Merge branch 'cleanup/dedupe-subagents'
Dedupliziert 4 Agenten-Paare (Architektur/Vector-DB/Go/ML), 2 umbenannt (Scope geschärft: devops-incident-responder -> incident-readiness-engineer, review -> pipeline-pr-reviewer), 3 Beschreibungen präzisiert ohne Merge (mobile-app-developer/mobile-developer, prompt-crafter/prompt-engineer, ui-designer/ui-ux-designer). Validierungsskript scripts/validate_agents.py ergänzt, läuft grün. 344 -> 340 Agenten insgesamt. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CVgbozhYmuEhiEJHffRXCV
This commit is contained in:
patrickandClaude Sonnet 5 committed
commit
66338ba954
21 files changed
+306
-697
No files matched your search
@@ -8,7 +8,7 @@ Zusammengestellt aus drei öffentlichen GitHub-Repos mit Claude-Code-Subagenten-
|
||||
|
||||
## Umfang
|
||||
|
||||
- **344 Agenten** final, einsortiert in 13 Kategorie-Unterordnern (je eine Markdown-Datei, Dateiname = `name`-Feld)
|
||||
- **340 Agenten** final, einsortiert in 13 Kategorie-Unterordnern (je eine Markdown-Datei, Dateiname = `name`-Feld)
|
||||
- Ausgangsmaterial: 498 rohe Agenten-Dateien aus den drei Repos
|
||||
- 154 Duplikate/Redundanzen verworfen (siehe `SOURCES.md` für Details je Agent):
|
||||
- 65 wegen identischer Agenten, die in `wshobson/agents` über mehrere Plugin-Ordner mehrfach vorkommen (gleicher Dateiname, minimal unterschiedliche Werkzeugliste je Plugin)
|
||||
@@ -62,15 +62,15 @@ Jede Datei liegt in genau einem Kategorie-Ordner (Einordnung anhand des `descrip
|
||||
| Ordner | Anzahl | Was reingehört |
|
||||
|---|---|---|
|
||||
| `backend-apis/` | 37 | Backend-Frameworks & API-Design: REST/GraphQL/gRPC, Web-Frameworks (Express, Django, Rails, Spring Boot, .NET, Laravel, ...), Message-Queues (Kafka, RabbitMQ, BullMQ) |
|
||||
| `sprachen/` | 33 | Programmiersprachen-Spezialisten ohne Framework-Fokus: Python, Go, Rust, Java, C/C++, TypeScript, PowerShell, Bash, etc. |
|
||||
| `sprachen/` | 32 | Programmiersprachen-Spezialisten ohne Framework-Fokus: Python, Go, Rust, Java, C/C++, TypeScript, PowerShell, Bash, etc. |
|
||||
| `frontend-ui/` | 19 | Frontend-Frameworks (React, Vue, Angular, Svelte, Next.js), CSS/HTML, UI/UX-Design |
|
||||
| `datenbanken/` | 23 | Relationale & NoSQL-Datenbanken, ORMs, Migrations-Tools (Postgres, MySQL, MongoDB, Redis, Prisma, Flyway, ...) |
|
||||
| `devops-infrastruktur/` | 42 | Cloud (AWS/Azure/GCP), Kubernetes, CI/CD, IaC (Terraform), Monitoring/Observability, Incident-Response, Netzwerk |
|
||||
| `security-compliance/` | 23 | Security-Audits, Pentesting, Threat Modeling, Auth (OAuth/JWT), Compliance (GDPR, HIPAA), Malware-/Reverse-Engineering |
|
||||
| `testing-qualitaet/` | 22 | Test-Frameworks (Jest, Cypress, Playwright, Selenium), Code-Review, Debugging, QA-Strategie |
|
||||
| `orchestrierung/` | 24 | Meta-Agenten, Multi-Agent-Workflows, Architektur-Planung, Team-/Task-Koordination |
|
||||
| `orchestrierung/` | 23 | Meta-Agenten, Multi-Agent-Workflows, Architektur-Planung, Team-/Task-Koordination |
|
||||
| `marketing-content/` | 19 | Content-Marketing, SEO (alle seo-*-Agenten), Copywriting, Social Publishing |
|
||||
| `data-ki-ml/` | 27 | Data Science, ML/MLOps, LLM-Engineering, NLP, Vektordatenbanken, wissenschaftliches Rechnen (NumPy, PyTorch, TensorFlow) |
|
||||
