Desenvolvimento

CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

Use after implementing features - 7-criteria code review with MANDATORY artifact posting to GitHub issue; blocks PR creation until complete

Pre-build validation — red-test check + Contract Manifest wiring check

Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avoid. Use when reviewing PRs, establishing review standards, or improving review quality.

Production Go concurrency patterns — goroutines, channels, sync primitives, context, worker pools, pipelines, and graceful shutdown. Use when building concurrent Go applications or debugging race conditions.

Cria roteiros de CTA prontos para gravação (inscreva-se, curta, comente, leitura de patrocinador, promoção de canal), alinhados ao tom do canal e no momento ideal.

Use when Sam asks Codex to create, rename, compare, commit, push, merge, promote, or clean up Git branches. Covers Sam's feature branch naming convention, safe Git pre-checks, JetBrains DontCommit handling, commit-message defaults, push and release promotion verification, branch rename upstream cleanup, branch sync comparison, and submodule/gitlink handling.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Um fluxo de trabalho para perfilar aplicativos iOS/macOS com Instruments via xctrace CLI, identificando e corrigindo problemas de desempenho. É usado para 'medição com Instruments', 'profiling' e 'medição de desempenho'.

Reformats and rewrites subtitle text for timing, readability, and on-screen clarity, following broadcast subtitle standards.

Build stage — per-unit implementation with fresh context and mechanical backpressure

Esta skill ensina agentes de codificação como Claude Code/OpenClaw a usar a API Anthropic Claude Managed Agents para todo o processo de criação, execução e auditoria. É utilizada quando usuários ou agentes upstream precisam criar agentes gerenciados, executar sessões, processar eventos em stream, auditar uso ou interagir com APIs como /v1/agents, /v1/environments e /v1/sessions.