convex-backend

Installation
CLI
npx skills add https://github.com/korallis/Droidz --skill convex-backend

Install this skill with the CLI and start using the SKILL.md workflow in your workspace.

Last updated 4/30/2026

πŸ€– Droidz - Spec-Driven Development for AI

Transform how you build software with AI agents. Droidz is a complete framework that brings structure, standards, and systematic workflows to AI-assisted development.

Instead of ad-hoc prompting and context loss, Droidz gives you:

  • πŸ“‹ Spec-driven workflow - Plan β†’ Spec β†’ Tasks β†’ Implementation
  • πŸš€ Parallel execution - Run multiple task groups simultaneously (NEW!)
  • πŸ€– 8 specialized agents - Each expert in their domain
  • πŸ“š 50+ production skills - From TDD to Next.js to security patterns
  • πŸ“ Team standards - Consistent code across all features
  • πŸ”„ Repeatable process - Same quality, every time

Stop reinventing workflows. Start shipping faster.


πŸ’¬ Join Our Discord Community

Built specifically for Ray Fernando's Discord members! 🎯

Get early access, share tips, connect with contributors, and influence future development.

β†’ Join Discord Community


πŸ’ Support This Project

If Droidz saves you time, consider supporting its development!

β†’ Donate via PayPal (@gideonapp)

Your support helps maintain and improve this framework! πŸ™

With Gratitude

We're deeply thankful for the generosity of friends who keep this framework alive:

  • Sorennza
  • Ray Fernando
  • Douwe de Vries

Every contributionβ€”large or smallβ€”directly fuels new features, improvements, and continued open distribution. Thank you for believing in Droidz.


Quick Start

# 1. Navigate to your project
cd /path/to/your/project

# 2. Install Droidz (one command!)
bash <(curl -fsSL https://raw.githubusercontent.com/korallis/Droidz/main/install.sh)

# 3. Follow the interactive menu to choose your AI platform
# (Factory AI, Claude Code, Cursor, etc.)

# 4. Restart your AI tool

# 5. Start using workflows!
> /standards-shaper  # Set up your project standards
> /plan-product      # Plan your product
> /shape-spec        # Design a feature

Table of Contents


Why Droidz?

The Problem with AI Development

Without structure, AI-assisted development leads to:

  • ❌ Inconsistent code quality
  • ❌ Lost context between sessions
  • ❌ Vague requirements β†’ Rework
  • ❌ No team alignment
  • ❌ Hard to onboard new devs

The Droidz Solution

Droidz brings systematic workflows to AI development:

Planning β†’ Specification β†’ Task Breakdown β†’ Implementation
   ↓            ↓               ↓                ↓
Product      Detailed       Actionable     Guided execution
 docs         spec.md        tasks.md      with standards

Result: Predictable, high-quality output every time.


The Droidz Workflow

Droidz follows a proven 8-phase cycle for building features:

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                    DROIDZ WORKFLOW                          β”‚
β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
β”‚                                                             β”‚
β”‚  Phase 0: Setup Standards        β†’ /standards-shaper       β”‚
β”‚           ↓                                                 β”‚
β”‚  Phase 1: Product Planning       β†’ /plan-product           β”‚
β”‚           ↓                                                 β”‚
β”‚  Phase 2: Spec Shaping           β†’ /shape-spec             β”‚
β”‚           ↓                                                 β”‚
β”‚  Phase 3: Spec Writing           β†’ /write-spec             β”‚
β”‚           ↓                                                 β”‚
β”‚  Phase 4: Task Creation          β†’ /create-tasks           β”‚
β”‚           ↓                                                 β”‚
β”‚  Phase 5: Task Orchestration     β†’ /orchestrate-tasks      β”‚
β”‚           ↓                                                 β”‚
β”‚  Phase 6: Implementation         β†’ /implement-tasks  πŸš€     β”‚
β”‚           β”‚                        (3 MODES!)               β”‚
β”‚           β”‚                                                 β”‚
β”‚           β”œβ”€β†’ A) Parallel (FAST) - All tasks run together  β”‚
β”‚           β”œβ”€β†’ B) Interactive - Live progress updates       β”‚
β”‚           └─→ C) Sequential - One at a time                β”‚
β”‚           ↓                                                 β”‚
β”‚  Phase 7: Continuous Improvement β†’ iterate & refine        β”‚
β”‚                                                             β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Why This Works

  1. Context Persists - Specs and standards live in your repo
  2. Clear Handoffs - Each phase produces artifacts for the next
  3. Parallel Execution - Implement multiple task groups simultaneously (NEW!)
  4. Progress Tracking - See real-time updates as tasks complete
  5. Team Alignment - Everyone works from the same spec
  6. Quality Gates - Standards enforced automatically
  7. Scalable - Same process for small features or large systems

πŸš€ NEW: Parallel Execution

Speed up implementation by 4x! Droidz now supports parallel execution using Factory AI's Droid Exec.

