engineering

Plugin engineering from marketplace chwezi-engineering in peterbamuhigire/chwezi-dev-engine. Commands read from the repo's manifest — yesterday.

Skills (171)

• 00-meta-initialization

  Use when initialising documentation and a methodology roadmap for a brand-new project by detecting project type, selecting Waterfall, Agile, or Hybrid delivery, and generating the governed document sequence.

• new-project

  Use when the task matches skill: new project scaffold and this skill''s local workflow.

• chwezi-dev-engine

  Top-level router for the Chwezi Core Systems web-development and software-engineering skills engine. Use for AI systems, SaaS, architecture, APIs, databases, security, frontend engineering, mobile, DevOps, reliability, product engineering, SDLC documentation, catalog maintenance, delivery evidence p

• ai-agent-commercial-operations

  Use when pricing, billing, refunding, recognizing revenue, or packaging commercial terms for agentic AI services, or when defining agent SLAs, customer commitments, SLA dashboards, breach credits, and service evidence.

• ai-agent-compliance-controls

  Use when mapping AI agent operations to SOC 2, ISO 27001, HIPAA, audit logs, control testing, attestations, and compliance evidence, including drill-cadence evidence, approval-completeness (PI1.1) gap checks, and signed agent-memory erasure proofs.

• ai-agent-governance-and-limits

  Use when defining agent budgets, step limits, reversibility, blast-radius controls, kill switches, and governance policy for agentic AI systems.

• ai-agent-multi-agent-coordination

  Use when designing systems where multiple agents collaborate on one task — supervisor/worker, debate, plan-execute, peer handoff. Covers handoff message contracts, shared scratchpad, conflict resolution, deadlock detection, and the cost/SLA discipline that keeps multi-agent setups from spiralling.

• ai-agent-observability-evaluation

  Use when measuring, evaluating, replaying, evidencing, or tracking success for AI agent tasks, steps, traces, and outcomes.

• ai-agent-runtime-architecture

  Use when designing multi-tenant agent runtimes, control loops, state machines, retries, idempotency, step caps, durable resumability, scheduling, cancellation, and workflow boundaries.

• ai-agent-safety-and-red-team

  Use when red-teaming agent tool and data perimeters for indirect prompt injection, action escalation, tenant exfiltration, unsafe tool chains, self-modification, or containment regressions.

• ai-agent-tooling-and-hitl

  Use when designing agent tool catalogs, tool schemas, action gating, human approval, and human-in-the-loop control for agentic AI systems.

• ai-analytics

  Use when designing AI analytics, dashboards, SaaS AI metrics, NLP analytics, predictive analytics, or executive AI insight workflows. Orchestrates the former granular AI analytics skills as references. Non-AI report, export and print engineering belongs to reporting-and-export-engineering.

• ai-app-architecture

  Use when designing or building AI-powered application systems — choosing architecture style, selecting components, structuring the AI stack, making build-vs-buy decisions, and planning multi-tenant AI module gating

• ai-cost-and-metering

  Use when modeling, metering, attributing, billing, or controlling AI usage costs across tenants, plans, features, providers, and agent workloads.

• ai-economic-value-engine

  Use when discovering, designing, prioritizing, or auditing AI-powered products for measurable business value. Applies to AI opportunity mapping, ROI cases, product strategy, client workshops, and deciding whether an AI feature should be built.

• ai-evaluation

  Use when building an AI/LLM evaluation harness, golden datasets, quality metrics, judge calibration, regression gates, production monitoring, drift detection, or user-feedback loops; use ai-llm-integration for provider calls.

• ai-feature-rollout-and-experimentation

  Use when planning a controlled AI-feature rollout or experiment in multi-tenant SaaS: tenant/user feature flags, percentage and canary cohorts, holdout metrics, A/B tests of prompts or models, eval and SLO gates, automatic rollback, tenant opt-out and consent, or shadow mode for risky changes.

