By robisson
Implements Amazon's Working Backwards methodology and operational excellence culture for AI coding agents, enabling structured product discovery via PR/FAQs, production-grade code reviews, safe staged deployments with feature flags, blameless post-incident analysis, and automated quality gates across the full development lifecycle.
> **Path resolution**: All `skills/`, `agents/`, and `patterns/` paths in this command are relative to the plugin root directory. If not found in the working directory, resolve from the plugin installation path.
> **Path resolution**: All `skills/`, `agents/`, and `patterns/` paths in this command are relative to the plugin root directory. If not found in the working directory, resolve from the plugin installation path.
> **Path resolution**: All `skills/`, `agents/`, and `patterns/` paths in this command are relative to the plugin root directory. If not found in the working directory, resolve from the plugin installation path.
> **Path resolution**: All `skills/`, `agents/`, and `patterns/` paths in this command are relative to the plugin root directory. If not found in the working directory, resolve from the plugin installation path.
> **Path resolution**: All `skills/`, `agents/`, and `patterns/` paths in this command are relative to the plugin root directory. If not found in the working directory, resolve from the plugin installation path.
You are a senior engineer who reviews code for production readiness. Your focus goes beyond correctness—you evaluate code for operability, testability, backward compatibility, readability, and long-term maintainability. You hold the bar: code that passes your review is code that won't wake someone up at 3 AM.
You are a senior leader who reviews Correction of Errors documents for quality, depth, and effectiveness. Your job is to ensure COEs identify real root causes (not surface-level explanations), propose mechanisms (not promises), and produce concrete action items that prevent recurrence. You reject COEs that blame individuals or propose "be more careful" as a solution.
You are a principal-level engineer who reviews design documents for technical soundness, operational readiness, and long-term sustainability. Your job is to ensure every design considers trade-offs explicitly, evaluates alternatives honestly, plans for scale, accounts for cost, and can be operated in production by any qualified engineer.
You are a senior technical writer and narrative reviewer who evaluates PR/FAQs, design narratives, and written proposals. Your job is to ensure documents are clear, customer-obsessed, data-driven, and free of ambiguity. You hold the bar for written communication quality—the same bar Jeff Bezos applied to six-pagers.
You are a verification engineer who validates that implementation correctly satisfies the spec's properties and requirements. You do NOT trust that code works because it compiles or because example-based tests pass. You verify correctness through property-based testing, interface conformance checking, and regression detection.
Designing APIs contract-first with backward compatibility guarantees, clear versioning strategy, error semantics, idempotency, and pagination. The API is a promise—never break existing clients.
Reverse-engineer an existing project to produce a Design Doc, API contracts, and a Threat Model anchored in the real code, IaC, and observability. Run once per project. Output anchors all subsequent /spec and /build invocations.
Applying Amazon's raise-the-bar principle to every code review. What reviewers look for — clarity, correctness, design, reuse, operational readiness. "Ship It" means the change raises or maintains the quality bar.
Blameless post-incident analysis focused on timeline, 5 Whys, mechanisms over people, and concrete action items with owners.
Managing external dependencies safely with circuit breakers, timeouts, retries with exponential backoff, bulkhead pattern, graceful degradation, and dependency isolation.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Production-grade engineering skills for AI coding agents, built on Amazon Way of building services.
Getting Started · Quick Start · All Skills · Agent Personas · Philosophy · Contributing
Author's disclaimer: "Amazon, in my opinion, has a very unique way of designing, building, and operating large-scale distributed services. This is publicly available in a variety of formats, from YouTube videos to blog articles, knowledge frameworks like the Well-Architected Framework, and the Amazon Builders Library. My idea here was to organize this knowledge so that AI Agents can leverage this way of seeing a problem and convert it into customer-centric value, accelerating the developer's work."
Amazon Agent Skills encode Amazon's engineering workflows as structured markdown that AI coding agents follow consistently. Instead of relying on tribal knowledge or hoping your agent "figures it out," these skills provide deterministic, repeatable processes that mirror how Amazon builds software at scale.
Each skill encodes:
When the right workflow is unclear, agents should load skills/using-amazon-skills/SKILL.md first. It is the meta-skill that routes ambiguous requests to the correct lifecycle phase and skill chain.
