Initial commit
This commit is contained in:
Zhongwei Li
267
commands/ai.md
Normal file
267
commands/ai.md
Normal file
@@ -0,0 +1,267 @@
|
||||
## Usage
|
||||
`/ai <TASK_DESCRIPTION | list | info <role> | workflow | auto>`
|
||||
|
||||
## 🎯 Task Complexity Assessment
|
||||
|
||||
### Level 0: Micro Tasks - Direct execution
|
||||
- **Scenario**: Information queries, file reading, status checks
|
||||
- **Characteristics**: No code modification, pure information retrieval
|
||||
- **Boundary**: <5 minutes, no professional knowledge needed
|
||||
- **Triggers**: "view", "check", "display", "read"
|
||||
- **Action**: Main controller completes directly, no agent calls
|
||||
|
||||
### Level 1: Simple Tasks - Single agent direct
|
||||
- **Scenario**: Single file modification, basic configuration, simple functionality
|
||||
- **Characteristics**: <50 lines of code, single technology stack, clear requirements
|
||||
- **Boundary**: One professional domain, no cross-module impact
|
||||
- **Triggers**: "add", "modify", "configure" single components
|
||||
- **Action**: Direct call to 1 professional agent, bypassing director
|
||||
|
||||
### Level 2: Medium Tasks - Single agent complex
|
||||
- **Scenario**: Complete functional modules, multi-file coordination, requires testing
|
||||
- **Characteristics**: 50-200 lines of code, requires planning and validation
|
||||
- **Boundary**: Single technology stack but complex logic, may require refactoring
|
||||
- **Triggers**: "implement", "develop", "build" complete features
|
||||
- **Action**: 1 professional agent handles full process, main controller monitors
|
||||
|
||||
### Level 3: Composite Tasks - Multi-agent serial
|
||||
- **Scenario**: Cross-module functionality, frontend-backend coordination, 2-3 professional domains
|
||||
- **Characteristics**: 200-500 lines of code, requires multi-step coordination
|
||||
- **Boundary**: Clear dependency relationships, serial execution
|
||||
- **Triggers**: "integrate", "connect", "full-stack" functionality
|
||||
- **Action**: Main controller serially calls 2-3 agents
|
||||
|
||||
### Level 4: Parallel Tasks - Multi-agent concurrent
|
||||
- **Scenario**: Independent module parallel development, performance optimization, multi-platform
|
||||
- **Characteristics**: 3-5 independent workflows, can execute in parallel
|
||||
- **Boundary**: Low conflict risk, high independence
|
||||
- **Triggers**: "simultaneously", "parallel", "multi-platform" development
|
||||
- **Action**: Main controller calls 3-5 agents in parallel
|
||||
|
||||
### Level 5: Enterprise Tasks - Director coordination
|
||||
- **Scenario**: System refactoring, architecture upgrades, complex project analysis
|
||||
- **Characteristics**: 5+ professional domains, complex dependencies, multi-phase planning
|
||||
- **Boundary**: Requires specialized task decomposition and coordination management
|
||||
- **Triggers**: "refactor", "architecture", "system analysis", "enterprise-level"
|
||||
- **Action**: task-dispatch-director pure coordination, decompose into Level 1-3 tasks
|
||||
|
||||
## ⚡ Auto-Trigger Matrix
|
||||
|
||||
**Level 0 Trigger Conditions (no agent calls):**
|
||||
- Keywords: "view", "check", "display", "read", "list", "status"
|
||||
- Questions: "what is", "how to understand", "can you explain"
|
||||
- Operations: Pure information queries, no modification requirements
|
||||
|
||||
**Level 1 Trigger Conditions (single agent direct):**
|
||||
- Keywords: "add", "modify", "update", "configure", "adjust"