Three Execution Modes

When you run /implement-tasks, choose how to execute:

A) Parallel Execution (FAST) ⚑

  • All task groups run simultaneously
  • Uses Factory's headless Droid Exec mode
  • Auto-loads API key from droidz/config.yml
  • Bounded concurrency (configurable, default: 4)
  • Robust error handling
  • Best for: Multi-group implementations
# Just run the script - API key loads from droidz/config.yml
$ bash droidz/specs/[spec]/implementation/run-parallel.sh

πŸš€ Starting parallel implementation...
πŸ“„ Loading configuration from droidz/config.yml
βœ… Using API key from config.yml
βš™οΈ  Autonomy level: medium
πŸ”’ Max parallel: 4

▢️  Starting: 1-database-setup.md
▢️  Starting: 2-api-endpoints.md
▢️  Starting: 3-frontend-ui.md
▢️  Starting: 4-testing.md
βœ… Completed: 1-database-setup.md
βœ… Completed: 2-api-endpoints.md
βœ… Completed: 3-frontend-ui.md
βœ… Completed: 4-testing.md

πŸŽ‰ All task groups completed!

B) Interactive with Live Progress πŸ“Š

  • Sequential execution with real-time TodoWrite updates
  • See tool calls and results as they happen
  • Best for: Learning, debugging, following along

C) Sequential Delegation πŸ”„

  • Traditional one-at-a-time execution
  • Simple and reliable
  • Best for: Single task groups

Requirements for Parallel Mode

One-Time Setup:

# 1. Copy the config template
cp droidz/config.yml.template droidz/config.yml

# 2. Get your Factory API key
# Visit: https://app.factory.ai/settings/api-keys

# 3. Edit droidz/config.yml and add your key:
factory_api_key: "fk-your-key-here"

# That's it! The script will auto-load your key from config.yml
# ⚠️  config.yml is in .gitignore - your key won't be committed

Optional Configuration:

You can also configure in droidz/config.yml:

  • default_autonomy_level: "low", "medium", or "high" (default: "medium")
  • max_parallel_executions: 1-10 (default: 4)

Running Parallel Execution:

# Just run the script - API key loads automatically
bash droidz/specs/[your-spec]/implementation/run-parallel.sh

Installation

Prerequisites

  • One of these AI tools:
    • Factory AI
    • Claude Code
    • Cursor
    • Cline
    • Codex CLI
    • VS Code with AI extension

Install Command

# Navigate to your project first!
cd /path/to/your/project

# Run the installer
bash <(curl -fsSL https://raw.githubusercontent.com/korallis/Droidz/main/install.sh)

What Gets Installed

The installer creates these directories in your project:

your-project/
β”œβ”€β”€ .factory/          # Factory AI droids & commands (if selected)
β”‚   β”œβ”€β”€ droids/        # 8 specialized droids
β”‚   └── commands/      # 20+ workflow commands
β”œβ”€β”€ .claude/           # Claude Code agents & commands (if selected)
β”‚   β”œβ”€β”€ agents/        # 8 specialized agents
β”‚   └── commands/      # 20+ workflow commands
└── droidz/            # Shared across all platforms
    β”œβ”€β”€ standards/     # Your team's coding standards
    β”‚   β”œβ”€β”€ global/    # Global conventions
    β”‚   β”œβ”€β”€ backend/   # API, database patterns
    β”‚   β”œβ”€β”€ frontend/  # Components, styling
    β”‚   └── testing/   # Test patterns
    β”œβ”€β”€ product/       # Product documentation
    β”‚   β”œβ”€β”€ mission.md
    β”‚   β”œβ”€β”€ roadmap.md
    β”‚   └── tech-stack.md
    └── specs/         # Feature specifications
        └── [feature]/
            β”œβ”€β”€ spec.md
            β”œβ”€β”€ tasks.md
            └── planning/

Everything is checked into git and shared with your team.