• ai-feature-spec

  Use when specifying one AI-powered feature end to end, including model choice, prompt and context contracts, output schema, fallbacks, human oversight, UX states, and evaluation.

• ai-incident-response

  Use when preventing, detecting, triaging, communicating, recovering from, or reviewing AI incidents, AI errors, RCA, and postmortems.

• ai-llm-integration

  Use when integrating an LLM provider into an application with streaming, structured outputs, tool calls, embeddings, multi-model routing, retries, caching, and usage metering, or when choosing regex, an LLM, or a hybrid pipeline to extract fields from structured text such as forms, invoices, or scra

• ai-model-gateway

  Use when designing or building an LLM gateway for provider abstraction, tenant-aware routing, fallbacks, quotas, residency, audit logging, cost capture, and kill-switch enforcement.

• ai-observability-and-debugging

  Use when building the observability stack for AI features in a multi-tenant SaaS — prompt/response tracing, semantic logging, replay tooling, "show me why this answer", per-stage latency/cost breakdown, ticket→trace tie-back, and dashboards that answer the operational questions (which tenant, which

• ai-opportunity-canvas

  Use when discovering and ranking AI use cases for a project or module and producing an opportunity register with impact, effort, cost, risk, and evidence gaps.

• ai-prompt-engineering

  Use when writing, refining, or structuring prompts for AI-powered app features — system prompts, user prompt templates, few-shot examples, chain-of-thought, prompt versioning, and defensive prompting

• ai-rag-patterns

  Use when building features that answer questions from private data, documents, policies, or time-sensitive information — RAG architecture, chunking, hybrid search, re-ranking, vector databases, evaluation, agentic and multimodal RAG, and bounded iterative retrieval for context-starved subagents.

• ai-security

  Use when securing an AI/LLM-powered feature against prompt injection, cross-tenant data leakage and tenant isolation failures, jailbreaks, and adversarial inputs. Covers PII scrubbing before model calls, output validation, rate limiting, audit logging, and DPPA/GDPR compliance for AI data flows.

• ai-web-apps

  Use when designing or building an AI-enhanced web app with chat, RAG, MCP tools, streaming, provider abstraction, feature gates, token budgets, and output guardrails.

• coding-agent-optimization

  Use when auditing or tuning a development machine's Claude Code or Codex setup for context, model, subagent, permission, or token efficiency, deciding when to compact a long session, or running independent lanes in parallel safely. Analyse local capabilities first; apply only supported reversible ch

• openai-agents-sdk

  Use when building Python agents with the OpenAI Agents SDK, including runners, tools, handoffs, guardrails, tracing, memory, multi-agent topology, and deterministic orchestration.

• android-development

  Use when building or reviewing native Android apps with Kotlin, Compose, architecture, Room/DataStore persistence, offline sync, or test-driven development; use mobile-platform-operations for store release work.

• api-design-first

  Use when designing HTTP APIs with OpenAPI, versioning, authentication, rate limits, idempotency, error contracts, observability requirements, and choosing REST, webhooks, SSE, or WebSocket delivery.

• distributed-systems-patterns

  Use when designing or reviewing multi-service, message-driven, or eventually consistent systems. Covers service boundaries, consistency tradeoffs, event workflows, outbox and inbox patterns, sagas, ordering, and idempotency.

• ecommerce-platform-audit-requirements

  Use when scoping or specifying an e-commerce platform, payment, API, security, AI, data protection, integration, and remediation audit for SMEs or cross-border digital trade programmes.

• graphql-patterns

  Use when designing or operating GraphQL APIs with schemas, resolvers, authorization, pagination, federation, code generation, and hostile-input controls.

• microservices-architecture

  Use when designing, reviewing, or refactoring microservice boundaries, communication, service ownership, deployment independence, resilience, and distributed data flows. Load absorbed microservices fundamentals, models, communication, and resilience references as needed.

• system-architecture-design

  Use when defining or reviewing software architecture for web apps, mobile backends, SaaS platforms, APIs, distributed systems, or major features. Covers bounded contexts, module decomposition, hexagonal ports-and-adapters boundaries, contracts, failure handling, ADRs, and scalability tradeoffs.

