senior-dev

Plugin senior-dev from marketplace expert-ai-developer-skills in jggomez/expert-ai-developer-skills. Commands read from the repo's manifest — 2 days ago.

Skills (15)

• adversarial-challenger

  Adversarial stress testing, fuzzing, worst-case inputs, failure-path probes, timeout/reconnection simulations, and concurrency/memory stress.

• blackbox-tester

  Black-box browser verification validating real user flows, GUI forms, console/network errors, visual layouts, and 4-viewport screenshot evidence using deterministic Playwright execution.

• code-critic

  Independent code review inspecting cyclomatic complexity, DRY, SOLID, anti-patterns, maintainability, and interface robustness.

• code-implementer

  Guides the implementation of code using Test-Driven Development (TDD) and clean code principles. Trigger when implementing new features, fixing bugs, or refactoring existing code.

• code-smells-expert

  Analyzes source code to identify, classify, and diagnose architectural design flaws known as "Code Smells" and technical debt. Use this skill when requested to perform a technical audit, evaluate code quality, look for SOLID violations (especially SRP and OCP), or identify reasons why code is diffic

• compliance-verifier

  Guides the final quality assurance and compliance verification of a project. Trigger when checking non-functional requirements, static code analysis, test coverage, and security compliance before release.

• context-capture

  Use when finishing a task at State 5 (Ship & Finish) or when the user explicitly asks to "save context", "guarda contexto", "record decisions", or "hand off" — writes ultra-compact persistent memory to context/memory/ and ensures target-project root AGENTS.md (<= 90 lines) stays wired to DESIGN.md a

• context-restore

  Use at session start (State 0) or when asked to "load context", "catch up", or "what was done before" — prioritizes LLM Wiki Progressive Disclosure (context/memory/MEMORY.md) across Claude Code and Google Antigravity while supporting user-confirmed restore for scripted sessions (context/sessions/).

• loop-engineering

  Implements 3-Tier Adaptive SDLC state machines, capability-gated discovery, target-project AGENTS.md bootstrapping, isolated parallel worker execution (Disjoint Mode A / Git Worktree Mode B), and 3-loop self-correcting review gates.

• product-analyst

  Analyzes ambiguous feature requests, clarifies business rules, and authors the ultra-concise `## Product` section of the single discovery file docs/<feature-name>/spec.md (<= 50 lines) with standard User Stories (US-XX) and testable Acceptance Criteria (AC-XX).

• qa-tester

  Designs and executes Unit, Integration, and E2E test suites and authors concise, actionable IEEE/ISTQB QA Test Matrix artifacts (docs/<feature-name>/test-matrix.md <= 80 lines) backed by empirical exit code 0 terminal proof.

• refactoring-code-expert

  Executes structural improvements on existing code to increase maintainability, readability, and extensibility without altering external behavior. Use this skill to address technical debt, fix "Code Smells", apply design patterns, or improve adherence to SOLID principles.

• senior-architect-engineering

  Pragmatic software architecture and system design skill. Authors concise MADR Architecture Decision Records (docs/<feature-name>/adr-NNN-*.md <= 55 lines) and the `## Architecture` section of the single discovery file docs/<feature-name>/spec.md (<= 50 lines) grounded in KISS, YAGNI, SOLID, and clea

• senior-dev-orchestrator

  Orchestrates the software development lifecycle (LLM Wiki memory restoration, target AGENTS.md bootstrap, 3-tier dynamic routing, capability and risk-gated subagent dispatch, parallel TDD implementation with disjoint file or git worktree isolation, fail-honest E2E and adversarial verification, and m

• ui-ux-designer

  Expert UI/UX designer and design systems architect. Establishes official Google 2-layer DESIGN.md contracts (YAML tokens + 8 concise sections), optional feature UI deltas (`## Design` section of docs/<feature-name>/spec.md), accessibility (WCAG AA), and responsive component states for web and mobile

Subagents (10)

• architect-engineer

  Specialized subagent for pragmatic software architecture, clean module

• challenger

  Specialized adversarial subagent executing stress tests, fuzzing campaigns,

• code-implementer

  Specialized subagent for writing production-grade code using Test-Driven

• compliance-verifier

  Specialized subagent for final technical verification, quality attribute

• critic

  Specialized adversarial subagent performing independent, uncompromising

• e2e-blackbox-tester

  Specialized black-box browser verification subagent validating live web

• product-analyst

  Specialized subagent for product discovery, business rule disambiguation,

• qa-tester

  Specialized subagent for Integration and E2E test execution, boundary

• senior-dev-orchestrator

  Senior Developer Orchestrator that understands business requirements,

• ui-ux-designer

  Specialized subagent for UI/UX design systems, official Google 2-layer

MCP servers (3)

• cloudrun

  runs: npx -y @google-cloud/cloud-run-mcp

• firebase-mcp-server

  runs: npx -y firebase-tools@latest mcp

• playwright

  runs: npx -y @playwright/mcp@latest --isolated