Post-Installation

  1. Restart your AI tool - Required for new commands/agents to load
  2. Verify installation:
    > /commands     # See available commands
    > /droids       # See available droids (Factory AI)
    > /agents       # See available agents (Claude Code)
    

Commands Reference

Droidz provides 20+ commands organized by phase. Here are the essential ones:

Setup & Planning Commands

/standards-shaper ⭐ START HERE

Purpose: Create project-wide coding standards

When to use: Once per project, before any development

What it does:

  • Detects your tech stack (React, Next.js, TypeScript, etc.)
  • Creates standards for global, backend, frontend, testing
  • Generates dos/don'ts for consistency

Output:

droidz/standards/
β”œβ”€β”€ global/
β”‚   β”œβ”€β”€ coding-principles.md
β”‚   β”œβ”€β”€ error-handling.md
β”‚   └── security.md
β”œβ”€β”€ backend/
β”‚   β”œβ”€β”€ api-design.md
β”‚   └── database.md
β”œβ”€β”€ frontend/
β”‚   β”œβ”€β”€ components.md
β”‚   └── styling.md
└── testing/
    └── testing-patterns.md

Example:

> /standards-shaper

AI: I'll analyze your project and create standards...
AI: Detected: Next.js 14, TypeScript, Tailwind, Prisma
AI: Creating standards with framework-specific examples...

βœ… Created 12 standards files
βœ… All standards include your actual tech stack

/plan-product

Purpose: Define product vision and roadmap

When to use: Starting new products, major milestones, team onboarding

What it does:

  • Asks questions about your product
  • Creates mission statement
  • Builds phased roadmap
  • Documents tech stack decisions

Output:

droidz/product/
β”œβ”€β”€ mission.md        # Vision, goals, success metrics
β”œβ”€β”€ roadmap.md        # Phases, features, timeline
└── tech-stack.md     # Technologies and rationale

Example:

> /plan-product

AI: What problem does your product solve?
You: Task management for remote teams

AI: Who are your target users?
You: Remote engineering teams of 5-50 people

[More questions...]

βœ… Created mission.md
βœ… Created roadmap.md (4 phases)
βœ… Created tech-stack.md

Specification Commands

/shape-spec

Purpose: Shape requirements for a new feature

When to use: Before building anything new

What it does:

  • Asks clarifying questions
  • Researches similar implementations (if Exa/Ref available)
  • Saves requirements and decisions
  • Creates spec folder structure

Output:

droidz/specs/2024-11-24-user-authentication/
β”œβ”€β”€ planning/
β”‚   β”œβ”€β”€ requirements.md   # What you need
β”‚   β”œβ”€β”€ decisions.md      # Key choices made
β”‚   └── visuals/          # Wireframes, screenshots
└── README.md             # Overview

Example:

> /shape-spec

AI: What feature are you planning?
You: User authentication with OAuth

AI: Which OAuth providers?
You: Google and GitHub

AI: What user data do you need to store?
You: Email, name, profile picture

[More questions...]

βœ… Saved requirements.md
βœ… Saved decisions.md
βœ… Created spec folder

/write-spec

Purpose: Create detailed specification from shaped requirements

When to use: After shaping (Phase 2 complete)

What it does:

  • Reads shaped requirements
  • Generates comprehensive spec document
  • Includes architecture, APIs, data models, UI, security, testing

Output:

droidz/specs/2024-11-24-user-authentication/
β”œβ”€β”€ spec.md              # ⭐ THE SPEC
β”œβ”€β”€ planning/
β”‚   └── requirements.md
└── README.md

spec.md structure:

# User Authentication Specification

## 1. Overview
## 2. User Stories
## 3. Technical Architecture
## 4. Data Models
## 5. API Endpoints
## 6. UI/UX Flow
## 7. Security Considerations
## 8. Testing Strategy
## 9. Success Metrics

Example:

> /write-spec

AI: Reading shaped requirements...
AI: Generating specification...