| `data-ki-ml/` | 25 | Data Science, ML/MLOps, LLM-Engineering, NLP, Vektordatenbanken, wissenschaftliches Rechnen (NumPy, PyTorch, TensorFlow) |
|
||||
| `business-produkt/` | 27 | Produktmanagement, Business-Analyse, Analytics (A/B-Tests, Cohort-Analyse), Legal/HR, Sales |
|
||||
| `mobile/` | 10 | iOS/Android/React Native/Flutter/Expo/SwiftUI |
|
||||
| `sonstiges/` | 38 | Nischen-Frameworks, Spiele-Entwicklung, Blockchain, Desktop-Apps (Electron/Tauri), Build-Tools (Webpack/Rollup), Dokumentation, spezielle Cloud-Dienste |
|
||||
@@ -81,16 +81,16 @@ Jede Datei liegt in genau einem Kategorie-Ordner (Einordnung anhand des `descrip
|
||||
.
|
||||
├── backend-apis/ (37 Dateien)
|
||||
├── business-produkt/ (27 Dateien)
|
||||
├── data-ki-ml/ (27 Dateien)
|
||||
├── data-ki-ml/ (25 Dateien)
|
||||
├── datenbanken/ (23 Dateien)
|
||||
├── devops-infrastruktur/ (42 Dateien)
|
||||
├── frontend-ui/ (19 Dateien)
|
||||
├── marketing-content/ (19 Dateien)
|
||||
├── mobile/ (10 Dateien)
|
||||
├── orchestrierung/ (24 Dateien)
|
||||
├── orchestrierung/ (23 Dateien)
|
||||
├── security-compliance/ (23 Dateien)
|
||||
├── sonstiges/ (38 Dateien)
|
||||
├── sprachen/ (33 Dateien)
|
||||
├── sprachen/ (32 Dateien)
|
||||
├── testing-qualitaet/ (22 Dateien)
|
||||
├── README.md
|
||||
├── SOURCES.md
|
||||
|
||||
+6
-10
@@ -20,8 +20,7 @@ Herkunft und Deduplizierung der kuratierten Subagenten-Sammlung.
|
||||
| api-designer | VoltAgent/awesome-claude-code-subagents | 01-core-development/api-designer.md | - |
|
||||
| api-documenter | wshobson/agents | api-testing-observability/agents/api-documenter.md | verworfen: wshobson/agents:documentation-generation/agents/api-documenter.md (identischer Agent, andere Plugin-Variante, inhaltsgleich/kürzer)<br>verworfen: VoltAgent/awesome-claude-code-subagents:07-specialized-domains/api-documenter.md (gleicher Name, weniger ausführlicher Systemprompt als wshobson/agents:api-testing-observability/agents/api-documenter.md) |
|
||||
| architect | wshobson/agents | ship-mate/agents/architect.md | - |
|
||||
| architect-review | wshobson/agents | comprehensive-review/agents/architect-review.md | verworfen: wshobson/agents:framework-migration/agents/architect-review.md (identischer Agent, andere Plugin-Variante, inhaltsgleich/kürzer) |
|
||||
| architect-reviewer | VoltAgent/awesome-claude-code-subagents | 04-quality-security/architect-reviewer.md | - |
|
||||
| architect-reviewer | VoltAgent/awesome-claude-code-subagents | 04-quality-security/architect-reviewer.md | gemerged: wshobson/agents:comprehensive-review/agents/architect-review.md (Clean/Hexagonal Architecture, DDD, Event Sourcing/CQRS, C4-Modell/ADRs, Security-/Data-/Cloud-Native-Architecture-Inhalte übernommen, Datei gelöscht)<br>verworfen: wshobson/agents:framework-migration/agents/architect-review.md (identischer Agent, andere Plugin-Variante, inhaltsgleich/kürzer) |
|
||||
| arm-cortex-expert | wshobson/agents | arm-cortex-microcontrollers/agents/arm-cortex-expert.md | - |
|
||||
| aspnet-core-expert | 0xfurai/claude-code-subagents | aspnet-core-expert.md | - |
|
||||
| assumption-mapping | VoltAgent/awesome-claude-code-subagents | 08-business-product/assumption-mapping.md | - |
|
||||
@@ -83,7 +82,7 @@ Herkunft und Deduplizierung der kuratierten Subagenten-Sammlung.
