Audit AWS, Azure, GCP, hybrid, or multi-cloud infrastructure across security, reliability, cost, efficiency, performance, operations, delivery, and developer experience. Use for read-only environment reviews, Well-Architected assessments, cloud cost and utilization reviews, DevOps/platform-engineering assessments, architecture evidence audits, technical due diligence, or ranked infrastructure remediation plans. Do not use for penetration testing, compliance certification, or executing infrastructure changes.
Audit AWS, Azure, GCP, hybrid, or multi-cloud infrastructure across security, reliability, cost, efficiency, performance, operations, delivery, and developer experience. Use for read-only environment reviews, Well-Architected assessments, cloud cost and utilization reviews, DevOps/platform-engineering assessments, architecture evidence audits, technical due diligence, or ranked infrastructure remediation plans. Do not use for penetration testing, compliance certification, or executing infrastructure changes.
Audit an existing codebase or system and produce an evidence-backed findings register and prioritized remediation roadmap. Covers scoping the audit questions, a read-only orientation, eight dimensions (architecture, maintainability, reliability, security, performance, test coverage, operability, delivery), change-frequency by complexity hotspots, test-gap mapping to critical paths, findings with evidence and confidence, severity times likelihood times exposure scoring, and now/next/later sequencing. Use when someone asks to audit a codebase, assess technical debt, review the health of an inherited or acquired system, find reliability or security gaps, judge whether to rewrite or refactor, or prepare due diligence on a code base. Do not use for dependency version and licence health alone (use dependency-health), for planning a data or platform move (use migration-plan), for designing the target system (use technical-architecture), or for reviewing a single change (use gitnexus-review).
Audits existing systems for architecture, maintainability, reliability, security, performance, and test gaps.
Coordinate an active production incident or prepare an incident runbook using runtime evidence, explicit roles, bounded mitigations, stakeholder updates, verification, rollback, and a blameless follow-up. Use for outage command, degraded service, security or provider incidents, incident timelines, status updates, and post-incident action plans. Do not use to execute destructive remediation or claim recovery without authoritative readback.
Assess the likely consequences of a proposed or local code change with GitNexus graph evidence, then verify the result against the exact repository. Use for dependency tracing, blast-radius analysis, regression planning, and deciding whether a shared symbol is safe to change.
Assess the likely consequences of a proposed or local code change with GitNexus graph evidence, then verify the result against the exact repository. Use for dependency tracing, blast-radius analysis, regression planning, and deciding whether a shared symbol is safe to change.
Plan an infrastructure-as-code setup, or the adoption of one for existing manual infrastructure. Inventories resources by layer and stateful versus stateless, picks a tool by criteria, designs environments, repository, module, and remote state layout, deployer identity, handling of sensitive values, a reviewed plan-then-apply flow with policy checks and a production approval gate, drift detection, change-safety rules for replacements and deletions, and rollback classified per resource. Use when someone asks to set up or codify infrastructure, manage staging and production from code, structure modules and state, design an infrastructure deploy pipeline, or decide how to roll back infrastructure changes. Do not use for application design (use technical-architecture), auditing existing cloud resources (use audit-cloud-infrastructure), data or platform moves (use migration-plan), or monitoring design (use observability-plan).
Plans infrastructure-as-code setup across environments, resources, secrets, deploy flow, and rollback approach.
Implementation Plan workflow that groups context collection, production, review, and packaging tasks into one deliverable.
Plan a safe technical migration (schema, data store, hosting platform, service or API version, framework, or vendor) as a staged parallel-change plan. Covers an inventory of what moves and who depends on it, a compatibility matrix for old and new code against old and new data, a data preservation plan with reconciliation checks, backfill duration math, phases with entry and exit gates, a cutover and point-of-no-return decision, a rollback per phase, and a cleanup step. Use when someone asks how to migrate a database, move to a new platform or provider, change a schema without downtime, version or retire an API, plan a cutover, or write a rollback plan. Do not use for an audit of existing code health (use codebase-audit), for the target design itself (use technical-architecture), for infrastructure definitions (use iac-setup), or for live incident handling (use coordinate-production-incident).
Plans safe migrations with compatibility, data preservation, rollout phases, verification, and rollback.
Turn product requirements into a buildable implementation plan for a web or mobile app. Converts requirements into testable acceptance criteria, decides the delivery platform (responsive web, installable web app, native, or cross-platform) from capability needs, breaks work into vertical slices with the files to create or change, the interface contract, the screen states, accessibility and analytics needs, a test plan traced to each criterion, milestones with three-point estimates, and a staged rollout with a kill switch and a support policy for old app versions. Use when someone asks how to implement a feature or app, to plan a build from a spec, to break a front-end project into milestones, to decide web versus native, or to plan a mobile release. Do not use for the system-level design (use technical-architecture), for splitting a spec into engineering tickets only (use technical-requirements-splitter), for a data or platform move (use migration-plan), or for the visual design itself (use wireframe-spec).
Turns requirements into implementation plans for web or mobile with milestones, files, tests, and rollout.
Plan the logs, metrics, traces, alerts, dashboards, service level objectives, and incident response hooks for a system so its operators can tell within minutes whether users are hurting and why. Starts from user journeys, defines good-event service level indicators and SLO targets with error budget and multi-window burn-rate alert math, maps instrumentation per component, sets log field and metric cardinality rules, designs tiered dashboards and symptom-based paging, adds runbook and escalation hooks, and budgets telemetry volume, retention, and privacy. Use when someone asks how to monitor a system, what to log or alert on, how to set SLOs, why alerts are noisy, how to add tracing, or how to prepare a service for on-call. Do not use for triaging a specific metric anomaly (use anomaly-triage), running a live incident (use coordinate-production-incident), auditing existing code (use codebase-audit), or defining infrastructure resources (use iac-setup).
Defines logs, metrics, traces, alerts, dashboards, SLOs, and incident response hooks for a system.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Review QA Manager evidence with requirement-to-test traceability, fast and full gate plans, comparable performance baselines, security evidence records, workflow maps, and UI edge-case gaps.
Verify unstable framework, library, and platform facts against the installed version and current primary sources before implementation. Use when technical decisions depend on APIs, configuration, defaults, compatibility, or behavior that may have changed.
Verify unstable framework, library, and platform facts against the installed version and current primary sources before implementation. Use when technical decisions depend on APIs, configuration, defaults, compatibility, or behavior that may have changed.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Create a technical architecture plan for a new or evolving system from its requirements. Ranks quality attributes with measurable targets, sizes load and storage with back-of-envelope capacity math, sets system boundaries and data ownership, maps the context, containers, and data flows for key scenarios, designs APIs and data storage by access pattern, covers infrastructure, security trust boundaries, and failure modes, and records each major choice as a decision with options, criteria, reversibility, and a build sequence that proves the riskiest assumptions first. Use when someone asks to design a system architecture, choose between a monolith and services, plan data flow and APIs, size infrastructure, or document architecture decisions and tradeoffs. Do not use for splitting a finished design into tickets (use technical-requirements-splitter), assessing an existing codebase (use codebase-audit), planning a move between systems (use migration-plan), or writing infrastructure definitions (use iac-setup).
Creates architecture plans with system boundaries, data flow, APIs, infrastructure, security, and tradeoffs.
Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.