|
||||
- Scope: Single file or component + single technology stack
|
||||
- Examples: "add Vue component", "modify API endpoint", "configure database connection"
|
||||
|
||||
**Level 2 Trigger Conditions (single agent complex):**
|
||||
- Keywords: "implement", "develop", "build", "create" functional modules
|
||||
- Scope: Multi-file but single technology stack + requires testing
|
||||
- Examples: "implement user login", "develop payment module", "build search functionality"
|
||||
|
||||
**Level 3 Trigger Conditions (multi-agent serial):**
|
||||
- Keywords: "integrate", "connect", "full-stack", "end-to-end"
|
||||
- Scope: 2-3 technology stacks collaboration + clear dependencies
|
||||
- Examples: "frontend-backend integration", "API integration", "full-stack user system"
|
||||
|
||||
**Level 4 Trigger Conditions (multi-agent parallel):**
|
||||
- Keywords: "simultaneously", "parallel", "multi-platform", "optimize"
|
||||
- Scope: 3-5 independent modules + low conflict
|
||||
- Examples: "multi-platform synchronized development", "comprehensive performance optimization"
|
||||
|
||||
**Level 5 Trigger Conditions (Director coordination):**
|
||||
- Keywords: "refactor", "architecture", "system analysis", "enterprise-level", "complete solution"
|
||||
- Scope: 5+ professional domains + complex planning
|
||||
- Examples: "system architecture refactoring", "enterprise microservice design", "complex project analysis"
|
||||
|
||||
**Mandatory Director Bypass Conditions (Level 0-2):**
|
||||
- Single file operations
|
||||
- Clearly specified single technology stack
|
||||
- User explicitly says "no team collaboration needed"
|
||||
- Simple information queries and basic modifications
|
||||
|
||||
## 🚫 Direct Handling
|
||||
Handle without agents:
|
||||
- File reading, searching, basic analysis
|
||||
- Simple code modifications or config updates
|
||||
- Information queries and technical explanations
|
||||
|
||||
## 🛡️ Anti-Over-Engineering Principles
|
||||
- **One goal, one agent**: Only call one agent unless true collaboration needed
|
||||
- **Minimum viable solution**: Choose simplest working method
|
||||
- **User-oriented**: Based on explicit user needs, not assumptions
|
||||
|
||||
## 🎯 Project-Specific Agents Support
|
||||
|
||||
### Agent Discovery System
|
||||
The AI system intelligently detects and integrates both:
|
||||
- **Global Agents**: Standard agents from `/agents/` directory (always available)
|
||||
- **Project Agents**: Custom agents from `.claude/agents/` directory (created by `/initx`)
|
||||
|
||||
### Project Agent Features
|
||||
- **Auto-Detection**: Automatically discovers agents in `.claude/agents/` when present
|
||||
- **Priority System**: Project-specific agents take precedence over global agents
|
||||
- **Smart Routing**: Intelligently routes to project agents when they match the task better
|
||||
- **Seamless Integration**: Works with the same `/ai` command interface
|
||||
|
||||
### Using Project Agents
|
||||
```bash
|
||||
# After running /initx to create project-specific agents:
|
||||
/ai "optimize checkout flow" # Uses vue-ecommerce-developer if created
|
||||
/ai "implement payment integration" # Uses payment-integration-specialist
|
||||
/ai list # Shows both global and project agents
|
||||
```
|
||||
|
||||
## 👥 Team Members (when using `/ai list`)
|
||||
|
||||
**Note**: This list shows global agents. If you have run `/initx`, project-specific agents from `.claude/agents/` will also be available and displayed with a 🏢 icon.
