claude

build-like-amazon

Production-grade engineering skills for AI coding agents, built on Amazon's Working Backwards methodology and operational excellence culture.

16 on GitHubby Robisson Oliveirav0.6.0MITupdated 1 month agodevelopment
/

Plugin build-like-amazon from marketplace build-like-amazon in robisson/build-like-amazon-agent-skills. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (29)

  • bla

    Build Like Amazon — the entry point for the BLA engineering flow. Routes a request to the right phase: Working Backwards discovery (wb, listen, define, invent, refine, test-idea), brownfield onboarding (onboard), design (design, spec), implementation (build, review), release (deploy, operate) and po

  • api-contract-first

    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.

  • brownfield-discovery

    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.

  • code-review-bar-raising

    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.

  • correction-of-errors

    Blameless post-incident analysis focused on timeline, 5 Whys, mechanisms over people, and concrete action items with owners.

  • dependency-management

    Managing external dependencies safely with circuit breakers, timeouts, retries with exponential backoff, bulkhead pattern, graceful degradation, and dependency isolation.

  • design-document

    Writing a technical design document that translates a Working Backwards output into a concrete, reviewable engineering plan with architecture, trade-offs, cost estimation, and operational concerns.

  • design-review

    Review a technical design before specs or implementation. Evaluate problem clarity, requirements, alternatives, trade-offs, architecture, dependency behavior, security, operations, cost, testability, and simplicity.

  • feature-flag-lifecycle

    Complete lifecycle of feature flags from creation through gradual rollout to cleanup, including kill switches and A/B testing.

  • implementation-memory

    Internal /build flow mechanism that maintains fixed-size procedural memory of durable implementation-quality lessons.

  • incremental-implementation

    Implementing features in thin vertical slices that each deliver value independently. Feature flags, safe defaults, rollback-friendly changes. Never a big-bang deployment.

  • infrastructure-as-code

    CDK/CloudFormation design principles for immutable infrastructure, environment parity, least privilege, tagging strategy, and cost optimization. Infrastructure is code—it deserves the same rigor as application code.

  • mechanism-creation

    Turning lessons learned into automated mechanisms that prevent recurrence of problems.

  • metrics-review

    Reviewing operational and business metrics for continuous improvement, trend analysis, and proactive issue detection.

  • operational-code

    Writing code with built-in observability from day one. Structured logging (JSON), metrics emission (latency p50/p99, error rates), alarm-ready code, request tracing, graceful degradation.

  • operational-excellence

    Dashboards, alarms, and runbooks that make a service operable. Covers latency, error rate, availability, throughput, and severity-based alarming.

  • operational-readiness-review

    The ORR process — a self-assessment checklist covering monitoring, alarming, runbooks, on-call, scaling, security, deployment safety, cost, and dependencies. Must pass before launch.

  • pipeline-safety

    CI/CD pipeline safety with automated gates, deployment blockers, alarm checks, and one-click rollback.

  • progressive-deployment

    Deploy changes incrementally through expanding blast radius stages with bake time and automatic rollback on alarm.

  • spec-driven-implementation

    Bridge between an approved Design Document and code. Decompose the system-level blueprint into N vertical specs (requirements → design → tasks), each independently deliverable. Fail fast by ordering hardest-first. Execute wave-by-wave with approval gates.

  • test-driven-development

    Red-Green-Refactor cycle with Amazon's test pyramid (80% unit, 15% integration, 5% e2e). Coverage gates, DAMP over DRY in tests, canary tests in production.

  • threat-modeling

    Security threat modeling using STRIDE methodology adapted for cloud services. Covers data classification, IAM boundaries, encryption requirements, blast radius analysis, and systematic identification of attack vectors before code is written.

  • using-amazon-skills

    Meta-skill for navigating and applying the complete skills library. Routing flow chart, core operating behaviors, and skill discovery logic.

  • wb-define

    Stage 2 of Working Backwards: Articulate the customer's problem or opportunity with precision, using data to quantify impact and framing it in the customer's language — not engineering jargon.

  • wb-invent

    Stage 3 of Working Backwards: Generate multiple solution approaches, classify decisions as one-way vs two-way doors, evaluate alternatives against customer benefit and feasibility, and select the recommended solution with clear rationale.

  • wb-listen

    Stage 1 of Working Backwards: Identify who the customer is and gather deep insights about their current experience, pain points, and unmet needs through systematic observation and data collection.

  • wb-refine

    Stage 4 of Working Backwards: Write the PR/FAQ — a press release announcing the product as if it already exists, plus a comprehensive FAQ addressing hard questions. This is the core Amazon mechanism that forces clarity, customer-centric thinking, and rigorous pre-mortems before any code is written.

  • wb-test-and-iterate

    Stage 5 of Working Backwards: Define how success will be measured using input and output metrics, set specific numeric targets, design experiments to validate assumptions, and plan iteration cycles based on data feedback.

  • working-backwards

    Entry point for developing new products, features, or initiatives using Amazon's Working Backwards process. Orchestrates 5 stages from customer insight to measurable success, starting with the 5 Customer Questions as a lightweight on-ramp before committing to a full PR/FAQ.

Subagents (10)

  • Code Review Bar Raiser

    Review code for production readiness — correctness, operability, testability, backward compatibility, readability, and long-term maintainability.

  • COE Reviewer

    Review a Correction of Errors document for root-cause depth, mechanisms over intentions, blameless framing, and concrete action items with owners and dates.

  • Design Bar Raiser

    Review a design document for technical soundness, honest alternatives, capacity and cost planning, operability, and pattern-catalog fit.

  • Doc Bar Raiser

    Review PR/FAQs and written narratives for customer obsession, clarity, data over opinion, and genuinely hard FAQs; in /onboard Path B, surface the questions only a human can answer.

  • Implementation Verifier

    Verify that an implementation satisfies the spec's properties and requirements through property-based testing, interface conformance checking, and regression detection.

  • Ops Bar Raiser

    Review designs, code, and launch plans for operational readiness — monitoring, alarms, deployment safety, recoverability, debuggability, capacity, and runbooks.

  • Principal Engineer

    Break ties on disputed design decisions with a long-term, system-wide call that names the trade-off explicitly and states which side to take.

  • Requirements Analyzer

    Analyze a requirements document across all requirements at once to detect contradictions, gaps, and ambiguities that only become visible when requirements interact.

  • Security Guardian

    Review code, designs, and configurations for security vulnerabilities, unsafe data handling, weak access control, and unnecessary blast radius.

  • Task Planner

    Decompose a design into a dependency-ordered tasks.md that maximizes parallelism, marks one-way doors, and traces every task to a requirement.

Hooks (1)

  • SessionStart

    sh "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"

View source on GitHub

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain build-like-amazon?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted