Plugin build-like-amazon

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

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

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

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.

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

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

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.

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

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

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

Design APIs using a contract-first approach to ensure backward compatibility, clear versioning, and stable interfaces across various protocols.

Reverse-engineers existing projects to generate Design Documents, API contracts, and Threat Models from code, IaC, and observability data.

Evaluates code changes against five dimensions—clarity, correctness, design, reuse, and operational readiness—to maintain high engineering standards.

Performs blameless post-incident analysis using the 5 Whys method to identify systemic root causes and implement automated safeguards.

Implements resilience patterns like circuit breakers, timeouts, retries, and bulkheads to protect services from external dependency failures.

Translates customer requirements into a detailed engineering plan including architecture, trade-offs, cost estimation, and operational concerns.

Evaluates technical design documents for clarity, completeness, security, and operational readiness before implementation begins.

Manages the complete lifecycle of feature flags including creation, gradual rollout, kill switch implementation, A/B testing, and cleanup.

Maintains a fixed-size procedural memory of implementation lessons to improve future build executions via a markdown file.

Decompose features into thin vertical slices that are independently deployable, testable, and rollback-safe using feature flags and small commits.

Defines principles for managing cloud infrastructure using CDK and CloudFormation through immutable deployments, environment parity, and least privilege.

Converts lessons learned and recurring failures into automated systems and processes that prevent error recurrence without human vigilance.

Perform proactive analysis of operational, business, and resource metrics to detect trends, identify anomalies, and drive data-informed improvements.

Enables agents to write production-ready code with embedded observability through structured logging, metrics, tracing, and graceful degradation.

Enables agents to evaluate and implement service observability through dashboards, severity-based alarming, and actionable runbooks.

Performs a structured self-assessment of operational requirements including monitoring, scaling, security, and deployment safety before production launches.

Enforces automated quality gates, deployment blockers, and one-click rollback mechanisms to protect production environments.

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

Decomposes approved design documents into vertical technical specifications consisting of requirements, design, and task files.

Implements the Red-Green-Refactor cycle using a test pyramid of unit, integration, and end-to-end tests with production canary monitoring.

Identifies security design flaws using the STRIDE methodology, data classification, and blast radius analysis before system implementation.

Provides a meta-framework for navigating, selecting, and combining specialized skills and architectural patterns using Amazon's operating principles.

Transforms customer insights into precise, data-backed problem statements using a structured template to prevent scope creep and align teams.

Generates multiple solution approaches, classifies decisions as one-way or two-way doors, and evaluates alternatives to recommend a solution.

Conducts systematic customer research to identify specific segments, gather quantitative and qualitative data, and produce a Customer Insight Summary.

Enables agents to write Amazon-style press releases and frequently asked questions to drive customer-centric product development.

Defines success metrics, numeric targets, and validation experiments to measure product impact using input and output metrics.

Orchestrates a five-stage product development methodology starting from customer insights to produce a PR/FAQ document.

Aucune description dans le fichier.