By coolwuu
Orchestrate end-to-end feature development from OpenSpec specification to implementation, testing, code review, and deployment, with multi-agent parallel execution, browser automation, git workflows, and infrastructure debugging.
Show current git branch, uncommitted files, and recent commits
Append a tagged learning to the project's lesson file with domain and severity tags
Run the project verification suite defined in .claude/smart-dev.json
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
Layer-2 diagnostic agent for API/controller failures. Use when: unexpected status codes, curl vs browser diverge, filter returns wrong data, CORS errors, enum binding, response shape mismatch. Does NOT fix — emits findings only.
Reviews code changes for architectural consistency and patterns. Use PROACTIVELY after any structural changes, new services, or API modifications. Ensures SOLID principles, proper layering, and maintainability.
Design RESTful APIs, microservice boundaries, and database schemas. Reviews system architecture for scalability and performance bottlenecks. Use PROACTIVELY when creating new backend services or APIs.
Senior backend engineer specializing in scalable API development and microservices architecture. Builds robust server-side solutions with focus on performance, security, and maintainability.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Save current session state to a handover document for seamless continuation in a new session. Invoke manually or triggered automatically when context window reaches 85%.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when the user wants to delegate a task to OpenAI Codex CLI, get a second opinion, or run codex review on changes
Configurable 9-phase feature development workflow enforcer (Phase 0 Context Setup → Phase 8 Approval & Commit). Delegates planning to OpenSpec (proposal→specs→design→tasks) and enhances execution with superpowers skills (TDD, subagent-driven-development, worktrees, verification). Auto-validates phase transitions, manages state via context.md, and orchestrates specialized agents. Use when user says "start feature" or "resume feature", mentions implementing/building/creating a feature, needs structured development process, references TDD or test-driven development, asks about feature planning or implementation phases, references 9-phase workflow or mentions "Phase 1" or "Planning phase", needs approval gates or phase validation, or asks "how do I start a feature" or "what's the development workflow".
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
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.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
One plugin. Your entire dev workflow. Configured per-project.
42 skills | 59 agents | 11 hooks | 3 commands | 2 profiles
Project-specific conventions, build commands, and features — all opt-in via config.
| Feature | What it does | |
|---|---|---|
| :shield: | Safety hooks | Block rm -rf, git push --force, DROP TABLE — before they execute |
| :gear: | Config-driven conventions | Drop a JSON file, get project-specific rules injected every session |
| :repeat: | 9-phase dev workflow | Brainstorm → Plan → Implement → Review → Verify — enforced, not suggested |
| :busts_in_silhouette: | 59 specialist agents | Right model, right task — 51 sonnet, 7 opus, 1 haiku, all pre-configured |
| :floppy_disk: | Session continuity | Auto-handover saves state; resume picks up exactly where you left off |
| :zap: | Zero config start | Install and go — safety guards work immediately, no setup required |
# 1. Add the marketplace
/plugin marketplace add coolwuu/smart-dev-plugin
# 2. Install the plugin
/plugin install smart-dev@coolwuu-smart-dev-plugin
# 3. Verify
/plugin # → Installed tab shows smart-dev
That's it. Skills, agents, and hooks are available immediately.
The core workflow is dev-workflow — a structured 9-phase process from idea to merged code. Trigger it naturally:
"Start feature: add user authentication"
"I want to build a dark mode toggle"
"Let's implement the search API"
The workflow activates automatically when you mention building or implementing something. It walks you through:
| Phase | What happens | You do |
|---|---|---|
| 0 | Creates a git worktree + context file, runs explore | Describe the feature |
| 1 | Planning — generates proposal, specs, design, tasks | Approve each artifact |
| 2 | Reviews project conventions, checks readiness | Confirm |
| 3 | Implementation — TDD, subagent delegation, parallel execution | Write code / approve |
| 4 | Code review — dispatches reviewer agents in waves | Resolve findings |
| 5 | Refactoring pass — structural improvements | Approve changes |
| 6 | Summarization (optional) | Opt in |
| 7 | Retrospective (optional) | Opt in |
| 8 | Final verification, approval gate, commit/merge | Approve commit |
State is tracked in context.md — if a session ends mid-feature, just say "resume feature" and the workflow picks up where you left off.
Add to your project's CLAUDE.md to customize:
## Feature Development Workflow
**Phases:** 0,1,2,3,4,8
**TDD:** required
**FeatureDocsPath:** docs/features
| Option | Values | Default |
|---|---|---|
| Phases | 0-8 (comma-separated) | 0,1,2,3,8 |
| TDD | required / optional / none | optional |
| FeatureDocsPath | Path from repo root | Documentation/Requirements/Feature |
You don't have to use the full workflow. Every skill is independently invocable:
/smart-dev:auto-handover # Save session state before context runs out
/smart-dev:resume-handover # Resume from where you left off
/smart-dev:verify # Run your project's test/build/lint suite
/smart-dev:lesson # Capture a learning from this session
/smart-dev:dev-status # Quick git status overview
/smart-dev:codex # Delegate a task to OpenAI Codex CLI
/smart-dev:e2e-troubleshoot # 6-layer diagnostic ladder for E2E failures
/smart-dev:parallel-execution # Run multiple tasks via parallel subagents
/smart-dev:visual-ui-critique # Critique a UI screenshot
Even without configuration, these hooks fire automatically after installation:
rm -rf, git push --force, DROP TABLEmodel parameternpx claudepluginhub coolwuu/smart-dev-plugin --plugin smart-devHarness-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
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
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.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.