DevOps e Infra

Interview someone to clarify fuzzy thinking — sharpens voice-to-text brain dumps into precise articulation through synthesis and friction. Used by facilitation workflows.

Multi-agent work execution using Agent Teams. Parses a plan into tasks, summons swarm workers that claim and complete tasks independently, and runs quality gates before completion.

Realiza auditoria de segurança defensiva pré-entrega para projetos Claude Code, cobrindo web, mobile (MASVS), cloud/IaC, web3 e ML/AI em 18 linguagens e 34 frameworks. Gera um relatório Markdown com score, attack chains, achados detalhados e fixes copy-paste, ativada quando o desenvolvedor solicita uma revisão de segurança antes do deploy.

Shape rough ideas into clear, actionable work definitions. Use this skill whenever someone has an unstructured idea that needs to become a concrete work definition — feature requests, bug reports, PRDs, customer feedback, Slack threads, stakeholder asks, or vague "we should do X" statements. Trigger phrases include "shape this", "scope this", "write a PRD", "define this work", "turn this into a ti

Fallback for manual session logging when auto-capture is disabled or fails, plus explicit resume/handoff/status requests. Auto-capture via hooks/session-end-capture.mjs is the primary Stop-time path — this skill is a safety net. Triggers on end-of-session signals ("done", "end", "всё", "хватит", "finish", "конец") and resume-intent requests ("resume", "продолжи", "что делали", "handoff", "what did

Scan the codebase for deficiencies, generate a prioritized report ranked by efficiency (points per iteration), and optionally transition into focused improve loops area-by-area until the user stops or the score hits 100.

Generates an incident response plan (response-plan-{id}.md) for Phase 5 — Launch. Covers task #27 of the project management agent. Handles mixed incident types: Technical (system failures, critical bugs, infrastructure), Operational (deployment failures, process breakdowns), and Business (KPI collapse, PR crises, legal issues). Classifies severity (Critical / High / Medium / Low) from PM descripti

Execute AIs de CLI externos como subagentes isolados para delegação de tarefas, processamento paralelo e separação de contexto. Ideal para delegar tarefas complexas de várias etapas, executar investigações paralelas, obter um novo contexto ou usar definições de agentes especializados, retornando JSON estruturado com a saída do agente, código de saída e status de execução.

Esta skill aborda um fluxo de trabalho de competição Kaggle impulsionado por Agente de IA, compartilhando experiência real em estabilização de pontuação, solução de problemas de submissão, fluxos de trabalho de kernel, delegação de GPU e desenvolvimento orientado por especificações para alcançar as primeiras posições. É útil para competições Kaggle, análise de falhas, configuração de pipelines automatizados ou replicação de notebooks de destaque.

Model evaluation in R with performance metrics, calibration, ROC analysis, decision curves, and validation.

Diagnostic accuracy analysis in R, including sensitivity, specificity, ROC curves, likelihood ratios, and decision curves.

Assess what's needed to make feedback loops autonomous in a repo. Use when someone says "loop check", "what do I need to work autonomously", "check my feedback loops", "what's manual here", "what should I automate", "can an agent iterate here", or before starting work in an unfamiliar repo to understand what's missing for autonomous iteration. Also use when the user asks "what do you need to make