diff --git a/.claude/commands/agents/README.md b/.claude/commands/agents/README.md new file mode 100644 index 0000000000..dca2aa7c70 --- /dev/null +++ b/.claude/commands/agents/README.md @@ -0,0 +1,10 @@ +# Agents Commands + +Commands for agents operations in Claude Flow. + +## Available Commands + +- [agent-types](./agent-types.md) +- [agent-capabilities](./agent-capabilities.md) +- [agent-coordination](./agent-coordination.md) +- [agent-spawning](./agent-spawning.md) diff --git a/.claude/commands/agents/agent-capabilities.md b/.claude/commands/agents/agent-capabilities.md new file mode 100644 index 0000000000..1daf5eeffd --- /dev/null +++ b/.claude/commands/agents/agent-capabilities.md @@ -0,0 +1,21 @@ +# agent-capabilities + +Matrix of agent capabilities and their specializations. + +## Capability Matrix + +| Agent Type | Primary Skills | Best For | +|------------|---------------|----------| +| coder | Implementation, debugging | Feature development | +| researcher | Analysis, synthesis | Requirements gathering | +| tester | Testing, validation | Quality assurance | +| architect | Design, planning | System architecture | + +## Querying Capabilities +```bash +# List all capabilities +npx claude-flow agents capabilities + +# For specific agent +npx claude-flow agents capabilities --type coder +``` diff --git a/.claude/commands/agents/agent-coordination.md b/.claude/commands/agents/agent-coordination.md new file mode 100644 index 0000000000..704a6dc1e5 --- /dev/null +++ b/.claude/commands/agents/agent-coordination.md @@ -0,0 +1,28 @@ +# agent-coordination + +Coordination patterns for multi-agent collaboration. + +## Coordination Patterns + +### Hierarchical +Queen-led with worker specialization +```bash +npx claude-flow swarm init --topology hierarchical +``` + +### Mesh +Peer-to-peer collaboration +```bash +npx claude-flow swarm init --topology mesh +``` + +### Adaptive +Dynamic topology based on workload +```bash +npx claude-flow swarm init --topology adaptive +``` + +## Best Practices +- Use hierarchical for complex projects +- Use mesh for research tasks +- Use adaptive for unknown workloads diff --git a/.claude/commands/agents/agent-spawning.md b/.claude/commands/agents/agent-spawning.md new file mode 100644 index 0000000000..38c8581d4c --- /dev/null +++ b/.claude/commands/agents/agent-spawning.md @@ -0,0 +1,28 @@ +# agent-spawning + +Guide to spawning agents with Claude Code's Task tool. + +## Using Claude Code's Task Tool + +**CRITICAL**: Always use Claude Code's Task tool for actual agent execution: + +```javascript +// Spawn ALL agents in ONE message +Task("Researcher", "Analyze requirements...", "researcher") +Task("Coder", "Implement features...", "coder") +Task("Tester", "Create tests...", "tester") +``` + +## MCP Coordination Setup (Optional) + +MCP tools are ONLY for coordination: +```javascript +mcp__claude-flow__swarm_init { topology: "mesh" } +mcp__claude-flow__agent_spawn { type: "researcher" } +``` + +## Best Practices +1. Always spawn agents concurrently +2. Use Task tool for execution +3. MCP only for coordination +4. Batch all operations diff --git a/.claude/commands/agents/agent-types.md b/.claude/commands/agents/agent-types.md new file mode 100644 index 0000000000..645fab47ed --- /dev/null +++ b/.claude/commands/agents/agent-types.md @@ -0,0 +1,26 @@ +# agent-types + +Complete guide to all 54 available agent types in Claude Flow. + +## Core Development Agents +- `coder` - Implementation specialist +- `reviewer` - Code quality assurance +- `tester` - Test creation and validation +- `planner` - Strategic planning +- `researcher` - Information gathering + +## Swarm Coordination Agents +- `hierarchical-coordinator` - Queen-led coordination +- `mesh-coordinator` - Peer-to-peer networks +- `adaptive-coordinator` - Dynamic topology + +## Specialized Agents +- `backend-dev` - API development +- `mobile-dev` - React Native development +- `ml-developer` - Machine learning +- `system-architect` - High-level design + +For full list and details: +```bash +npx claude-flow agents list +``` diff --git a/.claude/commands/analysis/README.md b/.claude/commands/analysis/README.md new file mode 100644 index 0000000000..1eb295c1a8 --- /dev/null +++ b/.claude/commands/analysis/README.md @@ -0,0 +1,9 @@ +# Analysis Commands + +Commands for analysis operations in Claude Flow. + +## Available Commands + +- [bottleneck-detect](./bottleneck-detect.md) +- [token-usage](./token-usage.md) +- [performance-report](./performance-report.md) diff --git a/.claude/commands/analysis/bottleneck-detect.md b/.claude/commands/analysis/bottleneck-detect.md new file mode 100644 index 0000000000..85c8595eb6 --- /dev/null +++ b/.claude/commands/analysis/bottleneck-detect.md @@ -0,0 +1,162 @@ +# bottleneck detect + +Analyze