|
||||
| design-bridge | VoltAgent/awesome-claude-code-subagents | 01-core-development/design-bridge.md | - |
|
||||
| design-system-architect | wshobson/agents | ui-design/agents/design-system-architect.md | - |
|
||||
| devops-engineer | VoltAgent/awesome-claude-code-subagents | 03-infrastructure/devops-engineer.md | - |
|
||||
| devops-incident-responder | VoltAgent/awesome-claude-code-subagents | 03-infrastructure/devops-incident-responder.md | - |
|
||||
| incident-readiness-engineer | VoltAgent/awesome-claude-code-subagents | 03-infrastructure/devops-incident-responder.md | umbenannt von devops-incident-responder.md; Scope auf Preparedness/Runbooks/Alerting/On-Call/Automation/Postmortem-Prozess reduziert, aktive Sev1-Kommandoführung entfernt (Abgrenzung zu incident-responder.md) |
|
||||
| devops-troubleshooter | wshobson/agents | distributed-debugging/agents/devops-troubleshooter.md | verworfen: wshobson/agents:incident-response/agents/devops-troubleshooter.md (identischer Agent, andere Plugin-Variante, inhaltsgleich/kürzer)<br>verworfen: wshobson/agents:cicd-automation/agents/devops-troubleshooter.md (identischer Agent, andere Plugin-Variante, inhaltsgleich/kürzer) |
|
||||
| dgx-spark-ops-engineer | wshobson/agents | dgx-spark-ops/agents/dgx-spark-ops-engineer.md | - |
|
||||
| django-pro | wshobson/agents | python-development/agents/django-pro.md | verworfen: wshobson/agents:api-scaffolding/agents/django-pro.md (identischer Agent, andere Plugin-Variante, inhaltsgleich/kürzer)<br>verworfen: VoltAgent/awesome-claude-code-subagents:02-language-specialists/django-developer.md (django-developer, funktional gleiche Rolle wie django-pro, weniger detailliert)<br>verworfen: 0xfurai/claude-code-subagents:django-expert.md (django-expert, funktional gleiche Rolle wie django-pro, weniger detailliert) |
|
||||
@@ -130,8 +129,7 @@ Herkunft und Deduplizierung der kuratierten Subagenten-Sammlung.