• validation-contract

  Use when authoring or normalising a specialist skill, or preparing to ship a feature or release — defines the seven evidence categories every specialist skill must declare against and provides the canonical Release Evidence Bundle template. The contract spine that turns scattered validation skills i

• database-design-engineering

  Use when designing or reviewing relational or document-backed data architecture for SaaS platforms, ERP systems, APIs, analytics stores, or mobile sync. Covers domain modeling, tenancy, indexing, migrations, event stream data contract and schema evolution, integrity, retention, and performance trade

• database-reliability

  Use when defining database SLOs, error budgets, backup verification, capacity policy, incident response, game days, or MySQL and PostgreSQL on-call practice.

• mysql-engineering

  Use when designing, implementing, administering, tuning, backing up, restoring, monitoring, or troubleshooting MySQL schemas and production systems; use database-reliability for datastore-independent SLO and recovery policy.

• postgresql-engineering

  Use when designing, implementing, administering, tuning, backing up, restoring, monitoring, or troubleshooting PostgreSQL schemas and production systems; use database-reliability for datastore-independent SLO and recovery policy.

• cicd-pipelines

  Use when building CI/CD pipelines with build, test, security, packaging, deployment stages, reusable workflows, short-lived cloud authentication, caching, promotion gates, pipeline telemetry, and hardening GitHub Actions workflows (SHA pinning, OIDC); use deployment-release-engineering for rollout d

• cloud-architecture

  Use when designing cloud deployments, Dockerising applications, laying out AWS or GCP environments, choosing a deployment pattern, or moving a workload from a single VM to a resilient multi-AZ topology.

• deployment-release-engineering

  Use when designing or reviewing deployment pipelines, rollout strategies, release gates, rollback plans, migration-safe releases, and post-deploy verification for production systems. Covers build promotion, environment strategy, release evidence, and operational safety.

• docker-development

  Use when containerizing PHP, Python, JavaScript, or API services with Dockerfiles, multi-stage images, Compose, CI builds, runtime permissions, and persistent dependencies.

• infrastructure-as-code

  Use when provisioning or changing cloud infrastructure with Terraform or Ansible — modules, remote state with S3 native locking, workspaces vs directory-per-env, common AWS patterns, idempotent Ansible roles for Debian/Ubuntu, GitOps with ArgoCD/Flux, drift detection, and Vault secret injection.

• kubernetes-platform

  Use when building or running production Kubernetes clusters, namespaces, workloads, ingress, autoscaling, multi-tenant RBAC, network/Pod Security, resource quotas, upgrades, certificates, etcd, metrics, disruption, and recovery.

• observability-monitoring

  Use when designing or reviewing logs, metrics, traces, alerts, SLOs, dashboards, audit events, or production telemetry for web apps, APIs, SaaS platforms, mobile backends, and AI systems. Covers instrumentation strategy, diagnosis-first telemetry, alert quality, and operational visibility.

• reliability-engineering

  Use when designing or reviewing production reliability for APIs, SaaS platforms, background jobs, distributed workflows, mobile backends, or AI-enabled systems. Covers timeout and retry policy, degradation, queue safety, incident readiness, and recovery-aware design.

• execution-plan-scripts

  Use when converting an approved long-running plan into self-contained execution prompts across sessions or workers. Covers dependency order, checkpoints, capability fallback and evidence handoff; use world-class-engineering for a single implementation slice.

• accounting-engine

  Use when designing or implementing double-entry accounting policy and an embedded ledger engine for invoices, payments, stock, balanced postings, mapped accounts, idempotency, reversals, period locks, audit trails, and financial statements.

• accounting-finance-controller

  Use when coordinating accounting and finance implementation reviews, doctrine routing, control evidence, remediation priorities, and release decisions across a software system.