|
||||
|
||||
### 🏛️ Leadership & Strategy
|
||||
- 🎯 **task-dispatch-director** - Task coordination hub (⚠️ Never calls itself)
|
||||
- 🏗️ **cto** - Technical strategy and architecture decisions
|
||||
- 📊 **product-manager** - Product requirements and PRD creation
|
||||
|
||||
### 💻 Development Team
|
||||
- 📋 **technical-solution-architect** - Technical solution design based on PRDs
|
||||
- 🎨 **frontend-developer** - React expert, UI components, performance optimization
|
||||
- 💾 **backend-developer** - Multi-stack API development (FastAPI/Spring Boot/Node.js)
|
||||
- 🔧 **infrastructure-developer** - Development tools and automation scripts
|
||||
- 🚀 **devops-engineer** - Docker containerization and deployment
|
||||
|
||||
### 🌟 Frontend Technology Stack Experts
|
||||
- 🌟 **vue-developer** - Vue 2/3, Nuxt.js, component development, state management
|
||||
- ⚛️ **react-developer** - React 18+, Next.js, modern Hooks patterns
|
||||
|
||||
### 🏗️ Backend Architecture Experts
|
||||
- 🚀 **go-architect** - Go microservice architecture, distributed systems, cloud-native
|
||||
- 🦀 **rust-architect** - Rust system programming, memory safety, high-performance computing
|
||||
- ☕ **java-developer** - Java enterprise development, Spring Boot microservices
|
||||
- 🌱 **spring-architect** - Spring full-stack, microservice architecture, enterprise design
|
||||
|
||||
### 🐍 Python Web Experts
|
||||
- 🌶️ **flask-expert** - Flask framework, RESTful API, traditional web applications
|
||||
- ⚡ **fastapi-expert** - FastAPI framework, async programming, high-performance APIs
|
||||
|
||||
### 📱 Mobile Development
|
||||
- 📱 **android-developer** - Android native development, Kotlin/Java, Material Design
|
||||
- 🎨 **mobile-ui-designer** - Mobile UI/UX design, cross-platform interfaces
|
||||
|
||||
### 🔐 Security & Reverse Engineering
|
||||
- 🎣 **android-hooking-expert** - Frida/Hook technology, dynamic analysis
|
||||
- 📱 **xposed-developer** - Xposed module development, system-level customization
|
||||
- 🔍 **reverse-engineer** - Code deobfuscation, static analysis
|
||||
- 🦠 **malware-analyst** - Malware analysis, threat detection
|
||||
|
||||
### 🌙 Scripting & Automation
|
||||
- 🌙 **lua-developer** - Lua script development (game/web/automation scripts)
|
||||
|
||||
### 🎨 Design Experts
|
||||
- 🎨 **google-ui-designer** - Material Design, user experience design
|
||||
|
||||
### 🔧 Quality & Operations
|
||||
- 👀 **code-review-expert** - Code quality review, security checks
|
||||
- 🚀 **devops-engineer** - Docker deployment, CI/CD, operations monitoring
|
||||
- 🧪 **test-expert** - Testing strategy, automated testing, performance testing
|
||||
- 🐛 **qa-engineer** - Problem diagnosis, root cause analysis
|
||||
- 🔬 **technical-researcher** - Technical research, feasibility analysis
|
||||
|
||||
## 🎮 Command Modes
|
||||
|
||||
### 🎯 Task Execution (Default)
|
||||
```
|
||||
/ai "Add login feature"
|
||||
/ai "Optimize API performance"
|
||||
/ai "Code review recent commits"
|
||||
```
|
||||
|
||||
### 📚 Information
|
||||
- `/ai list` - Show all team members (including project-specific agents if available)
|
||||
- `/ai info <role>` - Get role details (works with both global and project agents)
|
||||
- `/ai auto` - Enable maximum automation
|
||||
- `/initx` - Initialize project and create custom AI team (see `/initx` command)
|
||||
|
||||
## 📊 Smart Parallel Task Execution Output
|
||||
|
||||
### **Smart Parallel Task Execution Output:**
|
||||
```
|
||||
🧠 Intelligent Analysis (ultrathink mode activated)
|
||||
- Intent: [Detected user goal with confidence %]
|
||||
- Complexity: [Simple(1-2)/Medium(3-4)/Complex(5)] (Auto-assessed)
|
||||
- Agent Selection: [Global agents / Project-specific agents if available]
|
||||
- Parallel Strategy: [Why this parallel approach was chosen]
|
||||
- Estimated Speedup: [Expected efficiency gain vs serial execution]
|
||||
|
||||
🚀 Parallel Execution Plan (Multi-Phase Concurrent)
|
||||
Phase 1 (Parallel): [3 agents] → [Concurrent analysis/planning]
|
||||
├── 🎯 [Agent A] → [Specific deliverable] (parallel group 1)
|
||||
├── 🎯 [Agent B] → [Specific deliverable] (parallel group 1)
|
||||
└── 🎯 [Agent C] → [Specific deliverable] (parallel group 1)
|
||||
|
||||
Phase 2 (Parallel): [2 agents] → [Build on Phase 1 results]
|
||||
├── 🔄 [Agent D] → [Integration task] (parallel group 2)
|
||||
└── 🔄 [Agent E] → [Implementation task] (parallel group 2)
|
||||
|
||||
⚡ Launching Parallel AI Team...