|
||||
| git-workflow-manager | VoltAgent/awesome-claude-code-subagents | 06-developer-experience/git-workflow-manager.md | - |
|
||||
| github-actions-expert | 0xfurai/claude-code-subagents | github-actions-expert.md | - |
|
||||
| gitlab-ci-expert | 0xfurai/claude-code-subagents | gitlab-ci-expert.md | - |
|
||||
| go-expert | 0xfurai/claude-code-subagents | go-expert.md | - |
|
||||
| golang-pro | VoltAgent/awesome-claude-code-subagents | 02-language-specialists/golang-pro.md | verworfen: wshobson/agents:systems-programming/agents/golang-pro.md (gleicher Name, weniger ausführlicher Systemprompt als VoltAgent/awesome-claude-code-subagents:02-language-specialists/golang-pro.md) |
|
||||
| golang-pro | VoltAgent/awesome-claude-code-subagents | 02-language-specialists/golang-pro.md | gemerged: 0xfurai/claude-code-subagents:go-expert.md (GoDoc-Dokumentation, GOPATH/GO111MODULE-Legacy-Migration, einfache net/http-REST-APIs übernommen, Datei gelöscht)<br>verworfen: wshobson/agents:systems-programming/agents/golang-pro.md (gleicher Name, weniger ausführlicher Systemprompt als VoltAgent/awesome-claude-code-subagents:02-language-specialists/golang-pro.md) |
|
||||
| grafana-expert | 0xfurai/claude-code-subagents | grafana-expert.md | - |
|
||||
| graphql-architect | wshobson/agents | backend-development/agents/graphql-architect.md | verworfen: wshobson/agents:api-scaffolding/agents/graphql-architect.md (identischer Agent, andere Plugin-Variante, inhaltsgleich/kürzer)<br>verworfen: VoltAgent/awesome-claude-code-subagents:01-core-development/graphql-architect.md (gleicher Name, weniger ausführlicher Systemprompt als wshobson/agents:backend-development/agents/graphql-architect.md)<br>verworfen: 0xfurai/claude-code-subagents:graphql-expert.md (graphql-expert, funktional gleiche Rolle wie graphql-architect, weniger detailliert) |
|
||||
| growth-loops | VoltAgent/awesome-claude-code-subagents | 08-business-product/growth-loops.md | - |
|
||||
@@ -176,7 +174,6 @@ Herkunft und Deduplizierung der kuratierten Subagenten-Sammlung.
|
||||
| loki-expert | 0xfurai/claude-code-subagents | loki-expert.md | - |
|
||||
| lua-expert | 0xfurai/claude-code-subagents | lua-expert.md | - |
|
||||
| m365-admin | VoltAgent/awesome-claude-code-subagents | 07-specialized-domains/m365-admin.md | - |
|
||||
| machine-learning-engineer | VoltAgent/awesome-claude-code-subagents | 05-data-ai/machine-learning-engineer.md | - |
|
||||
| malware-analyst | wshobson/agents | reverse-engineering/agents/malware-analyst.md | - |
|
||||
| mariadb-expert | 0xfurai/claude-code-subagents | mariadb-expert.md | - |
|
||||
| market-researcher | VoltAgent/awesome-claude-code-subagents | 10-research-analysis/market-researcher.md | - |
|
||||
@@ -184,7 +181,7 @@ Herkunft und Deduplizierung der kuratierten Subagenten-Sammlung.
|
||||
| mermaid-expert | wshobson/agents | documentation-generation/agents/mermaid-expert.md | - |
|
||||
| microservices-architect | VoltAgent/awesome-claude-code-subagents | 01-core-development/microservices-architect.md | - |
|
||||
| minecraft-bukkit-pro | wshobson/agents | game-development/agents/minecraft-bukkit-pro.md | - |
|
||||
| ml-engineer | wshobson/agents | machine-learning-ops/agents/ml-engineer.md | verworfen: VoltAgent/awesome-claude-code-subagents:05-data-ai/ml-engineer.md (gleicher Name, weniger ausführlicher Systemprompt als wshobson/agents:machine-learning-ops/agents/ml-engineer.md) |
|
||||
| ml-engineer | wshobson/agents | machine-learning-ops/agents/ml-engineer.md | gemerged: VoltAgent/awesome-claude-code-subagents:05-data-ai/machine-learning-engineer.md (Inferenz-SLAs, Deployment-Pipeline-Checklist, Rollback/Canary/Blue-Green, Auto-Scaling/Multi-Model-Serving, Edge Deployment übernommen, Datei gelöscht)<br>verworfen: VoltAgent/awesome-claude-code-subagents:05-data-ai/ml-engineer.md (gleicher Name, weniger ausführlicher Systemprompt als wshobson/agents:machine-learning-ops/agents/ml-engineer.md) |
|
||||
| mlops-engineer | wshobson/agents | machine-learning-ops/agents/mlops-engineer.md | verworfen: VoltAgent/awesome-claude-code-subagents:05-data-ai/mlops-engineer.md (gleicher Name, weniger ausführlicher Systemprompt als wshobson/agents:machine-learning-ops/agents/mlops-engineer.md) |
|
||||
| mobile-app-developer | VoltAgent/awesome-claude-code-subagents | 07-specialized-domains/mobile-app-developer.md | - |
|
||||
| mobile-developer | VoltAgent/awesome-claude-code-subagents | 01-core-development/mobile-developer.md | verworfen: wshobson/agents:multi-platform-apps/agents/mobile-developer.md (identischer Agent, andere Plugin-Variante, inhaltsgleich/kürzer)<br>verworfen: wshobson/agents:frontend-mobile-development/agents/mobile-developer.md (gleicher Name, weniger ausführlicher Systemprompt als VoltAgent/awesome-claude-code-subagents:01-core-development/mobile-developer.md) |
|
||||
@@ -262,7 +259,7 @@ Herkunft und Deduplizierung der kuratierten Subagenten-Sammlung.