The skills cover the complete software lifecycle through Amazon's lens:
graph LR
WB[Working Backwards] --> Design --> Build --> Deploy --> Operate --> Learn --> WB
This circular lifecycle means every operational lesson feeds back into the next iteration — exactly how Amazon achieves compounding quality improvements over time.
| Command | Description | Phase |
|---|---|---|
/onboard | Reverse-engineer an existing project — produce design artifacts from real code so the agent understands your system | Onboarding |
/wb | Full Working Backwards cycle — from customer problem to PR/FAQ | Working Backwards |
/listen | Stage 1: Identify customer pain through signals and data | Working Backwards |
/define | Stage 2: Write the press release and FAQ | Working Backwards |
/invent | Stage 3: Explore solution space and select approach | Working Backwards |
/refine | Stage 4: Iterate on the solution with stakeholder feedback | Working Backwards |
/test-idea | Stage 5: Validate assumptions before committing resources | Working Backwards |
/design | Conduct a design review with architecture tenets | Design |
/spec | Create a new implementation spec (when design already exists) | Design |
/build | Implement with Amazon's coding standards and testing bar | Build |
/review | Code review with bar raiser mentality | Build |
/deploy | Progressive deployment with automatic rollback | Deploy |
/operate | Operational readiness and runbook generation | Operate |
/learn | Correction of Errors — blameless post-incident analysis | Learn |
👉 New here? Read
docs/getting-started.mdfirst — it walks you through install + 4 hands-on scenarios (new product, existing project onboarding, small change, production incident) in ~10 minutes. The setup snippets below are also there, with full context.
Kiro uses three mechanisms: skills (workflow guidance), steering (persistent operating rules), and commands (slash commands). To get the full workflow running:
With Kiro IDE, you dont need to execute /spec command, because kiro alreadt an excepcional native support to spec driven developmentm but the other commands area still very useful
git clone https://github.com/robisson/build-like-amazon.git
cd your-project
# 1. Skills — router files + full skill library
cp -r build-like-amazon/.kiro/skills/ .kiro/skills/
cp -r build-like-amazon/skills/ .kiro/skills/amazon/
npx claudepluginhub robisson/build-like-amazon-agent-skills12 PM-specific agent skills, 6 workflow commands, 3 automation hooks for Product Managers
Ship features end-to-end with launch checklists and rollout plans
Engineering + Product + Operations + Legal + Design + Data Science + Security Operations + Developer Experience + Infrastructure Specialist + AI Operations team — 100 agents as Claude Code specialists. Infrastructure, DevOps, backend, security, ML/AI, mobile, UX, analytics, growth, revenue, content, PR, customer success, finance, people, operations, support, contracts, compliance, IP, governance, regulatory, color systems, typography, motion, accessibility, design tokens, forecasting, feature engineering, model training, drift monitoring, vector search, LLM fine-tuning, pen testing, detection engineering, incident response, zero trust, API docs, SDK design, developer onboarding, Kubernetes, Terraform, FinOps, service mesh, edge computing, caching, queuing, multi-cloud, chaos engineering, model deployment, LLM evaluation, AI observability, guardrails, prompt engineering, embeddings, ranking, and more.
Lean agent skills for building, shipping, strategy, and growth — no context bloat.
50 specialist skills + 43 slash commands for coding agents — orchestrator, backend, frontend, QA, security, deploy, detective-spec, static-analysis, skill-author, program-router, parallel-dispatcher, blog-publisher, blog-screenshot, canary-deployment, zoom-out, handoff-context, post-deploy-canary-monitor, pattern-conformity, research-prep, context-budget, direct-response-copy, ux-research + spec-driven development, anti-AI writing, memory consolidation, executable YAML pipelines + insights dashboard (v2.18.0, 6 tabs). v2.37.0: absorcao de 7 ebooks Casa do Codigo — skill 50 ux-research (gap real: discovery qualitativo — entrevista, persona baseada em pesquisa, journey map, teste de usabilidade, arquitetura de informacao; antecede PO 01 e UI/UX 02) + 3 policies de XP (pair-programming, continuous-integration, sustainable-pace, ligadas a skill 37) + incrementos cirurgicos: skill 01 ganha Fundamento de Negocio (validacao de hipotese, MVP, monetizacao, AARRR, product-market fit — do Guia da Startup); skill 14 ganha Keyword Research (KEI, intent, cauda longa) + Off-Page/Link Building (do SEO Pratico); skill 07 ganha Infrastructure as Code (provisionamento declarativo, idempotencia, drift — principios do DevOps na pratica traduzidos pra Terraform/Ansible); skill 38 ganha lentes de coesao/acoplamento, seam distribuido (REST/async/RPC, HATEOAS) e camadas (da Introducao a Arquitetura). Livros de Jogos HTML5 Canvas (nicho <2%) descartados por frequencia. v2.36.0: skill 50 direct-response-copy — copy de direct response destilada de 3 ebooks classicos PT-BR: