🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Checkpoint: File edits
rUvd25432d460a9
diff --git a/.agents/skills/performance-analysis/SKILL.md b/.agents/skills/performance-analysis/SKILL.mdnew file mode 100644index 0000000000..e1cb3ce5c2--- /dev/null+++ b/.agents/skills/performance-analysis/SKILL.md@@ -0,0 +1,61 @@+---+name: performance-analysis+description: >+ Performance profiling, benchmarking, and optimization analysis. Identifies bottlenecks, measures latency, and provides optimization recommendations.+ Use when: performance issues, slow responses, memory usage concerns, optimization needed, benchmarking required.+ Skip when: feature development, bug fixes unrelated to performance, documentation tasks.+---++# Performance Analysis Skill++## Purpose+Performance profiling, benchmarking, and optimization analysis for claude-flow applications.++## When to Trigger+- Performance issues reported+- Slow API responses (>100ms for MCP)+- High memory usage+- Before/after optimization comparison+- Benchmarking new features++## Commands++### Run Benchmark Suite+```bash+npx claude-flow performance benchmark --suite all+```++### Profile Memory Usage+```bash+npx claude-flow memory usage --detail by-agent+```++### Detect Bottlenecks+```bash+npx claude-flow performance profile --depth full+```++### Generate Report+```bash+npx claude-flow performance report --format markdown+```++### Optimize Configuration+```bash+npx claude-flow performance optimize --target memory+```++## Performance Targets++| Metric | Target | How to Measure |+|--------|--------|----------------|+| HNSW Search | 150x-12,500x faster | `memory search --benchmark` |+| MCP Response | <100ms | `mcp test --latency` |+| CLI Startup | <500ms | `time npx claude-flow --version` |+| Memory Reduction | 50-75% | `memory usage --quantization int8` |++## Best Practices+1. Always establish baseline before optimization+2. Profile in production-like environment+3. Focus on critical path bottlenecks+4. Measure impact of each change independently