βœ… Created spec.md (2,400 lines)
βœ… Includes:
   - 5 user stories
   - Database schema
   - 8 API endpoints
   - Security checklist
   - 12 test scenarios

Implementation Commands

/create-tasks

Purpose: Break spec into implementable tasks

When to use: After spec is written

What it does:

  • Reads spec.md
  • Breaks into logical task groups
  • Creates tasks with dependencies
  • Adds acceptance criteria

Output:

droidz/specs/2024-11-24-user-authentication/
β”œβ”€β”€ spec.md
β”œβ”€β”€ tasks.md             # ⭐ IMPLEMENTATION TASKS
└── planning/

tasks.md structure:

# Implementation Tasks

## Task Group 1: Database Setup
- [ ] 1.1: Create users table
- [ ] 1.2: Create oauth_tokens table
- [ ] 1.3: Add database indexes

## Task Group 2: OAuth Integration
- [ ] 2.1: Set up OAuth configs
- [ ] 2.2: Create callback endpoints
- [ ] 2.3: Handle token exchange

## Task Group 3: Frontend
- [ ] 3.1: Create login page
- [ ] 3.2: Add OAuth buttons
- [ ] 3.3: Handle redirects

## Task Group 4: Testing
- [ ] 4.1: Unit tests for OAuth
- [ ] 4.2: E2E login flow test
- [ ] 4.3: Security tests

Example:

> /create-tasks

AI: Reading spec.md...
AI: Identifying task groups...
AI: Creating tasks with dependencies...

βœ… Created tasks.md
βœ… Found 4 task groups
βœ… Total: 23 tasks

/orchestrate-tasks

Purpose: Plan multi-agent implementation

When to use: Before implementing (optional but recommended)

What it does:

  • Shows task groups
  • Lets you assign specialists (if using subagents)
  • Maps relevant standards to each group
  • Generates implementation prompts

Output:

droidz/specs/2024-11-24-user-authentication/
β”œβ”€β”€ spec.md
β”œβ”€β”€ tasks.md
β”œβ”€β”€ orchestration.yml    # ⭐ COORDINATION PLAN
└── implementation/
    └── prompts/
        β”œβ”€β”€ 1-database-setup.md
        β”œβ”€β”€ 2-oauth-integration.md
        β”œβ”€β”€ 3-frontend.md
        └── 4-testing.md

Example:

> /orchestrate-tasks

AI: Found 4 task groups. Assign specialists:

1. Database Setup β†’ ?
2. OAuth Integration β†’ ?
3. Frontend β†’ ?
4. Testing β†’ ?

You:
1. backend-specialist
2. backend-specialist
3. frontend-specialist
4. test-specialist

AI: Map standards for each group:

You:
1. backend/*, global/security.md
2. backend/*, global/error-handling.md
3. frontend/*, global/
4. testing/*

βœ… Created orchestration.yml
βœ… Generated 4 implementation prompts

/implement-tasks

Purpose: Execute implementation with parallel execution support

When to use: After tasks are created

Three Execution Modes:

A) Parallel Execution (FAST) πŸš€

  • Uses Factory's Droid Exec (headless mode) for true concurrent processing
  • Runs all task groups simultaneously
  • Best for: Multi-group implementations
  • Requirements: Factory API key in droidz/config.yml (one-time setup)
  • Features:
    • Auto-loads API key from config file
    • Bounded concurrency (configurable, default: 4)
    • Configurable autonomy level (low/medium/high)
    • Robust error handling (if one fails, others continue)
    • All droids update same tasks.md file
    • Real-time output from all executions

B) Interactive with Live Progress πŸ“Š

  • Uses Task tool + TodoWrite for real-time updates
  • Sequential execution with live progress tracking visible in session
  • Best for: Following along, learning, debugging
  • Features:
    • Live TodoWrite updates
    • See tool calls and results as they happen
    • Track progress as each task group completes

C) Sequential Delegation (SIMPLE) πŸ”„

  • Traditional one-at-a-time implementation
  • Best for: Single task group, simple implementations

Example (Parallel Mode):

> /implement-tasks

How would you like to execute implementation?
A) Parallel Execution (FAST) - Using Droid Exec
B) Interactive with Live Progress - Using TodoWrite
C) Sequential Delegation (SIMPLE)

Enter A, B, or C: A

βœ… Created parallel execution setup

PROMPTS: droidz/specs/2024-11-24/implementation/prompts/
β”œβ”€β”€ 1-database-setup.md
β”œβ”€β”€ 2-api-endpoints.md
β”œβ”€β”€ 3-frontend-ui.md
└── 4-testing.md

