Explorar skills

Depura, testa e soluciona problemas em servidores MCP. Verifica esquemas de ferramentas, testa chamadas e diagnostica falhas de conexão. Sem dependências.

Use at the start of every conversation that touches a non-trivial code or design task. Establishes the ssep skill-matching matrix (4 specialized skills — reviewing-spec-and-policy, reviewing-design-fidelity, improving-feature-completeness, running-integration-tests) and requires the matrix to be evaluated BEFORE any other action, including clarifying questions, file reads, or implementation. Trigg

Debug issues through structured investigation, failing test creation, and targeted fixes. Use when the user provides an error message, traceback, steps-to-reproduce, or describes unexpected behavior.

Dynamic Expert Council QA system. Selects domain-relevant expert personas to review deliverables before final delivery. 3 tiers with build/review mode toggle. Works with any AI assistant.

Audit the latest GitHub Actions workflow runs on the current branch/PR for warnings, errors, failures, deprecation notices, and other log noise — then fix what's fixable in-repo (workflow YAML, configs, source, tests). Hands commit + push back to the developer. Use after CI finishes and before merge, or whenever the user asks about failing/noisy CI — phrasings like "audit the PR", "why did CI fail

Performs comprehensive codebase audit checking architecture, tech debt, security vulnerabilities, test coverage, documentation, dependencies, and maintainability. Use when auditing a project, assessing codebase health, running security scans, checking for vulnerabilities, reviewing code quality, analyzing tech debt, or asked to audit/analyze the entire codebase.

Pacote de habilidades JUnit 5 para criar, depurar, modernizar, documentar e rotear fluxos de trabalho de teste JVM.

Generate probe-skeleton YAML files at `lineage/{repo}/probes/{P-NNN}.yaml` from `feature-flows.yaml`'s uncovered test-matrix cells. Each skeleton carries the feature_id + test_class + cross-references + a TODO-marked arrange/act/observe/assert block the maintainer fills in. Accelerates probe corpus growth — slice 4 of dynamic-verification ADR. Local-only per APPROACH.md section 5 rule 12.

Esta skill busca e exibe o conteúdo mais recente em alta, gerando itens Top com base em uma taxa de cliques estimada, e não na popularidade bruta. Ela suporta a consulta de tópicos quentes atuais, status de serviço e conteúdo agrupado, podendo solicitar aos usuários a configuração de tarefas agendadas.

Use when refactoring AI-generated code projects (vibe-coded apps, Claude/Cursor/GPT output) that have visual inconsistency, code duplication, lack of design system, or structural problems. Trigger on "refactor this AI project", "fix the design", "clean up this vibe-coded app", or when inheriting an AI-generated codebase.

Compresses verbose text into the shortest precise phrasing that preserves every constraint and leaves zero ambiguity. Use whenever the user wants to shorten, compress, tighten, distill, or cut down any text — CLAUDE.md sections, README files, AGENTS.md personas, CONTRIBUTING.md, commit messages, error messages, package descriptions, or any prose that says too much with too many words. Also use whe

Use before committing or opening a pull request — reviews staged changes as a principal engineer for correctness, edge cases, and logic flaws. Always invoke this before creating a PR.