Unified development workflow — bridges superpowers (discipline/TDD) with dotcontext (agents/PREVC/context)
npx claudepluginhub nexuz-sys/devflow --plugin devflowDispatch a specialist agent or get a recommendation for the current task
Advance to the next PREVC phase after checking gate requirements
Search MemPalace for project memories
Show current PREVC phase, progress, operating mode, and available actions
Sync and update .context/ docs, agents, and skills with current project state
Start a PREVC development workflow, initialize project, or show help
System architecture design, technical decisions, and scalability review
Server-side architecture, APIs, database integration, and service layer design
Root cause analysis and targeted fixes with regression test coverage
Review code quality, patterns, best practices, and spec compliance
Schema design, query optimization, migrations, and data integrity
CI/CD pipelines, infrastructure, deployment, and operational tooling
API docs, README, inline documentation, and project context maintenance
Implement new features according to specifications and approved plans
UI development, components, state management, and user experience
MemPalace memory operations — diary writing, context retrieval, and palace organization for DevFlow workflows
iOS and Android development, mobile UX, and cross-platform considerations
Bottleneck identification, profiling, and targeted optimization
Generates and maintains product PRDs with phased roadmaps
Code restructuring, pattern improvements, and technical debt reduction
Vulnerability assessment, security review, and compliance checking
Test coverage, test design, and testing strategy
Use when you need to discover, select, or invoke a specialist agent for a specific task or PREVC phase
Use when designing, modifying, or reviewing APIs — REST, GraphQL, RPC, or internal interfaces. Covers contracts, versioning, error handling, and documentation.
Use during PREVC Execution phase when autonomy is assisted or autonomous — manages story-by-story loop with specialist agent dispatch, TDD enforcement, and bidirectional escalation
Use when triaging bugs, investigating unexpected behavior, or performing root cause analysis before fixing
Use when writing git commit messages — follows conventional commits with context-aware scope and body
Entrevista interativa para configurar .context/.devflow.yaml — detecta heurísticas git e pré-seleciona recomendações.
Use when you need to enrich any task with project context — codebase structure, semantic analysis, patterns, and conventions
Use to update existing .context/ docs, agents, and skills with current project state — called by /devflow-sync or automatically by /devflow init when .context/ already exists
Use when writing, updating, or reviewing documentation — API docs, README, inline comments, architecture docs
Use when decomposing a large feature into implementable chunks — identifies components, dependencies, and delivery order
Gate bloqueante auto-ativado antes de qualquer edição. Detecta a estratégia git do projeto e aplica branch protection + isolamento.
Set DevFlow language preference — all responses, hook messages, and interactions switch to the selected language
Search MemPalace for project memories — agent diaries, PREVC decisions, and historical context
Persistent learning memory — curated runbook of mistakes, corrections, and patterns that work. Always active, every session.
Automate testing of the NXZ Go mobile app (com.moober_self_checkout) using Appium MCP. Use this skill whenever the user wants to test, automate, interact with, or run QA on the NXZ Go app, the Moober self-checkout app, NXZ, or mentions testing a POS/self-checkout app on Android. Also trigger when the user says "test NXZ", "run NXZ Go test", "automate NXZ Go", "testar NXZ", or asks about E2E testing the self-checkout app.
Use when multiple independent tasks can be executed simultaneously — coordinates parallel agent/subagent dispatch
Use when creating or reviewing pull requests — PR description, review checklist, merge readiness
Use to generate a complete product PRD with phased roadmap — supports new projects and retroactive PRD for existing codebases
Use during PREVC Confirmation phase — finalizes the branch, updates documentation, and syncs context across tools
Use during PREVC Execution phase — implements the approved plan using dotcontext agent orchestration (Full Mode) or superpowers SDD/TDD (Lite/Minimal)
Use when starting any development task — orchestrates the PREVC workflow (Planning, Review, Execution, Validation, Confirmation) with scale-adaptive routing
Use during PREVC Planning phase — combines superpowers brainstorming (9-step Socratic process) with dotcontext context enrichment and plan scaffolding
Use during PREVC Review phase — validates design and plan through agent-driven review with superpowers code review discipline
Use during PREVC Validation phase — comprehensive verification including tests, security audit, and spec compliance check
Use when initializing DevFlow in a new project — scaffolds .context/ with project-aware agents, skills, and docs in dotcontext-compatible format
Use when restructuring code without changing behavior — safe patterns, test preservation, incremental steps
Use when assessing security of code, APIs, or infrastructure — OWASP-based review with severity classification
Use when creating new DevFlow skills — follows TDD-for-docs methodology from superpowers with devflow conventions
Use when designing test suites, generating test cases, or reviewing test coverage — covers unit, integration, and E2E strategies
Use when starting any conversation — establishes the unified development workflow combining superpowers discipline with dotcontext agents and PREVC workflow
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research