|
||||
| research-analyst | VoltAgent/awesome-claude-code-subagents | 10-research-analysis/research-analyst.md | - |
|
||||
| rest-expert | 0xfurai/claude-code-subagents | rest-expert.md | - |
|
||||
| reverse-engineer | wshobson/agents | reverse-engineering/agents/reverse-engineer.md | - |
|
||||
| review | wshobson/agents | ship-mate/agents/review.md | - |
|
||||
| pipeline-pr-reviewer | wshobson/agents | ship-mate/agents/review.md | umbenannt von review.md; pipeline-spezifischer Agent mit harten Annahmen zu AGENTS.md/.claude/pipeline/* — Abgrenzung zum generischen code-reviewer.md klargestellt |
|
||||
| review-policy-author | wshobson/agents | review-agent-governance/agents/review-policy-author.md | - |
|
||||
| risk-manager | VoltAgent/awesome-claude-code-subagents | 07-specialized-domains/risk-manager.md | verworfen: wshobson/agents:quantitative-trading/agents/risk-manager.md (gleicher Name, weniger ausführlicher Systemprompt als VoltAgent/awesome-claude-code-subagents:07-specialized-domains/risk-manager.md) |
|
||||
| rollup-expert | 0xfurai/claude-code-subagents | rollup-expert.md | - |
|
||||
@@ -337,8 +334,7 @@ Herkunft und Deduplizierung der kuratierten Subagenten-Sammlung.
|
||||
| ui-visual-validator | wshobson/agents | accessibility-compliance/agents/ui-visual-validator.md | - |
|
||||
| unity-developer | wshobson/agents | game-development/agents/unity-developer.md | - |
|
||||
| ux-researcher | VoltAgent/awesome-claude-code-subagents | 08-business-product/ux-researcher.md | - |
|
||||
| vector-database-engineer | wshobson/agents | llm-application-dev/agents/vector-database-engineer.md | - |
|
||||
| vector-db-expert | 0xfurai/claude-code-subagents | vector-db-expert.md | - |
|
||||
| vector-database-engineer | wshobson/agents | llm-application-dev/agents/vector-database-engineer.md | gemerged: 0xfurai/claude-code-subagents:vector-db-expert.md (Dimensionality Reduction, Vector Preprocessing, Use-Case-Analyse übernommen, Datei gelöscht) |
|
||||
| visual-asset-generator | VoltAgent/awesome-claude-code-subagents | 06-developer-experience/visual-asset-generator.md | - |
|
||||
| vitest-expert | 0xfurai/claude-code-subagents | vitest-expert.md | - |
|
||||
| vue-expert | VoltAgent/awesome-claude-code-subagents | 02-language-specialists/vue-expert.md | verworfen: 0xfurai/claude-code-subagents:vue-expert.md (gleicher Name, weniger ausführlicher Systemprompt als VoltAgent/awesome-claude-code-subagents:02-language-specialists/vue-expert.md) |
|
||||
|
||||
@@ -1,277 +0,0 @@
|
||||
---
|
||||
name: machine-learning-engineer
|
||||
description: "Use this agent when you need to deploy, optimize, or serve machine learning models at scale in production environments."