SCRIPT: run-parallel.sh

TO EXECUTE:
$ bash droidz/specs/2024-11-24/implementation/run-parallel.sh

πŸš€ Starting parallel implementation...
πŸ“„ Loading configuration from droidz/config.yml
βœ… Using API key from config.yml
βš™οΈ  Autonomy level: medium
πŸ”’ Max parallel: 4

▢️  Starting: 1-database-setup.md
▢️  Starting: 2-api-endpoints.md
▢️  Starting: 3-frontend-ui.md
▢️  Starting: 4-testing.md
βœ… Completed: 1-database-setup.md
βœ… Completed: 2-api-endpoints.md
βœ… Completed: 3-frontend-ui.md
βœ… Completed: 4-testing.md

πŸŽ‰ All task groups completed!

Utility Commands

/improve-skills

Purpose: Enhance AI agent skills

When to use: Customizing agent capabilities

What it does:

  • Shows current skills
  • Lets you improve descriptions
  • Adds examples
  • Makes skills more discoverable

Specialized Agents

Droidz includes 8 specialized agents, each expert in their domain:

1. product-planner

Expertise: Product strategy, roadmaps, vision

Use when:

  • Starting new products
  • Planning major features
  • Creating product documentation

What it creates:

Best for: Product managers, founders, tech leads


2. spec-shaper

Expertise: Requirements gathering, research

Use when:

  • Feature requirements are unclear
  • Need to research implementations
  • Validating technical approach

What it does:

  • Asks clarifying questions
  • Researches patterns (with Exa/Ref)
  • Documents decisions
  • Shapes clear requirements

Best for: Early-stage feature design


3. spec-writer

Expertise: Writing detailed specifications

Use when:

  • Have shaped requirements
  • Need implementable spec
  • Building complex features

What it creates:

  • Comprehensive spec.md with:
    • Architecture
    • Data models
    • API contracts
    • UI flows
    • Security considerations
    • Testing strategy

Best for: Detailed feature planning


4. spec-verifier

Expertise: Specification review

Use when:

  • Validating specs before implementation
  • Checking completeness
  • Finding gaps

What it checks:

  • Completeness
  • Clarity
  • Implementability
  • Security considerations
  • Test coverage

Best for: Quality assurance, pre-implementation review


5. tasks-list-creator

Expertise: Breaking specs into tasks

Use when:

  • Have completed spec
  • Ready to start implementation
  • Need task breakdown

What it creates:

  • tasks.md with:
    • Logical task groups
    • Clear dependencies
    • Acceptance criteria
    • Size estimates

Best for: Implementation planning


6. implementer

Expertise: Feature implementation

Use when:

  • Have tasks defined
  • Ready to code
  • Following spec and standards

What it does:

  • Reads spec and tasks
  • Implements features
  • Follows project standards
  • Writes tests
  • Updates progress

Best for: Actual development work


7. implementation-verifier

Expertise: Testing and verification

Use when:

  • Implementation complete
  • Need to verify against spec
  • Running test suite

What it does:

  • Verifies against acceptance criteria
  • Runs all tests
  • Checks standards compliance
  • Creates verification report

Best for: Quality assurance, pre-merge checks


8. spec-initializer

Expertise: Spec folder setup

Use when:

  • Starting new spec
  • Need folder structure

What it creates:

  • Spec folder with proper structure
  • README.md template
  • planning/ directory

Best for: Quick spec initialization


Best Practices

βœ… DO:

1. Start with Standards

First feature? Run this FIRST:
> /standards-shaper

Why: Standards ensure consistency from day one

2. Always Shape Before Writing

> /shape-spec     # Ask questions, clarify
> /write-spec     # Write detailed spec

Why: Shaping prevents vague specs and rework

3. Break Down Complex Tasks

Don't:
- [ ] Build entire auth system

Do:
- [ ] Create database tables
- [ ] Implement OAuth flow
- [ ] Add login UI
- [ ] Write tests

Why: Small tasks are easier to implement and track

4. Use Orchestration for Big Features

> /orchestrate-tasks   # Plan before implementing

Why: Coordination prevents conflicts and missed requirements

5. Reference Specs in Code

// See droidz/specs/2024-11-24-user-authentication/spec.md
// Section 4.2: OAuth Token Storage
export const saveOAuthToken = async (userId, token) => {
  // ...
}

Why: Links code to requirements

6. Update Standards as You Learn

Found a better pattern? Add to:
droidz/standards/[category]/[pattern].md

Why: Standards evolve with your team

7. Keep Specs Updated

Feature changed during implementation?
Update spec.md to match reality.