performance bottlenecks in swarm operations and suggest optimizations. + +## Usage + +```bash +npx claude-flow bottleneck detect [options] +``` + +## Options + +- `--swarm-id, -s ` - Analyze specific swarm (default: current) +- `--time-range, -t ` - Analysis period: 1h, 24h, 7d, all (default: 1h) +- `--threshold ` - Bottleneck threshold percentage (default: 20) +- `--export, -e ` - Export analysis to file +- `--fix` - Apply automatic optimizations + +## Examples + +### Basic bottleneck detection + +```bash +npx claude-flow bottleneck detect +``` + +### Analyze specific swarm + +```bash +npx claude-flow bottleneck detect --swarm-id swarm-123 +``` + +### Last 24 hours with export + +```bash +npx claude-flow bottleneck detect -t 24h -e bottlenecks.json +``` + +### Auto-fix detected issues + +```bash +npx claude-flow bottleneck detect --fix --threshold 15 +``` + +## Metrics Analyzed + +### Communication Bottlenecks + +- Message queue delays +- Agent response times +- Coordination overhead +- Memory access patterns + +### Processing Bottlenecks + +- Task completion times +- Agent utilization rates +- Parallel execution efficiency +- Resource contention + +### Memory Bottlenecks + +- Cache hit rates +- Memory access patterns +- Storage I/O performance +- Neural pattern loading + +### Network Bottlenecks + +- API call latency +- MCP communication delays +- External service timeouts +- Concurrent request limits + +## Output Format + +``` +🔍 Bottleneck Analysis Report +━━━━━━━━━━━━━━━━━━━━━━━━━━━ + +📊 Summary +├── Time Range: Last 1 hour +├── Agents Analyzed: 6 +├── Tasks Processed: 42 +└── Critical Issues: 2 + +🚨 Critical Bottlenecks +1. Agent Communication (35% impact) + └── coordinator → coder-1 messages delayed by 2.3s avg + +2. Memory Access (28% impact) + └── Neural pattern loading taking 1.8s per access + +⚠️ Warning Bottlenecks +1. Task Queue (18% impact) + └── 5 tasks waiting > 10s for assignment + +💡 Recommendations +1. Switch to hierarchical topology (est. 40% improvement) +2. Enable memory caching (est. 25% improvement) +3. Increase agent concurrency to 8 (est. 20% improvement) + +✅ Quick Fixes Available +Run with --fix to apply: +- Enable smart caching +- Optimize message routing +- Adjust agent priorities +``` + +## Automatic Fixes + +When using `--fix`, the following optimizations may be applied: + +1. **Topology Optimization** + + - Switch to more efficient topology + - Adjust communication patterns + - Reduce coordination overhead + +2. **Caching Enhancement** + + - Enable memory caching + - Optimize cache strategies + - Preload common patterns + +3. **Concurrency Tuning** + + - Adjust agent counts + - Optimize parallel execution + - Balance workload distribution + +4. **Priority Adjustment** + - Reorder task queues + - Prioritize critical paths + - Reduce wait times + +## Performance Impact + +Typical improvements after bottleneck resolution: + +- **Communication**: 30-50% faster message delivery +- **Processing**: 20-40% reduced task completion time +- **Memory**: 40-60% fewer cache misses +- **Overall**: 25-45% performance improvement + +## Integration with Claude Code + +```javascript +// Check for bottlenecks in Claude Code +mcp__claude-flow__bottleneck_detect { + timeRange: "1h", + threshold: 20, + autoFix: false +} +``` + +## See Also + +- `performance report` - Detailed performance analysis +- `token usage` - Token optimization analysis +- `swarm monitor` - Real-time monitoring +- `cache manage` - Cache optimization diff --git a/.claude/commands/analysis/performance-report.md b/.claude/commands/analysis/performance-report.md new file mode 100644 index 0000000000..04b8d9e9ac --- /dev/null +++ b/.claude/commands/analysis/performance-report.md @@ -0,0 +1,25 @@ +# performance-report + +Generate comprehensive performance reports for swarm operations. + +## Usage +```bash +npx claude-flow analysis performance-report [options] +``` + +## Options +- `--format ` - Report format (json, html, markdown) +- `--include-metrics` - Include detailed metrics +- `--compare ` - Compare with previous swarm + +## Examples +```bash +# Generate HTML report +npx claude-flow analysis performance-report --format html + +# Compare swarms +npx claude-flow analysis performance-report --compare swarm-123 + +# Full metrics report +npx claude-flow analysis performance-report --include-metrics --format markdown +``` diff --git a/.claude/commands/analysis/token-usage.md b/.claude/commands/analysis/token-usage.md new file mode 100644 index 0000000000..5d6f2b9cff --- /dev/null +++ b/.claude/commands/analysis/token-usage.md @@ -0,0 +1,25 @@ +# token-usage + +Analyze token usage patterns and optimize for efficiency. + +## Usage +```bash +npx claude-flow analysis token-usage [options] +``` + +## Options +- `--period