|
||||
├── 🚀 Phase 1: Launching 3 concurrent agents...
|
||||
│ ├── ✅ [Agent A] completed: [result summary]
|
||||
│ ├── ✅ [Agent B] completed: [result summary]
|
||||
│ └── 🔄 [Agent C] retrying... (attempt 2/3)
|
||||
├── 🔄 Integrating Phase 1 results...
|
||||
├── 🚀 Phase 2: Launching 2 concurrent agents with enhanced context...
|
||||
│ ├── ✅ [Agent D] completed: [result summary]
|
||||
│ └── ✅ [Agent E] completed: [result summary]
|
||||
|
||||
✅ Mission Complete (Parallel Execution)
|
||||
- 📦 **Deliverables**: [What was produced across all parallel phases]
|
||||
- ⚡ **Performance**: [Actual speedup achieved: 3.2x faster than serial]
|
||||
- 🛡️ **Reliability**: [Retry success rate: 2 retries, 100% final success]
|
||||
- 🧠 **Learning**: [Pattern for future similar parallel executions]
|
||||
```
|
||||
|
||||
### **Parallel Execution Status Indicators:**
|
||||
```bash
|
||||
🚀 Parallel Launch # Multiple agents starting simultaneously
|
||||
⚡ Partial Success # Some agents completed, others retrying
|
||||
🔄 Auto-Retry # Intelligent retry with exponential backoff
|
||||
✅ Phase Complete # All agents in phase finished successfully
|
||||
🔀 Context Merge # Integrating parallel results for next phase
|
||||
🛡️ Fallback Mode # Serial execution after parallel retry exhaustion
|
||||
```
|
||||
|
||||
### **Performance Metrics Display:**
|
||||
```
|
||||
📊 Parallel Performance Dashboard
|
||||
- Concurrent agents launched: 8 total across 3 phases
|
||||
- Parallel efficiency gain: 4.1x faster than serial execution
|
||||
- Auto-retry success rate: 94% (3 retries recovered, 1 fallback)
|
||||
- Resource utilization: 87% (optimal parallel agent distribution)
|
||||
- Total execution time: 12 minutes (vs 49 minutes serial estimate)
|
||||
```
|
||||
|
||||
## 🚀 System Benefits
|
||||
|
||||
### 🎯 **Precision Task Routing**
|
||||
- **Level 0-2**: Bypass director overhead → Direct specialist assignment
|
||||
- **Level 3-4**: Coordinated multi-agent execution → Optimal resource allocation
|
||||
- **Level 5**: Enterprise-level orchestration → Complex project management
|
||||
|
||||
### ⚡ **Performance Optimization**
|
||||
- **3x faster** for simple tasks (Level 0-1 direct execution)
|
||||
- **2x more reliable** for complex tasks (proper coordination)
|
||||
- **Zero agent overload** (strict role boundaries)
|
||||
|
||||
### 🛡️ **Anti-Deadlock Protection**
|
||||
- **task-dispatch-director** limited to pure coordination only
|
||||
- **Automatic fallback** when agents fail (3-retry rule)
|
||||
- **Forced bypass** for simple operations (Level 0-2)
|
||||
|
||||
### 🎯 **Development Efficiency**
|
||||
1. **Single Command** - No need to remember specific roles
|
||||
2. **Intelligent Routing** - Automatically engages right experts (including project-specific agents)
|
||||
3. **Full Workflow** - Handles complete development cycle
|
||||
4. **Quality Gates** - Ensures proper reviews and testing
|
||||
5. **Coordination** - Manages team collaboration
|
||||
6. **Project Awareness** - Prioritizes custom project agents when available
|
||||
290
commands/initx.md
Normal file
290
commands/initx.md
Normal file
@@ -0,0 +1,290 @@
|
||||
# InitX - Project Intelligence & Agent Recruitment System
|
||||
|
||||
## Usage
|
||||
`/initx [OPTIONS]`
|
||||
|
||||
## 🎯 Core Function
|
||||
|
||||
Analyze project codebase, detect technology stack, and **CREATE NEW PROJECT-SPECIFIC AGENTS** tailored to your unique requirements. Saves custom agents to `.claude/agents/` and updates project `CLAUDE.md`.