Why: Specs are documentation, keep them accurate

8. Use Task Groups

Group 1: Database
Group 2: Backend
Group 3: Frontend
Group 4: Testing

Why: Logical organization, easier to delegate


❌ DON'T:

1. Skip Planning

❌ Jump straight to code
βœ… Plan β†’ Spec β†’ Tasks β†’ Implement

2. Write Vague Specs

❌ "Add user authentication"
βœ… "Implement OAuth 2.0 with Google/GitHub, 
    JWT tokens, refresh token rotation,
    secure storage per spec section 5.3"

3. Ignore Standards

❌ Implement however you want
βœ… Follow droidz/standards/ patterns

4. Mix Concerns in Tasks

❌ - [ ] Build frontend and backend
βœ… - [ ] Build backend API
    - [ ] Build frontend UI

5. Lose Context

❌ "What were we building again?"
βœ… Read droidz/specs/[feature]/spec.md

6. Skip Testing

❌ Implement without tests
βœ… Tests are part of implementation (Task Group 4)

7. Work in Isolation

❌ Solo development without docs
βœ… Use workflow so team can collaborate

8. Forget to Commit Droidz Files

❌ .gitignore droidz/
βœ… Commit specs, standards, product docs

Examples

Example 1: Building a New Feature

Scenario: Add real-time notifications to your app

# Phase 0: Standards exist (one-time setup)
> /standards-shaper
βœ… Standards created

# Phase 1: Product context
> /plan-product
βœ… Product docs created

# Phase 2: Shape the feature
> /shape-spec

AI: What feature are you planning?
You: Real-time notifications with WebSockets

AI: What types of notifications?
You: New messages, mentions, system alerts

AI: How should they be delivered?
You: Browser push + in-app toast

[More questions...]

βœ… requirements.md created

# Phase 3: Write detailed spec
> /write-spec

βœ… spec.md created (1,800 lines)
   Includes: WebSocket architecture, message schema,
   push notification setup, UI components

# Phase 4: Break into tasks
> /create-tasks

βœ… tasks.md created
   Found 5 task groups, 28 tasks

# Phase 5: Orchestrate (optional)
> /orchestrate-tasks

You assign:
1. WebSocket Server β†’ backend-specialist
2. Message Schema β†’ backend-specialist
3. Push Notifications β†’ backend-specialist
4. UI Components β†’ frontend-specialist
5. E2E Tests β†’ test-specialist

βœ… Implementation prompts generated

# Phase 6: Implement
[Use subagents or implement manually with prompts]

βœ… All 28 tasks completed
βœ… Tests passing
βœ… Feature ready to ship! πŸš€

Example 2: Onboarding New Team Member

# New dev joins your team

# 1. They clone the repo
git clone your-repo
cd your-repo

# 2. They install Droidz
bash <(curl -fsSL https://raw.githubusercontent.com/korallis/Droidz/main/install.sh)

# 3. They read your docs
cat droidz/product/mission.md      # Understand the product
cat droidz/product/tech-stack.md   # See tech choices
ls droidz/standards/                # Review coding standards

# 4. They explore past features
ls droidz/specs/                    # See all features built
cat droidz/specs/2024-11-20-*/spec.md  # Read a spec

# 5. They start their first feature
> /shape-spec                       # Learn the workflow
> /write-spec
> /create-tasks
> /implement-tasks

# Result: New dev is productive day 1, following same patterns as team

Example 3: Mid-Project Standards Creation

Scenario: You have a codebase but no standards yet

# Run standards-shaper
> /standards-shaper

AI: I'll analyze your codebase...
AI: Detected:
   - React 18 with hooks
   - TypeScript (strict mode)
   - Tailwind CSS
   - tRPC API
   - Prisma ORM
   - Vitest tests

AI: Creating standards with your patterns...

