## 🧠 INTELLIGENCE GATHERING FOUNDATION 10X
*Centralized Intelligence Gathering for All Analysis Commands*
**Claude, execute UNIFIED INTELLIGENCE GATHERING with CONFIGURABLE FOCUS AREAS for use by all 10X analysis commands.**
### 🎯 **EXECUTION MODES** (Modular Intelligence)
**Market Intelligence**:
```bash
/intelligence:gather_insights_10x --market "[domain]"
```
- Competitive analysis and benchmarking
- Market trends and user research
- Industry best practices
**Technical Intelligence**:
```bash
/intelligence:gather_insights_10x --technical "[tech_stack]"
```
- Technology stack analysis
- Framework documentation
- Performance benchmarks
**Pattern Intelligence**:
```bash
/intelligence:gather_insights_10x --patterns "[topic]"
```
- Organizational patterns
- Successful approaches
- Historical insights
**Full Intelligence** (Default):
```bash
/intelligence:gather_insights_10x --full "[project_context]"
```
- Comprehensive intelligence gathering
- All intelligence types combined
- Complete context building
### 🔥 **INTELLIGENCE GATHERING MODULES**
### **Module 1: Market & Competitive Intelligence**
```yaml
Market Research:
- cached_websearch_10x: "[domain] market size trends 2024"
- cached_websearch_10x: "top 10 [project_type] companies technology stack"
- gpt-researcher: Comprehensive market research and competitive landscape
- fetch: Analyze leading competitor architectures and features
- github: Research highest-starred similar projects
- cached_websearch_10x: "[target_market] pain points user research"
- meilisearch: Search organizational competitive intelligence
```
### **Module 2: Technical Intelligence**
```yaml
Technology Research:
- ml-code-intelligence MCP: Analyze existing codebase patterns
- 10x-command-analytics MCP: Review command usage patterns
- cached_websearch_10x: "[tech_stack] performance benchmarks scalability"
- github: Find proven architectures for similar scale/requirements
- gpt-researcher: Deep technology assessment and validation
- fetch: Download latest framework documentation
- cached_websearch_10x: "[technologies] security vulnerabilities updates"
- memory: Review relevant organizational patterns
- qdrant: Vector search for similar technology patterns
```
### **Module 3: Pattern & Historical Intelligence**
```yaml
Pattern Analysis:
- 10x-knowledge-graph MCP: Extract concepts and relationships
- context-aware-memory MCP: Store intelligence context with predictive loading
- 10x-workflow-optimizer MCP: Optimize intelligence gathering workflow
- smart_memory_unified: Retrieve organizational patterns
- chroma-rag: Semantic search across all organizational knowledge
- sqlite: Query historical success metrics
```
### **Module 4: Resource Intelligence**
```yaml
Resource Research:
- github: Find reusable components and libraries
- cached_websearch_10x: "[project_type] development timeline estimation"
- fetch: Development methodology guides and templates
- cached_websearch_10x: "deployment [project_type] cloud infrastructure costs"
```
### 🚀 **INTELLIGENT OUTPUT GENERATION**
**2.1 Structured Intelligence Report**
```markdown
# Intelligence Report - [TIMESTAMP]
## 🎯 Executive Summary
[Key findings and actionable insights]
## 📊 Market Intelligence
- Market Size: [data]
- Key Players: [list]
- Trends: [analysis]
- Opportunities: [identified gaps]
## 🔧 Technical Intelligence
- Recommended Stack: [technologies]
- Performance Benchmarks: [metrics]
- Security Considerations: [findings]
- Best Practices: [patterns]
## 🧩 Pattern Intelligence
- Successful Patterns: [organizational knowledge]
- Anti-patterns: [what to avoid]
- Historical Insights: [lessons learned]
## 📈 Recommendations
1. [Priority recommendations based on intelligence]
```
**2.2 Intelligence Storage**
```yaml
Storage Strategy:
Market Data:
- Location: Knowledge/intelligence/market_analysis_[timestamp].md
- Format: Structured markdown with metrics
Technical Data:
- Location: Knowledge/intelligence/technical_research_[timestamp].md
- Format: Technical specifications and benchmarks
Pattern Data:
- Location: Knowledge/patterns/successful_approaches_[timestamp].md
- Format: Actionable patterns and anti-patterns
Vector Storage:
- chroma-rag: All intelligence embedded for semantic search
- smart_memory_unified: Cross-referenced and classified
```
### 📊 **INTEGRATION WITH OTHER COMMANDS**
**Commands Using This Foundation:**
```yaml
/deep_analysis_10x:
- Calls: gather_insights_10x --full
- Adds: Strategic planning layer
/project_accelerator_10x:
- Calls: gather_insights_10x --market --technical
- Adds: Acceleration strategies
/create_feature_spec_10x:
- Calls: gather_insights_10x --market --patterns
- Adds: Feature specifications
/ml_powered_development_10x:
- Calls: gather_insights_10x --technical --patterns
- Adds: ML-specific optimizations
```
### 🔧 **CONFIGURATION OPTIONS**
```yaml
# Intelligence gathering configuration
intelligence_config:
depth:
quick: 5-10 minutes
standard: 15-20 minutes
comprehensive: 30+ minutes
sources:
priority_1: [cached_websearch, memory, knowledge_graph]
priority_2: [github, gpt-researcher, ml_mcps]
priority_3: [fetch, external_docs]
caching:
enable: true
ttl: 30 days
similarity_threshold: 0.8
output:
format: markdown
include_metrics: true
generate_visualizations: false
```
### 📈 **PERFORMANCE OPTIMIZATION**
**Parallel Execution**:
- Run market and technical research simultaneously
- Batch similar MCP calls together
- Use cached results when available
**Smart Prioritization**:
- Check cache first before external searches
- Use ML predictions to focus research
- Skip low-value intelligence based on context
**Resource Management**:
- Limit concurrent MCP calls to prevent overload
- Use progressive enhancement (quick → comprehensive)
- Monitor and optimize based on usage patterns
### 🎯 **SUCCESS METRICS**
- **Cache Hit Rate**: > 60% for common research
- **Intelligence Quality**: 90% actionable insights
- **Execution Time**: < 10 minutes for standard mode
- **Reusability**: 80% of gathered intelligence reused
- **Accuracy**: 95% relevant to project context
**EXECUTE IMMEDIATELY**: Begin unified intelligence gathering with configurable focus areas for optimal reuse across all analysis commands!