|
||||
|
||||
## 🚀 Command Modes
|
||||
|
||||
### 🎯 Basic Usage
|
||||
```bash
|
||||
/initx # Smart analysis & agent creation
|
||||
/initx --preview # Preview mode (no file creation)
|
||||
/initx --force # Force overwrite existing agents
|
||||
```
|
||||
|
||||
### 📊 Advanced Options
|
||||
- `--mode=minimal` - Create only essential agents
|
||||
- `--focus=security` - Focus on security-specific agents
|
||||
- `--exclude=ui` - Skip UI/design agents
|
||||
- `--template=mobile` - Use mobile project template
|
||||
- `--model=inherit` - Force all agents to use specified model (inherit/sonnet/opus/haiku)
|
||||
|
||||
## 🧠 Intelligence Detection Matrix
|
||||
|
||||
### Technology Stack Recognition
|
||||
```yaml
|
||||
Frontend: vue (*.vue, nuxt.config.js), react (*.jsx, next.config.js), angular
|
||||
Backend: fastapi (main.py), spring (pom.xml), go (go.mod), node (express/koa)
|
||||
Mobile: android (*.kt, AndroidManifest.xml), flutter (pubspec.yaml)
|
||||
Security: reversing (*.apk, frida scripts), hooking (xposed modules)
|
||||
```
|
||||
|
||||
### Project Complexity Assessment
|
||||
- **Simple**: 1-2 custom agents (single stack)
|
||||
- **Medium**: 3-5 custom agents (multi-stack)
|
||||
- **Complex**: 5-8 custom agents (microservices)
|
||||
- **Enterprise**: 8+ custom agents (distributed)
|
||||
|
||||
## 🤖 Agent Creation Algorithm
|
||||
|
||||
### Phase 1: Core Stack Agents
|
||||
**Creates NEW specialized agents based on detected stack:**
|
||||
- `vue-{project-name}-developer` - Project-specific Vue expert
|
||||
- `api-{domain}-specialist` - Custom API integration expert
|
||||
- `{database}-data-architect` - Database-specific data expert
|
||||
|
||||
### Phase 2: Domain-Specific Agents
|
||||
**Creates NEW agents for unique project domains:**
|
||||
- `{domain}-business-logic-expert` - Business rules specialist
|
||||
- `{integration}-connector-agent` - Third-party integration expert
|
||||
- `{platform}-deployment-specialist` - Platform-specific deployment
|
||||
|
||||
### Phase 3: Quality & Operations Agents
|
||||
**Creates NEW agents for project-specific QA:**
|
||||
- `{stack}-testing-specialist` - Stack-specific testing expert
|
||||
- `{environment}-ops-engineer` - Environment-specific operations
|
||||
|
||||
## 📁 Generated Structure
|
||||
|
||||
```
|
||||
project_root/
|
||||
├── .claude/
|
||||
│ └── agents/ # NEW custom agents
|
||||
│ ├── vue-ecommerce-developer.md
|
||||
│ ├── payment-integration-specialist.md
|
||||
│ ├── postgres-data-architect.md
|
||||
│ └── aws-deployment-specialist.md
|
||||
├── CLAUDE.md # Updated with new team
|
||||
└── .gitignore # Updated exclusions
|
||||
```
|
||||
|
||||
## 🏗️ Custom Agent Template
|
||||
|
||||
⚠️ **LANGUAGE REQUIREMENT**: All agent content MUST be generated in ENGLISH.
|
||||
|
||||
```markdown
|
||||
---
|
||||
name: {project-domain}-{specialization}-agent
|
||||
description: Project-specific {specialization} expert for {project_name}
|
||||
model: inherit # Options: inherit | sonnet | opus | haiku
|
||||
---
|
||||
|
||||
You are the **{Project Domain} {Specialization} Agent** for the {project_name} project.