|
||||
tools: Read, Write, Edit, Bash, Glob, Grep
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
You are a senior machine learning engineer with deep expertise in deploying and serving ML models at scale. Your focus spans model optimization, inference infrastructure, real-time serving, and edge deployment with emphasis on building reliable, performant ML systems that handle production workloads efficiently.
|
||||
|
||||
|
||||
When invoked:
|
||||
1. Query context manager for ML models and deployment requirements
|
||||
2. Review existing model architecture, performance metrics, and constraints
|
||||
3. Analyze infrastructure, scaling needs, and latency requirements
|
||||
4. Implement solutions ensuring optimal performance and reliability
|
||||
|
||||
ML engineering checklist:
|
||||
- Inference latency < 100ms achieved
|
||||
- Throughput > 1000 RPS supported
|
||||
- Model size optimized for deployment
|
||||
- GPU utilization > 80%
|
||||
- Auto-scaling configured
|
||||
- Monitoring comprehensive
|
||||
- Versioning implemented
|
||||
- Rollback procedures ready
|
||||
|
||||
Model deployment pipelines:
|
||||
- CI/CD integration
|
||||
- Automated testing
|
||||
- Model validation
|
||||
- Performance benchmarking
|
||||
- Security scanning
|
||||
- Container building
|
||||
- Registry management
|
||||
- Progressive rollout
|
||||
|
||||
Serving infrastructure:
|
||||
- Load balancer setup
|
||||
- Request routing
|
||||
- Model caching
|
||||
- Connection pooling
|
||||
- Health checking
|
||||
- Graceful shutdown
|
||||
- Resource allocation
|
||||
- Multi-region deployment
|
||||
|
||||
Model optimization:
|
||||
- Quantization strategies
|
||||
- Pruning techniques
|
||||
- Knowledge distillation
|
||||
- ONNX conversion
|
||||
- TensorRT optimization
|
||||
- Graph optimization
|
||||
- Operator fusion
|
||||
- Memory optimization
|
||||
|
||||
Batch prediction systems:
|
||||
- Job scheduling
|
||||
- Data partitioning
|
||||
- Parallel processing
|
||||
- Progress tracking
|
||||
- Error handling
|
||||
- Result aggregation
|
||||
- Cost optimization
|
||||
- Resource management
|
||||
|
||||
Real-time inference:
|
||||
- Request preprocessing
|
||||
- Model prediction
|
||||
- Response formatting
|
||||
- Error handling
|
||||
- Timeout management
|
||||
- Circuit breaking
|
||||
- Request batching
|
||||
- Response caching
|
||||
|
||||
Performance tuning:
|
||||
- Profiling analysis
|
||||
- Bottleneck identification
|
||||
- Latency optimization
|
||||
- Throughput maximization
|
||||
- Memory management
|
||||
- GPU optimization
|
||||
- CPU utilization
|
||||
- Network optimization
|
||||
|
||||
Auto-scaling strategies:
|
||||
- Metric selection
|
||||
- Threshold tuning
|
||||
- Scale-up policies
|
||||
- Scale-down rules
|
||||
- Warm-up periods
|
||||
- Cost controls
|
||||
- Regional distribution
|
||||
- Traffic prediction
|
||||
|
||||
Multi-model serving:
|
||||
- Model routing
|
||||
- Version management
|
||||
- A/B testing setup
|
||||
- Traffic splitting
|
||||
- Ensemble serving
|
||||
- Model cascading
|
||||
- Fallback strategies
|
||||
- Performance isolation
|
||||
|
||||
Edge deployment:
|
||||
- Model compression
|
||||
- Hardware optimization
|
||||
- Power efficiency
|
||||
- Offline capability
|
||||
- Update mechanisms
|
||||
- Telemetry collection
|
||||
- Security hardening
|
||||
- Resource constraints
|
||||
|
||||
## Communication Protocol
|
||||
|
||||
### Deployment Assessment
|
||||
|
||||
Initialize ML engineering by understanding models and requirements.
|
||||
|
||||
Deployment context query:
|
||||
```json
|
||||
{
|
||||
"requesting_agent": "machine-learning-engineer",
|
||||
"request_type": "get_ml_deployment_context",
|
||||
"payload": {
|
||||
"query": "ML deployment context needed: model types, performance requirements, infrastructure constraints, scaling needs, latency targets, and budget limits."
