Spec-driven development framework — hybrid orchestration with 7 real subagents (executor, simplifier, code-reviewer, QA, adversarial verifier, researcher, roadmap), curated project memory feeding every spawn, strict dual-verifier mode, 6 phases with correction loops, deterministic SQLite audit via hooks, 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 subagent
Run a comprehensive project health diagnostic across code, tests, dependencies, security, and process. Use --deps for a focused dependency audit.
Reviews a diff or file list against spec quality criteria, conventions, and security — reports findings, never fixes code. Dispatched by /pwdev-code:review (in parallel with qa).
Implements ONE atomic pwdev-code task: code, verification, atomic commit, and execution summary. Dispatched by /pwdev-code:execute (including fix plans) — do not use for planning, review, or spec work.
Audits test coverage and runs the real test suite for implemented tasks; proposes missing-test skeletons. Dispatched by /pwdev-code:review in parallel with code-reviewer. Never writes production code.
Investigates stack, domain, and pitfalls for a feature and writes .planning/context/{domain,stack,pitfalls}.md. Dispatched by /pwdev-code:discover in parallel with the interview. Read-mostly; never makes design decisions.
Decomposes an approved PRD into the multi-file executable roadmap (.planning/product/roadmap/ hierarchy Phase→Epic→Feature→Task with full traceability). Dispatched by /pwdev-code:product roadmap.
Design precise, production-grade enterprise UI — dashboards, admin panels, SaaS interfaces, and data-heavy applications. Use this skill for professional software interfaces that need Jony Ive-level craft: clean, minimal, functional, with intentional personality. Do NOT use for creative landing pages, marketing sites, or experimental/artistic frontends.
Write and refine high-quality user stories — INVEST criteria, "As a X, I want Y, so that Z" format, Gherkin acceptance criteria when applicable, definition of ready, anti-patterns, and a review checklist. Use when creating or reviewing user stories, PRD section 6, backlog items, or acceptance criteria. Do NOT use for technical specs, architecture decisions, or task decomposition.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
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.
The marketplace now goes beyond the development workflow:
perf-analyzer / perf-patterns / perf-optimize + analyst subagent)
that closes the loop: research → brief → copy → review → publish → analyze.The five original plugins were rebuilt on the modern Claude Code plugin system. No slash command was renamed or removed — internals were restructured.
.planning/pwdev-audit.db, rows distinguished by the plugin column) is
now written by plugin hooks: real duration_ms/session_id,
config_changes finally populated. A secret-guard PreToolUse hook
blocks reads of .env/*.pem/*.key/id_rsa* in every plugin.references/ directory,
resolved via ${CLAUDE_PLUGIN_ROOT} (no more duplicated blocks or broken
relative paths)./audit — single-statement SELECT-only query guard; portable
POSIX shell throughout./pwdev-code:memory + versioned
.planning/memory/) feeding every spawn; lessons auto-captured from
rejected verifications and blocked reviews.verify → fix plans →
execute --fix (max 2 iterations); review gate blocks verify;
verify --strict runs 2 parallel verifiers (worst verdict wins)./pwdev-code:simplify — two-pass quality refactor (propose ≥80%
confidence → human approves by ID → apply + refactor commit).skill-user-stories + /pwdev-code:product stories (INVEST, Gherkin
ACs, definition of ready).references/pwdevia-method.md); /status now detects FAILED/CAVEATS.prd.json
structure finally defined; init no longer configures model profiles
(nothing here resolves a model).Stack-agnostic UI/UX engineering framework for Claude Code — 6 real subagents + inline orchestrator/theme personas, 5-phase workflow with human gates, Figma integration, WCAG 2.1 AA, deterministic SQLite audit via hooks. Supports shadcn-vue, shadcn/ui, PrimeVue, Untitled UI, Tailwind Plus, and custom stacks.
Configure and manage Claude Code status line — installs a rich, configurable bash status bar (single-jq-pass, dynamic colors, formatted tokens, truncated paths) showing model, git branch, context usage, rate limits, and token counts.
PRD creation framework for Claude Code — 12-step interview-driven Product Requirements Documents, run inline (the interviewer talks to you; zero subagents by design), technology-agnostic, Markdown + canonical JSON export, deterministic SQLite audit via hooks.
Simplified AI-assisted feature development — PWDEVIA 7-question action plans created inline (interviewing you, max 2 rounds), executed by a real executor subagent with fresh context and IMPLEMENT/REPORT modes, deterministic SQLite audit via hooks. Fast, practical, no ceremony.
Framework de DevOps com postura de execução segura — leitura livre, mutação sob confirmação por comando, destrutivo bloqueado. 19 skills cobrindo AWS, Kubernetes, Docker, Linux, Nginx, PostgreSQL, observabilidade, incidente, segurança, Proxmox, automação, performance, backup, Laravel, confiabilidade, FinOps, infraestrutura de IA e documentação contínua. 4 subagentes e guard script como segunda barreira.
npx claudepluginhub pwdev-solucoes/pwdev-claude-marketplace --plugin pwdev-codeComprehensive 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.
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.