biblioteca de formulas de headline em 20 categorias de gatilho (357 modelos destilados em formulas parametrizadas), 8 gatilhos mentais + storytelling de venda, copy de Instagram (legenda/engajamento). Gate de integridade obrigatorio: sem claim nao-verificavel, sem depoimento fabricado, escassez so real. Complementa a skill 13 (copy de produto): 13 cobre landing/microcopy/brand voice, 50 cobre ads/pagina de vendas/email/social. v2.35.0: auto-skillify (absorcao parcial do activeloopai/hivemind) — hook UserPromptSubmit que a cada N turnos (default 20) injeta checkpoint perguntando se a atividade recente vale virar learned-skill (3 criterios: nao-googleavel, especifico do codebase, custou debugging). Adapta o skillify-via-Haiku do hivemind ao runtime: delega a decisao ao agente da sessao (ja pago) em vez de forkar LLM. Le a contagem do context-turn-counter. O resto do hivemind ja tinhamos: codebase graph=Graphify, semantic search=.index/vault.db, memory compound=memory-curator. v2.34.0: vault de memoria UNIFICADO ao kit — instalar o kit agora CRIA o vault automaticamente (scripts/init-vault.mjs roda no install.sh: cria estrutura logs/architecture/secrets, CLAUDE.md com as regras de escrita, .gitignore protegendo secrets/, git init). Path PORTAVEL via scripts/vault-resolver.mjs: $CLAUDE_MEMORY_VAULT → ~/.claude-memory (novo padrao, vale Windows/Mac/Linux) → D:/claude-memory (legado). Antes o vault era montado a mao e o path hardcoded; agora kit+memoria sao uma coisa so. Idempotente (nao sobrescreve vault existente). v2.33.0: absorcao obsidian-second-brain (memoria AI-first) — policy memory-write-rules.md aplica anti-fabricacao ao VAULT (false-absence: busque exaustivamente antes de afirmar que nao existe nota/decisao — o failure mode mais comum; no-fabrication: TBD para desconhecido; recency markers '(as of YYYY-MM, fonte)' em claims externos; niveis de confianca) + convencao 'For future Claude' (preambulo de 2-3 linhas que o futuro-Claude le em 10s pra decidir relevancia, no skill 31 session-summary) + comando /reconcile-memory (detecta contradicoes no vault — decisoes revertidas/superadas nunca atualizadas — e resolve: mais novo+autoritativo vence com secao ## History, ambiguo vira flag, evolucao marca superseded). v2.32.0: pre-build-gate (UserPromptSubmit hook) leva o 'pare e decida antes de codar' de cada disciplina (que o /auto tem nas fases) para o MODO PASSIVO — detecta intencao de criacao no prompt e injeta o checklist da disciplina certa: acceptance-criteria (defina done antes de implementar), api-contract (formato de erro + status codes antes da 1a rota), schema-integrity (constraints/FK/indices antes do 1o INSERT), ui-design (ancora estetica antes de estilizar), deploy-readiness (healthcheck/env/graceful-shutdown). 4 novas rules path-scoped por disciplina (rules/backend/, rules/database/, rules/frontend/, rules/common/acceptance-criteria.md). v2.31.0: design-aware /auto — fase UI-DESIGN como gate (PLAN→[UI-DESIGN]→BUILD) que invoca skill 02-ui-ux-design e bloqueia build de arquivo visual ate a ancora estetica estar escolhida; rules/frontend/ui-design.md (path-scoped em .css/.tsx/public) proibe o default generico (#4f46e5 indigo + system-ui), forca escolher 1 ancora; coverage config virou gate HARD no /auto; scope inference (app→fullstack) movido pra rules/common para o modo passivo herdar. Validado por bench A/B real (bench/ab/, 3 rounds) que expos UI generica nos 3 bracos. v2.29.0: claim-verifier (PostToolUse — detecta afirmacoes sem evidencia: 'email enviado', 'deploy OK', 'teste passou'; passa livre se ha exit code 0/HTTP 200/query result) + context-turn-counter (UserPromptSubmit — compact a cada 25 turnos, handoff inteligente a cada 50 usando vault de memoria). v2.28.0: /spec-kit (SDD pipeline unificado specify→plan→tasks→implement + Adversarial Verifier inline), /insights (recomendacoes baseadas em telemetria dos hooks), /swarm com Phase 3 Adversarial Verify (Implementor vs Verifier com goals opostos, spec atualizada em real-time). v2.27.0: investigate-first guard (hook PreToolUse que impede a IA de perguntar o auto-descobrivel — gh user, branch, package manager, porta, versao de runtime — manda investigar primeiro) + policy investigate-first. v2.26.0: silent-failure-hunter (16o subagent, review-only: caca catch{} vazio, swallowed errors, fallbacks perigosos, stack traces perdidos, rollback faltando) + skill 49 context-budget (audita peso de contexto carregado por componente) + /context-budget. v2.25.0: rules system path-scoped (`.claude/rules/` com `paths:` glob, inspirado no ECC), bug-fix da allowlist de subagents, 5 skills stub reescritos com profundidade. v2.24.0: curador AUTONOMO de memoria (inspirado no Hermes Agent) — roda async no SessionStart, faz decay/archive/dedup em JS puro sem gastar LLM e delega so a parte semantica ao agente presente. v2.23.0: absorcao addozhang (skill 48 research-prep, Spring Boot playbook, mem9 patterns). v2.22.0: memory curator nudge. v2.21.0: context-cost guards. v2.20.0: skill 47 pattern-conformity. 16 dispatchable subagents.
Tools for creating and managing Claude Code plugins, agents, commands, and skills