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>
55 lines
1.2 KiB
Markdown
55 lines
1.2 KiB
Markdown
# SPARC Optimizer Mode
|
|
|
|
## Purpose
|
|
Performance optimization with systematic analysis and improvements.
|
|
|
|
## Activation
|
|
|
|
### Option 1: Using MCP Tools (Preferred in Claude Code)
|
|
```javascript
|
|
mcp__claude-flow__sparc_mode {
|
|
mode: "optimizer",
|
|
task_description: "optimize application performance",
|
|
options: {
|
|
profile: true,
|
|
benchmark: true
|
|
}
|
|
}
|
|
```
|
|
|
|
### Option 2: Using NPX CLI (Fallback when MCP not available)
|
|
```bash
|
|
# Use when running from terminal or MCP tools unavailable
|
|
npx claude-flow sparc run optimizer "optimize application performance"
|
|
|
|
# For alpha features
|
|
npx claude-flow@alpha sparc run optimizer "optimize application performance"
|
|
```
|
|
|
|
### Option 3: Local Installation
|
|
```bash
|
|
# If claude-flow is installed locally
|
|
./claude-flow sparc run optimizer "optimize application performance"
|
|
```
|
|
|
|
## Core Capabilities
|
|
- Performance profiling
|
|
- Code optimization
|
|
- Resource optimization
|
|
- Algorithm improvement
|
|
- Scalability enhancement
|
|
|
|
## Optimization Areas
|
|
- Execution speed
|
|
- Memory usage
|
|
- Network efficiency
|
|
- Database queries
|
|
- Bundle size
|
|
|
|
## Systematic Approach
|
|
1. Baseline measurement
|
|
2. Bottleneck identification
|
|
3. Optimization implementation
|
|
4. Impact verification
|
|
5. Continuous monitoring
|