: problem statement, background context, proposed solution or approach, definition of done, and a thorough test plan covering unit tests, integration tests, E2E tests, and manual verification. Triggers on phrases like "create a gh

Habilidade oficial PGYER (蒲公英) para distribuição beta de aplicativos iOS, Android e HarmonyOS. Permite fazer upload de apps para testes beta, obter links de instalação/QR codes, consultar histórico de versões, gerenciar testadores e integrar com CI/CD.

Use ao desenvolver, depurar, implantar ou manter qualquer instância ou fork do CTFd. Aborda problemas como questões de stack Docker, desenvolvimento de plugins, erros CSRF 302, personalização de temas, migrações de banco de dados, configuração incorreta de proxy nginx, armadilhas do SQLAlchemy 1.4, infraestrutura de teste pytest ou respostas de API 500.

A double-loop learning execution review skill. Reviews the execution history after a task is completed and turns it into a concise retrospective, handoff, or improvement memo. Use this whenever a coding, writing, research, planning, debugging, or operational task has just finished; whenever files, commands, tests, or deliverables were produced; whenever the user asks to summarize what was done, re

Clean code, robust architecture, no test slop. Foundational skill for high-quality software engineering, code structure, and reviews.

Plan and execute large multi-step, multi-stack changes with contract-first waves, parallel worker ownership, user approval gates, ordered integration, and final verification/docs updates. Use only when the task spans multiple areas (for example frontend, backend, tests, errors, docs) or has dependency-heavy sequencing.

Disciplined 9-phase workflow for auditing and improving a project's skill library — discover, audit, candidates, edits, research, structure, QA, memory. Invoked by /skill-forge or when user asks to improve/audit/tune skills.

Scaffold a new feature with View, ViewModel, and tests following ios-std conventions.

Revisa a configuração global ~/.claude/ do usuário em relação aos documentos oficiais de melhores práticas do Claude Code e fontes curadas, gerando um relatório datado e rascunhos de patches em ~/.claude/bp-review/ sem modificar arquivos originais. Complementa o claude-health ao rastrear novos recursos, configurações obsoletas e recomendações alteradas.

Execute a task with automated verification. Classifies the goal, builds the cheapest possible verifier (deterministic test, regex/command check, LLM judge, or a hybrid of these), runs the work, and iterates until the verifier passes or a hard cap is hit. Use when a task has a checkable success criterion and you want confidence the output actually meets it — e.g. "write a function that does X", "dr

Pre-PR verification pipeline with plan validation, build, types, lint, test, security, diff review, and consistency checks. Verification gate — use before creating a PR or merging.