Adversarial verification of one SDD Composy task in verify_required: reproduce every claim with fresh commands, build the truth table, refute stale evidence, and produce the verdict that gates complete. Use when review is done and the task claims to be finished — 'verificar a TASK-003', 'a task está pronta mesmo?', 'is this task really complete'. Do NOT use for QA, code review, or a general 'verify my work' outside an SDD task.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
This portable skill is the adversarial gate for a task in verify_required: independently
reproduce every required claim with a fresh command, build the truth table, and attempt to refute
the earlier evidence. Read templates/verdict.md and render it, keeping its frontmatter keys and
headings exactly (translate prose only).
Language: before writing human-facing prose, run scripts/sdd_language.py <repo-root> and use the persisted language; on not_initialized, return it with next_action: run_init. Localization rules: references/language.md.
Record confined evidence paths, SHA-256 digests, exit codes, and environment, and keep generation
and verification actors separate. Use only PASS, FAIL, STALE, ENVIRONMENT_FAILURE, and
NOT_RUN verdicts; classify an environment failure separately from a failed test. Reject stale,
contradictory, missing, or hash-inconsistent evidence.
Only all-fresh PASS claims with non-blocking QA/review and explicit human approval approve the
verdict (verdict: COMPLETE), record scripts/sdd_tasks.py evidence <state> <TASK-ID> verify --status approved and trace --status consistent, and request the guarded task transition
verify_required -> complete (the COMPLETE workflow stage); every other outcome sets the
verdict to REJECTED, records verify --status rejected, and moves the task to
rejected --reason <blocker>, with a sanitized blocker and next action. Do not silently change claims, contracts, or source,
and do not stop user-owned services.
references/verification.md — writing the verdict (verdict semantics, staleness, refutation).Safety: Do not commit, push, or publish. Do not read or expose .env, credentials, tokens, private keys, certificates, or fleet environment files. Full contract: references/safety.md.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Accessibility auditing and remediation skill for Vue 3 + Reka UI. Use when reviewing components, verifying WCAG 2.1 AA, fixing ARIA issues, or validating keyboard navigation in Reka UI components.
The English summary is being prepared. Showing the original description.
Infraestrutura para IA — GPU, servidores MCP, gateway de LLM, pipeline de inferência, custo de token, cache semântico e observabilidade de modelo. Use quando o usuário disser "GPU", "MCP server", "LLM", "inferência", "modelo", "gateway de IA", "custo de token", "rate limit da API de IA", "self-host de modelo".
The English summary is being prepared. Showing the original description.
Escreve texto alternativo e descrição de imagem para peças de rede social. Use quando o usuário disser "alt text", "texto alternativo", "descrição da imagem", "acessibilidade da peça", "descrever para leitor de tela", ou automaticamente antes de qualquer publicação. Obrigatório em todas as peças — em carrossel, um por slide.
The English summary is being prepared. Showing the original description.
Organiza, compara e seleciona entre as variações geradas, e publica a grade de comparação como Artifact para aprovação do time. Use quando o usuário disser "qual dessas", "comparar as variações", "escolher a melhor", "mostrar as opções", "montar grade de aprovação", ou após qualquer lote de geração. Selecionar é trabalho, não detalhe.
The English summary is being prepared. Showing the original description.
Aumenta resolução e qualidade de imagem via Freepik/Magnific, ou orienta o processo manual quando não há chave. Use quando o usuário disser "upscale", "melhorar a resolução", "a imagem está pixelada", "Magnific", "Freepik", "aumentar a imagem", "imagem pequena demais". Gasta crédito — exige confirmação.
The English summary is being prepared. Showing the original description.
CI/CD e automação — GitHub Actions, Terraform, OpenTofu, Ansible, n8n. Use quando o usuário disser "pipeline", "CI/CD", "GitHub Actions", "workflow", "terraform", "ansible", "n8n", "automatizar", "deploy automático", "IaC".
The English summary is being prepared. Showing the original description.