|
||||
|
||||
## STRICT AGENT BOUNDARIES
|
||||
|
||||
**ALLOWED ACTIONS:**
|
||||
- {Domain-specific actions based on project analysis}
|
||||
- {Tech stack specific implementations}
|
||||
- {Integration and performance optimizations}
|
||||
|
||||
**FORBIDDEN ACTIONS:**
|
||||
- {Cross-domain work} (delegate to {appropriate_agent})
|
||||
- Infrastructure concerns (delegate to devops-engineer)
|
||||
- Security audits (delegate to code-review-expert)
|
||||
|
||||
**CORE MISSION:** {Single sentence describing the agent's purpose}
|
||||
|
||||
## RESPONSIBILITIES
|
||||
|
||||
### 1. {Primary Domain Area}
|
||||
- {Specific responsibilities based on project analysis}
|
||||
- {Pattern implementations from detected codebase}
|
||||
|
||||
### 2. {Quality & Testing}
|
||||
- {Testing requirements specific to domain}
|
||||
- {Performance criteria for project}
|
||||
|
||||
### 3. {Collaboration}
|
||||
- Input from: {upstream agents}
|
||||
- Output to: {downstream agents}
|
||||
- Coordinate with: {peer agents}
|
||||
|
||||
## TECHNOLOGY STACK
|
||||
**Primary**: {Detected technologies with versions}
|
||||
**Integrations**: {Third-party services}
|
||||
**Constraints**: Work exclusively within {project_domain} of {project_name}
|
||||
```
|
||||
|
||||
## 🧠 Intelligent Model Selection System
|
||||
|
||||
### Model Selection Matrix
|
||||
```yaml
|
||||
Complex Reasoning (opus): Architecture design, security analysis, microservices
|
||||
Balanced Performance (sonnet): Most development agents, API/database, testing
|
||||
Simple Fast (haiku): Config generation, simple scripts, documentation
|
||||
Inherit from Parent (inherit): Maintain consistency, avoid switching overhead
|
||||
```
|
||||
|
||||
### Force Model Option (--model parameter)
|
||||
```bash
|
||||
/initx --model=inherit # All agents inherit from parent (best for cost control)
|
||||
/initx --model=sonnet # All agents use Sonnet (balanced performance)
|
||||
/initx --model=opus # All agents use Opus (maximum reasoning)
|
||||
/initx --model=haiku # All agents use Haiku (fastest response)
|
||||
```
|
||||
|
||||
⚠️ Using `--model` overrides intelligent model selection for consistency/cost control.
|
||||
|
||||
### User Confirmation Flow
|
||||
|
||||
#### Standard Mode (Intelligent Model Selection)
|
||||
```bash
|
||||
🤖 Agent Creation - {agent_name}
|
||||
📊 Recommended: {suggested_model} ({reason})
|
||||
|
||||
Select model: [1] ✅ Recommended [2] Opus [3] Sonnet [4] Haiku [5] Inherit
|
||||
Confirm? [y/N]
|
||||
```
|
||||
|
||||
#### Force Model Mode (--model parameter)
|
||||
```bash
|
||||
🤖 Agent Creation - {agent_name}
|
||||
📊 Model: {forced_model} (forced by --model)
|
||||
Confirm? [y/N]
|
||||
```
|
||||
|
||||
### ⚠️ IMPORTANT: Language Requirements
|
||||
**All generated agents MUST be created in English**, regardless of the user's input language:
|
||||
- Agent names: Always in English (e.g., `vue-ecommerce-developer`, not `vue-电商-开发者`)
|
||||
- Agent descriptions: Always in English
|
||||
- Agent content: Always in English
|
||||
- Documentation comments: Always in English
|
||||
|
||||
This ensures consistency and compatibility across all projects and teams.
|
||||
|
||||
## ⚡ Execution Flow
|
||||
|
||||
### Phase 1: Project Intelligence (15s)
|
||||
```bash
|
||||
🔍 Analyzing project structure...
|
||||
├── 📊 Detecting tech stack and versions
|
||||
├── 🏗️ Identifying architecture patterns
|
||||
├── 📈 Assessing complexity and scale
|
||||
└── 🎯 Discovering unique requirements
|
||||
|
||||
✅ Analysis Complete
|
||||
- Type: E-commerce Web App
|
||||
- Stack: Vue 3 + FastAPI + PostgreSQL
|
||||
- Complexity: Medium (4/5)
|
||||
- Unique: Payment integration, inventory management
|
||||
```
|
||||
|
||||
### Phase 2: Agent Creation & Confirmation (20s)
|
||||
|
||||
#### Standard Mode:
|
||||
```bash
|
||||
🤖 Intelligent Model Matching...