• electronic-fiscal-taxing

  Use when implementing or reviewing electronic fiscal taxation integrations in web, ERP, POS, or mobile-backed systems; covers jurisdiction adapters, tenant-scoped tax identities, API security, queues, offline operation, fiscal evidence, and Uganda EFRIS as the detailed reference.

• multicurrency-and-fx

  Use when implementing IAS 21 multicurrency accounting: functional currency, presentation currency, transaction currency, exchange-rate tables, settlement, realised and unrealised forex gains or losses, revaluation, and currency-safe ledger design.

• avalonia-desktop-development

  Use when building or reviewing cross-platform .NET desktop apps with Avalonia UI, AXAML, MVVM, compiled bindings, virtualised lists, accessibility, headless tests, WebViews, or Windows and macOS packaging. Use csharp-dotnet-development for non-UI .NET architecture.

• frontend-architecture

  Use when turning a design system, product requirement, or frontend codebase into a maintainable component, content, state, and delivery architecture with measurable quality gates.

• frontend-performance

  Use when defining, implementing, or auditing frontend performance for web apps and SaaS frontends; produces a per-flow performance budget, measurement plan tied to SLOs, and CI regression gate. Use api-design-first for API shape and observability-monitoring for server SLOs.

• image-compression

  Use when implementing or reviewing client image optimisation plus authoritative server decode, validation, resize, metadata stripping, and canonical re-encoding. Use saas-managed-visual-assets for administrative asset lifecycle and frontend-performance for page budgets.

• nextjs-app-router

  Use when implementing or reviewing a Next.js App Router application with server and client components, route handlers, Proxy migration, caching, authentication, streaming, or deployment. Use react-development for framework-neutral components and api-design-first for external APIs.

• pos-sales-operations-engineering

  Use when implementing or reviewing a tenant-aware ERP POS, agent POS, or manual sales-entry workflow where customer defaults, product-to-stock identity, inventory timing, payments, permissions, and audit-safe posting must remain consistent. Use the design engine for visual craft.

• react-development

  Use when implementing or reviewing React components, hooks, state ownership, forms, rendering performance, error boundaries, or component tests. Use nextjs-app-router for Next.js server boundaries and ux-content-strategy for product content systems.

• tailwind-css

  Use when implementing or reviewing Tailwind CSS styling, responsive layouts, state variants, theme tokens, layers, grids, or build configuration. Use a design-system skill for visual direction and accessibility-wcag for formal accessibility review.

• ux-content-strategy

  Use when planning, governing, or upgrading product content as a system - voice charts, content-first design, UI text patterns, form completion gates, error taxonomy, content measurement, decision communication, lifecycle narrative, and content operations. Higher-level orchestration above tactical mi

• apple-game-platform-delivery

  Use when delivering a game on iOS, iPadOS, or macOS with Apple-native services, Metal diagnostics, controllers, haptics, cloud saves, signing, notarisation, sandboxing, or Mac window and display behaviour.

• game-2d-art-animation-and-vfx-pipeline

  Use when producing, importing, validating, or optimising 2D game concepts, sprites, atlases, tile sets, skeletal or frame animation, UI art, particles, VFX, resolution variants, or licensed source assets.

• game-3d-asset-pipeline

  Use when producing game-ready 3D environments, characters, props, materials, rigs, animations, LODs, collisions, Blender source/automation, FBX/glTF exports, or DCC-to-engine imports; use real-time-game-graphics for runtime rendering.

• game-accessibility-localisation-and-player-safety

  Use when designing or testing accessible gameplay, remapping, visual/audio alternatives, difficulty assists, localisation/internationalisation, cultural review, chat/community safety, reporting, moderation, parental controls, or player-support escalation.

• game-ai-behaviour-and-navigation

  Use when designing, implementing, profiling, or reviewing non-player-agent behaviour, navigation, perception, decision systems, crowds, reservations, behaviour trees, state trees, utility logic, encounter AI, or AI validation in a game; load an engine skill for concrete APIs.