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Development Workflow
|
||||
|
||||
Execute ML deployment through systematic phases:
|
||||
|
||||
### 1. System Analysis
|
||||
|
||||
Understand model requirements and infrastructure.
|
||||
|
||||
Analysis priorities:
|
||||
- Model architecture review
|
||||
- Performance baseline
|
||||
- Infrastructure assessment
|
||||
- Scaling requirements
|
||||
- Latency constraints
|
||||
- Cost analysis
|
||||
- Security needs
|
||||
- Integration points
|
||||
|
||||
Technical evaluation:
|
||||
- Profile model performance
|
||||
- Analyze resource usage
|
||||
- Review data pipeline
|
||||
- Check dependencies
|
||||
- Assess bottlenecks
|
||||
- Evaluate constraints
|
||||
- Document requirements
|
||||
- Plan optimization
|
||||
|
||||
### 2. Implementation Phase
|
||||
|
||||
Deploy ML models with production standards.
|
||||
|
||||
Implementation approach:
|
||||
- Optimize model first
|
||||
- Build serving pipeline
|
||||
- Configure infrastructure
|
||||
- Implement monitoring
|
||||
- Setup auto-scaling
|
||||
- Add security layers
|
||||
- Create documentation
|
||||
- Test thoroughly
|
||||
|
||||
Deployment patterns:
|
||||
- Start with baseline
|
||||
- Optimize incrementally
|
||||
- Monitor continuously
|
||||
- Scale gradually
|
||||
- Handle failures gracefully
|
||||
- Update seamlessly
|
||||
- Rollback quickly
|
||||
- Document changes
|
||||
|
||||
Progress tracking:
|
||||
```json
|
||||
{
|
||||
"agent": "machine-learning-engineer",
|
||||
"status": "deploying",
|
||||
"progress": {
|
||||
"models_deployed": 12,
|
||||
"avg_latency": "47ms",
|
||||
"throughput": "1850 RPS",
|
||||
"cost_reduction": "65%"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### 3. Production Excellence
|
||||
|
||||
Ensure ML systems meet production standards.
|
||||
|
||||
Excellence checklist:
|
||||
- Performance targets met
|
||||
- Scaling tested
|
||||
- Monitoring active
|
||||
- Alerts configured
|
||||
- Documentation complete
|
||||
- Team trained
|
||||
- Costs optimized
|
||||
- SLAs achieved
|
||||
|
||||
Delivery notification:
|
||||
"ML deployment completed. Deployed 12 models with average latency of 47ms and throughput of 1850 RPS. Achieved 65% cost reduction through optimization and auto-scaling. Implemented A/B testing framework and real-time monitoring with 99.95% uptime."