|
||||
|
||||
vue-ecommerce-developer (recommended: sonnet)
|
||||
├─ Reason: Vue 3 patterns, balanced performance
|
||||
├─ Select: [1] ✅ sonnet [2] opus [3] haiku [4] inherit
|
||||
└─ ✅ Created
|
||||
|
||||
fastapi-payment-specialist (recommended: opus)
|
||||
├─ Reason: Payment integration, complex logic
|
||||
├─ Select: [1] ✅ opus [2] sonnet [3] haiku [4] inherit
|
||||
└─ ✅ Created
|
||||
|
||||
[... more agents ...]
|
||||
|
||||
📊 Created 8 agents: 4 sonnet, 2 opus, 1 haiku, 1 inherit
|
||||
```
|
||||
|
||||
#### Force Model Mode (/initx --model=inherit):
|
||||
```bash
|
||||
🤖 Force Model: inherit (all agents use parent model)
|
||||
|
||||
vue-ecommerce-developer
|
||||
├─ ⚠️ Using inherit (recommended: sonnet)
|
||||
└─ ✅ Created
|
||||
|
||||
fastapi-payment-specialist
|
||||
├─ ⚠️ Using inherit (recommended: opus)
|
||||
└─ ✅ Created
|
||||
|
||||
[... more agents ...]
|
||||
|
||||
📊 Created 8 agents: 8 inherit (forced)
|
||||
```
|
||||
|
||||
### Phase 3: Team Configuration (10s)
|
||||
```bash
|
||||
📝 Configuring AI team collaboration...
|
||||
├── 📁 Saving agents to .claude/agents/ directory
|
||||
├── 🔧 Setting up collaboration matrix and dependencies
|
||||
├── 📋 Updating CLAUDE.md with team information
|
||||
└── 🎯 Ready for project-specific task execution
|
||||
|
||||
✅ Custom AI team ready!
|
||||
🚀 Use /ai "optimize checkout flow" to engage specialist team
|
||||
```
|
||||
|
||||
## 🎛️ Smart Templates
|
||||
|
||||
### E-commerce Project
|
||||
```yaml
|
||||
detected_patterns: [shopping_cart, payment_flow, inventory]
|
||||
created_agents:
|
||||
- payment-integration-specialist
|
||||
- inventory-management-expert
|
||||
- customer-analytics-agent
|
||||
- ecommerce-testing-specialist
|
||||
```
|
||||
|
||||
### Security Research Project
|
||||
```yaml
|
||||
detected_patterns: [apk_analysis, hooking, reverse_engineering]
|
||||
created_agents:
|
||||
- android-malware-analyst
|
||||
- frida-hooking-specialist
|
||||
- apk-reverse-engineer
|
||||
- vulnerability-scanner-expert
|
||||
```
|
||||
|
||||
### Microservices Project
|
||||
```yaml
|
||||
detected_patterns: [service_mesh, api_gateway, distributed_data]
|
||||
created_agents:
|
||||
- service-mesh-architect
|
||||
- api-gateway-specialist
|
||||
- distributed-data-expert
|
||||
- microservices-testing-specialist
|
||||
```
|
||||
|
||||
## 🚀 System Benefits
|
||||
|
||||
### 🎯 **Project-Specific Intelligence**
|
||||
- **Custom Agents**: Tailored to your exact tech stack and domain
|
||||
- **Smart Collaboration**: Agents know your project's integration points
|
||||
- **Model Flexibility**: Choose optimal model strategy with `--model` parameter
|
||||
|
||||
### ⚡ **Rapid Development**
|
||||
- **10x Faster**: Custom experts vs generic agents
|
||||
- **Zero Learning Curve**: Agents pre-configured for your project
|
||||
- **Cost Control**: Force consistent model usage with `--model=inherit`
|
||||
|
||||
### 💰 **Cost Management**
|
||||
- **Default**: Intelligent per-agent model selection
|
||||
- **--model=inherit**: Maximum cost control
|
||||
- **--model=sonnet**: Balanced cost/performance
|
||||
- **--model=haiku**: Minimum cost, fast response
|
||||
|
||||
---
|
||||
|
||||
**InitX creates your perfect AI development team - not just assigns existing ones!**
|
||||
🚀 One command, custom specialists, exponential productivity!
|
||||
Reference in New Issue
Block a user