• game-audio-implementation

  Use when designing, recording, licensing, editing, integrating, mixing, localising, profiling, or testing game music, ambience, dialogue, UI, Foley, spatial audio, and adaptive audio systems.

• game-build-release-engineering

  Use when creating reproducible Unity, Godot, Unreal, Android, iOS, or macOS game build pipelines, manifests, symbols, signing boundaries, artifact promotion, patching, certification, or rollback rehearsals.

• game-data-analytics-and-live-economy
• game-development-orchestration
• game-math-and-simulation
• game-narrative-and-interactive-story-design
• game-security-anti-cheat-and-abuse
• game-studio-delivery-and-commercial-operations
• game-testing-polish
• gameplay-systems-architecture
• godot-mobile-game-development
• lean-game-product-development
• level-world-and-content-production
• mobile-game-design
• mobile-game-performance
• mobile-game-release-liveops
• online-multiplayer-and-game-backend
• real-time-game-graphics
• unity-mobile-game-development
• unreal-game-development
• gis-enterprise-domain
• gis-platform-engineering
• ios-development
• ios-monetization
• ios-platform-capabilities
• ios-security-and-rbac
• algorithm-selection-and-complexity
• csharp-dotnet-development
• java-enterprise-development
• javascript-modern
• nodejs-development
• php-modern-standards
• python-data-analytics
• python-data-pipelines
• python-ml-predictive
• python-modern-standards
• typescript-effective
• typescript-full-stack
• kmp-development
• mobile-platform-operations
• pwa-offline-first
• bds-intake-and-monitoring-system-spec
• consulting-delivery-control-room
• content-writing
• customer-service-excellence
• document-spreadsheet-tooling-readiness
• excel-spreadsheets
• hospitality-hotel-restaurant-systems
• it-proposal-writing
• premium-software-product-execution
• product-discovery
• product-led-growth
• product-strategy-vision
• professional-word-output
• software-business-models
• software-pricing-strategy
• full-coverage-saas-seeding
• hr-module-design
• modular-saas-architecture
• multi-tenant-saas-architecture
• reporting-and-export-engineering
• saas-accounting-system
• saas-admin-backoffice-tooling
• saas-architecture-strategy
• saas-business-metrics
• saas-entitlements-and-plan-gating
• saas-erp-system-design
• saas-lifecycle-email-orchestration
• saas-managed-visual-assets
• saas-rate-limiting-and-quotas
• saas-sales-organization
• saas-seeder
• saas-sso-scim-enterprise-auth
• saas-tenant-data-portability-and-erasure
• stripe-payments
• subscription-billing
• tenant-document-numbering
• advanced-testing-strategy
• ai-assisted-development
• ai-slop-audit
• anti-ai-slop
• council
• doc-architect
• engine-control-plane
• git-collaboration-workflow
• github-ops
• implementation-status-auditor
• kaizen-improvement-system
• project-requirements
• santa-method
• sdlc-documentation
• skill-composition-standards
• skill-engine-audit
• skill-writing
• systematic-bug-diagnosis
• world-class-bid-red-team-and-delivery-qc
• world-class-engineering
• code-safety-scanner
• dpia-generator
• linux-security-hardening
• network-security
• vibe-security-skill
• web-app-security-audit

Subagents (10)

• architect

  Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.

• code-reviewer

  Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

• php-reviewer

  Expert PHP code reviewer specializing in PSR-12 compliance, PHP type system, common ORM patterns, security, and performance. Use for all PHP code changes. MUST BE USED for PHP projects.

• planner

  Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.

• pr-test-analyzer

  Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.

• security-reviewer

  Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.

• silent-failure-hunter

  Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation.

• tdd-guide

  Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Scales test depth to risk.

• type-design-analyzer

  Analyze type design for encapsulation, invariant expression, usefulness, and enforcement.

• typescript-reviewer

  Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all TypeScript and JavaScript code changes. MUST BE USED for TypeScript/JavaScript projects.

Hooks (1)

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/destructive-bash-gate.js"

Similar plugins