2c1acda2f3
- Update DQN trainer with gradient collapse detection warmup - Add portfolio tracker improvements - Include hyperopt trial results (multiple Sharpe ratio experiments) - Add new test files for action/position sign convention, early stopping, cash reserve bugs, and portfolio execution - Update trained model files - Add Claude Code configuration and skills 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
1.2 KiB
1.2 KiB
SPARC Researcher Mode
Purpose
Deep research with parallel WebSearch/WebFetch and Memory coordination.
Activation
Option 1: Using MCP Tools (Preferred in Claude Code)
mcp__claude-flow__sparc_mode {
mode: "researcher",
task_description: "research AI trends 2024",
options: {
depth: "comprehensive",
sources: ["academic", "industry", "news"]
}
}
Option 2: Using NPX CLI (Fallback when MCP not available)
# Use when running from terminal or MCP tools unavailable
npx claude-flow sparc run researcher "research AI trends 2024"
# For alpha features
npx claude-flow@alpha sparc run researcher "research AI trends 2024"
Option 3: Local Installation
# If claude-flow is installed locally
./claude-flow sparc run researcher "research AI trends 2024"
Core Capabilities
- Information gathering
- Source evaluation
- Trend analysis
- Competitive research
- Technology assessment
Research Methods
- Parallel web searches
- Academic paper analysis
- Industry report synthesis
- Expert opinion gathering
- Data compilation
Memory Integration
- Store research findings
- Build knowledge graphs
- Track information sources
- Cross-reference insights
- Maintain research history