Spec-driven development framework for Claude Code — 11 specialized agents, 6 phases (including code review + QA), and extensible skills that turn requirements into verified, traceable code.
Query the audit trail database for events, decisions, artifacts, and statistics. Export full PDF report.
Run the design phase to produce spec.md with architecture decisions
Run the discovery phase to gather requirements through interviews and research
Execute planned tasks by delegating to the executor agent
Run a comprehensive project health diagnostic across code, tests, dependencies, security, and process. Use --deps for a focused dependency audit.
You are a **Senior Software Architect** who makes technical decisions
You are a **Senior Code Reviewer** with deep expertise in software quality,
You are a **Senior Software Engineer** focused exclusively on
You are a **Technical Product Owner and Requirements Engineer** who extracts
You are a **Planning Engineer** who decomposes spec.md into atomic tasks
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Read this in Português Brasileiro
Plugin marketplace for Claude Code.
Paulo Soares, CTO of PWDEV, a company focused on developing GovTech solutions, believes that artificial intelligence is fundamentally reshaping software development. More than a passing trend, this shift represents a new way to support professionals, extend capabilities, and bring greater consistency across the entire development lifecycle. Guided by this vision, PWDEV is making these solutions available to help teams work with more structure, quality, and predictability.
Our plugins turn Claude Code from a general-purpose coding assistant into a disciplined engineering partner through specialized agents, structured workflows, and domain-specific knowledge packs.
Core philosophy across all plugins:
Never execute without a plan. Never ship without verification.
install, uninstall, customize, preview.tailwind-plus — Added to supported stacks in /pwdev-uiux:stack command.product, maintenance, session, manager-skills)./pwdev-code:execute auto-detects idle sessions (>2h) and generates fresh executor context./init, used silently across all commands.performance, balanced, or economy profiles to control which Claude model (Opus/Sonnet/Haiku) each agent uses..planning/pwdev-audit.db records all commands, decisions, and artifacts. Disabled by default, never versioned..planning/config.json, shared across all plugins.| Plugin | Description | Version | License |
|---|---|---|---|
| pwdev-code | Spec-driven development framework — 11 agents, 6 phases, 14 commands | 1.2.0 | Apache-2.0 |
| pwdev-uiux | UI/UX engineering framework — 8 agents, 5-phase workflow, Figma integration, WCAG 2.1 AA | 1.1.2 | Apache-2.0 |
| pwdev-feat | Simplified feature development — PWDEVIA 7-question plans + executor, fast and practical | 1.1.2 | Apache-2.0 |
| pwdev-prd | Interview-driven PRD creation — 12-step structured interview, Markdown + JSON, technology-agnostic | 1.1.2 | Apache-2.0 |
| pwdev-statusline | Rich terminal status line — model, git branch, context bar, rate limits, tokens | 1.0.0 | Apache-2.0 |
Framework that orchestrates 11 specialized agents across 6 phases to ensure every line of code is planned, traceable, and verified.
PRD ─▶ ROADMAP ─▶ DISCOVER ─▶ DESIGN ─▶ PLAN ─▶ EXECUTE ─▶ REVIEW ─▶ VERIFY
Agents: Product Manager, Delivery Lead, Requirements Engineer, Technical Analyst, Software Architect, Planning Engineer, Implementation Engineer, Code Reviewer, QA Engineer, Spec Verifier, Generalist Engineer
See the full plugin documentation.
Stack-agnostic UI/UX engineering framework that orchestrates 8 specialized agents across a 5-phase workflow.
UNDERSTAND ─▶ STRUCTURE ─▶ IMPLEMENT ─▶ REVIEW ─▶ HANDOFF
Agents: Orchestrator, UX Analyst, Design Bridge, UI Scanner, UI Builder, Theme Builder, A11y Reviewer, UX Critic
Key features: Figma MCP integration, WCAG 2.1 AA auditing, 7-axis UX review, project-specific contextual skills
See the full plugin documentation.
Simplified AI-assisted feature development using the PWDEVIA 7-question methodology. Describe what you want, get a structured plan, execute it.
Describe ─▶ Plan ─▶ Execute
Agents: PWDEVIA (Prompt Engineer) + Executor
npx claudepluginhub pwdev-solucoes/pwdev-claude-marketplace --plugin pwdev-codeSimplified AI-assisted feature development — generates structured action plans using the PWDEVIA 7-question methodology and executes them. Fast, practical, no ceremony.
Stack-agnostic UI/UX engineering framework for Claude Code — 8 agents, 5-phase workflow, Figma integration, WCAG 2.1 AA. Supports shadcn-vue, shadcn/ui, PrimeVue, Untitled UI, Tailwind Plus, and custom stacks.
Configure and manage Claude Code status line — installs a rich bash-based status bar showing model, git branch, context usage, rate limits, and token counts.
PRD creation framework for Claude Code — structured interview-driven Product Requirements Documents for features and systems, technology-agnostic, with Markdown + JSON export.
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.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
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.