βœ… Created 15 standards files
βœ… Examples use YOUR tech stack
βœ… Patterns match YOUR code style

# Now all future features follow these standards automatically

Customization

Modifying Standards

Standards are just markdown files. Edit them to match your team:

# Edit any standard
code droidz/standards/frontend/components.md

# Add your own patterns
echo "## Our Custom Button Pattern" >> droidz/standards/frontend/components.md
echo "..." >> droidz/standards/frontend/components.md

# Standards are preserved during Droidz updates

Creating Custom Agents

Add your own specialized agents:

# Factory AI
create .factory/droids/database-expert.md

# Claude Code
create .claude/agents/database-expert.md

Format:

---
name: database-expert
description: PostgreSQL and Prisma expert for database design
color: blue
model: inherit
---

You are a database design expert...

Adding Custom Commands

# Factory AI
create .factory/commands/optimize-queries.md

# Claude Code
create .claude/commands/optimize-queries.md

Troubleshooting

Commands Not Showing Up

Problem: Installed Droidz but commands don't work

Solutions:

  1. Restart your AI tool (required after installation)
  2. Verify installation:
    > /commands     # Should show 20+ commands
    
  3. Check file locations:
    ls .factory/commands/  # Factory AI
    ls .claude/commands/   # Claude Code
    

Agents Not Activating

Problem: Agents don't respond or aren't found

Solutions:

  1. Restart your AI tool
  2. Check file structure (must be flat, not nested):
    # βœ… Correct
    .factory/droids/implementer.md
    
    # ❌ Wrong
    .factory/droids/implementation/implementer.md
    
  3. Verify with:
    > /droids      # Factory AI
    > /agents      # Claude Code
    

Standards Not Being Followed

Problem: AI ignores your standards

Solutions:

  1. Reference standards explicitly:
    > Use the implementer agent and follow droidz/standards/backend/api-design.md
    
  2. Check standards exist:
    ls droidz/standards/
    
  3. Make standards more specific (add examples)

Lost Customizations After Update

Problem: Your standards got overwritten

Solutions:

  1. Check backup folder:
    ls /tmp/*droidz*backup*/
    
  2. Restore from backup:
    cp /tmp/droidz-backup-*/standards/* droidz/standards/
    
  3. Prevent in future: Commit droidz/ to git

Spec Not Loading

Problem: Agents can't find your spec

Solutions:

  1. Use correct path:
    > Read droidz/specs/2024-11-24-feature-name/spec.md
    
  2. Check file exists:
    ls droidz/specs/*/spec.md
    
  3. Verify spec is committed to git

Platform Support

Platform Install Location Content
Factory AI .factory/ droids/, commands/
Claude Code .claude/ agents/, commands/
Cursor .cursor/ workflows/
Cline .cline/ prompts/
Codex CLI .codex/ playbooks/
VS Code .vscode/droidz/ snippets/
All Platforms droidz/ standards/, product/, specs/

What's Included

8 Specialized Agents

  • product-planner
  • spec-shaper
  • spec-writer
  • spec-verifier
  • spec-initializer
  • tasks-list-creator
  • implementer
  • implementation-verifier

20+ Commands

  • /standards-shaper
  • /plan-product
  • /shape-spec
  • /write-spec
  • /create-tasks
  • /orchestrate-tasks
  • /implement-tasks
  • /improve-skills
  • ...and more

50+ Production Skills

  • Core Development: TDD, debugging, security, APIs
  • Modern Frameworks: Next.js 14, Convex, NeonDB, Tailwind
  • Tools: Playwright, MCP builder, document processing
  • Productivity: File organization, continuous improvement

Complete Standards Library

  • Global conventions
  • Backend patterns (API, database)
  • Frontend patterns (components, styling)
  • Testing strategies

Support & Community

Getting Help

  1. Documentation: Read droidz/standards/RECOMMENDED_WORKFLOW.md after installation
  2. Discord: Join Ray Fernando's community (link at top)
  3. Issues: GitHub Issues

Contributing

Droidz is open source! Contributions welcome:

  • Improve documentation
  • Add new skills
  • Create example workflows
  • Report bugs

License

MIT License - see LICENSE file for details


Credits

Created by the Droidz community with special thanks to:

  • Ray Fernando
  • All our supporters and contributors

Built on principles of spec-driven development adapted for modern AI coding agents.


Ready to transform your AI development workflow?

bash <(curl -fsSL https://raw.githubusercontent.com/korallis/Droidz/main/install.sh)

Questions? Join the Discord! πŸ’¬