agents/workflows/performance-optimization.md at dc42c9d53ae453504f08ac57915091382d20415a

mirror of https://github.com/wshobson/agents.git synced 2026-03-18 17:47:16 +00:00

Files

Seth Hobson 3802bca865 Refine plugin marketplace for launch readiness

Plugin Scope Improvements:
- Remove language-specialists plugin (not task-focused)
- Split specialized-domains into 5 focused plugins:
  * blockchain-web3 - Smart contract development only
  * quantitative-trading - Financial modeling and trading only
  * payment-processing - Payment gateway integration only
  * game-development - Unity and Minecraft only
  * accessibility-compliance - WCAG auditing only
- Split business-operations into 3 focused plugins:
  * business-analytics - Metrics and reporting only
  * hr-legal-compliance - HR and legal docs only
  * customer-sales-automation - Support and sales workflows only
- Fix infrastructure-devops scope:
  * Remove database concerns (db-migrate, database-admin)
  * Remove observability concerns (observability-engineer)
  * Move slo-implement to incident-response
  * Focus purely on container orchestration (K8s, Docker, Terraform)
- Fix customer-sales-automation scope:
  * Remove content-marketer (unrelated to customer/sales workflows)

Marketplace Statistics:
- Total plugins: 27 (was 22)
- Tool coverage: 100% (42/42 tools referenced)
- Fat plugins removed: 3 (language-specialists, specialized-domains, business-operations)
- All plugins now have clear, focused tasks

Model Migration:
- Migrate all 42 tools from claude-sonnet-4-0/opus-4-1 to model: sonnet
- Migrate all 15 workflows from claude-opus-4-1 to model: sonnet
- Use short model syntax consistent with agent files

Documentation Updates:
- Update README.md with refined plugin structure
- Update plugin descriptions to be task-focused
- Remove anthropomorphic and marketing language
- Improve category organization (now 16 distinct categories)

Ready for October 9, 2025 @ 9am PST launch

2025-10-08 20:54:29 -04:00

3.9 KiB

Raw Blame History

model

model
sonnet

Optimize application performance end-to-end using specialized performance and optimization agents:

[Extended thinking: This workflow coordinates multiple agents to identify and fix performance bottlenecks across the entire stack. From database queries to frontend rendering, each agent contributes their expertise to create a highly optimized application.]

Phase 1: Performance Analysis

1. Application Profiling

Use Task tool with subagent_type="performance-engineer"
Prompt: "Profile application performance for: $ARGUMENTS. Identify CPU, memory, and I/O bottlenecks. Include flame graphs, memory profiles, and resource utilization metrics."
Output: Performance profile, bottleneck analysis, optimization priorities

2. Database Performance Analysis

Use Task tool with subagent_type="database-optimizer"
Prompt: "Analyze database performance for: $ARGUMENTS. Review query execution plans, identify slow queries, check indexing, and analyze connection pooling."
Output: Query optimization report, index recommendations, schema improvements

Phase 2: Backend Optimization

3. Backend Code Optimization

Use Task tool with subagent_type="performance-engineer"
Prompt: "Optimize backend code for: $ARGUMENTS based on profiling results. Focus on algorithm efficiency, caching strategies, and async operations."
Output: Optimized code, caching implementation, performance improvements

4. API Optimization

Use Task tool with subagent_type="backend-architect"
Prompt: "Optimize API design and implementation for: $ARGUMENTS. Consider pagination, response compression, field filtering, and batch operations."
Output: Optimized API endpoints, GraphQL query optimization, response time improvements

Phase 3: Frontend Optimization

5. Frontend Performance

Use Task tool with subagent_type="frontend-developer"
Prompt: "Optimize frontend performance for: $ARGUMENTS. Focus on bundle size, lazy loading, code splitting, and rendering performance. Implement Core Web Vitals improvements."
Output: Optimized bundles, lazy loading implementation, performance metrics

6. Mobile App Optimization

Use Task tool with subagent_type="mobile-developer"
Prompt: "Optimize mobile app performance for: $ARGUMENTS. Focus on startup time, memory usage, battery efficiency, and offline performance."
Output: Optimized mobile code, reduced app size, improved battery life

Phase 4: Infrastructure Optimization

7. Cloud Infrastructure Optimization

Use Task tool with subagent_type="cloud-architect"
Prompt: "Optimize cloud infrastructure for: $ARGUMENTS. Review auto-scaling, instance types, CDN usage, and geographic distribution."
Output: Infrastructure improvements, cost optimization, scaling strategy

8. Deployment Optimization

Use Task tool with subagent_type="deployment-engineer"
Prompt: "Optimize deployment and build processes for: $ARGUMENTS. Improve CI/CD performance, implement caching, and optimize container images."
Output: Faster builds, optimized containers, improved deployment times

Phase 5: Monitoring and Validation

9. Performance Monitoring Setup

Use Task tool with subagent_type="devops-troubleshooter"
Prompt: "Set up comprehensive performance monitoring for: $ARGUMENTS. Include APM, real user monitoring, and custom performance metrics."
Output: Monitoring dashboards, alert thresholds, SLO definitions

10. Performance Testing

Use Task tool with subagent_type="test-automator"
Prompt: "Create performance test suites for: $ARGUMENTS. Include load tests, stress tests, and performance regression tests."
Output: Performance test suite, benchmark results, regression prevention

Coordination Notes

Performance metrics guide optimization priorities
Each optimization must be validated with measurements
Consider trade-offs between different performance aspects
Document all optimizations and their impact

Performance optimization target: $ARGUMENTS

3.9 KiB Raw Blame History