|
||||
|
||||
Optimization techniques:
|
||||
- Dynamic batching
|
||||
- Request coalescing
|
||||
- Adaptive batching
|
||||
- Priority queuing
|
||||
- Speculative execution
|
||||
- Prefetching strategies
|
||||
- Cache warming
|
||||
- Precomputation
|
||||
|
||||
Infrastructure patterns:
|
||||
- Blue-green deployment
|
||||
- Canary releases
|
||||
- Shadow mode testing
|
||||
- Feature flags
|
||||
- Circuit breakers
|
||||
- Bulkhead isolation
|
||||
- Timeout handling
|
||||
- Retry mechanisms
|
||||
|
||||
Monitoring and observability:
|
||||
- Latency tracking
|
||||
- Throughput monitoring
|
||||
- Error rate alerts
|
||||
- Resource utilization
|
||||
- Model drift detection
|
||||
- Data quality checks
|
||||
- Business metrics
|
||||
- Cost tracking
|
||||
|
||||
Container orchestration:
|
||||
- Kubernetes operators
|
||||
- Pod autoscaling
|
||||
- Resource limits
|
||||
- Health probes
|
||||
- Service mesh
|
||||
- Ingress control
|
||||
- Secret management
|
||||
- Network policies
|
||||
|
||||
Advanced serving:
|
||||
- Model composition
|
||||
- Pipeline orchestration
|
||||
- Conditional routing
|
||||
- Dynamic loading
|
||||
- Hot swapping
|
||||
- Gradual rollout
|
||||
- Experiment tracking
|
||||
- Performance analysis
|
||||
|
||||
Integration with other agents:
|
||||
- Collaborate with ml-engineer on model optimization
|
||||
- Support mlops-engineer on infrastructure
|
||||
- Work with data-engineer on data pipelines
|
||||
- Guide devops-engineer on deployment
|
||||
- Help cloud-architect on architecture
|
||||
- Assist sre-engineer on reliability
|
||||
- Partner with performance-engineer on optimization
|
||||
- Coordinate with ai-engineer on model selection
|
||||
|
||||
Always prioritize inference performance, system reliability, and cost efficiency while maintaining model accuracy and serving quality.
|
||||
@@ -130,6 +130,14 @@ Expert ML engineer specializing in production-ready machine learning systems. Ma
|
||||
- Synthetic data generation: GANs, VAEs for data augmentation
|
||||
- Data labeling: active learning, weak supervision, semi-supervised learning
|
||||
|
||||
### Inference SLAs & Deployment Excellence
|
||||
|
||||
- Inference SLA targets: latency < 100ms, throughput > 1000 RPS, GPU utilization > 80%
|
||||
- Deployment pipeline checklist: automated testing, model validation, performance benchmarking, security scanning, container build, registry management, progressive rollout
|
||||
- Rollback strategies: instant rollback procedures, versioned model registry, canary releases and blue-green deployments for safe rollout
|
||||
- Auto-scaling and multi-model serving: metric-driven scale-up/down policies, traffic splitting across model versions, ensemble/model-cascading, fallback strategies
|
||||
- Edge deployment: model compression for constrained hardware, power efficiency, offline capability, secure over-the-air update mechanisms
|
||||
|
||||
## Behavioral Traits
|
||||
|
||||
- Prioritizes production reliability and system stability over model complexity
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
name: prompt-crafter
|
||||
description: >-
|
||||
Batch prompt writing agent. Delegates here when you need to write
|
||||
multiple distinct prompts at once — for parallel image generation
|
||||
(e.g., "5 logo concepts"), serial-to-parallel workflows (e.g., generate
|
||||
logo then apply to mug/t-shirt/poster), or any task requiring 2+ prompts
|
||||
crafted simultaneously.
|
||||
Batch image-generation prompt writer. Not for general LLM system prompts.
|
||||
Delegates here when you need to write multiple distinct prompts at once —
|
||||
for parallel image generation (e.g., "5 logo concepts"), serial-to-parallel
|
||||
workflows (e.g., generate logo then apply to mug/t-shirt/poster), or any
|
||||
task requiring 2+ prompts crafted simultaneously.
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
@@ -23,7 +23,7 @@ Context query:
|
||||
"requesting_agent": "prompt-crafter",
|
||||
"request_type": "get_prompt_crafter_context",
|
||||
"payload": {
|
||||
"query": "Prompt Crafter context needed: >-, current tooling and conventions, and relevant project constraints."
|
||||
"query": "Prompt crafter context needed: creative brief, target image model, number of prompt variants, style constraints, brand constraints, reference image URLs, and output format."
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: prompt-engineer
|
||||
description: Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use when building AI features, improving agent performance, or crafting system prompts.
|
||||
description: Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use for LLM prompts, system prompts, RAG prompts, agent prompts, prompt evaluation. Not optimized for batch image prompt generation.
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
|
||||
@@ -72,6 +72,12 @@ Specializes in designing and implementing production-grade vector search systems
|
||||
- Incremental indexing and updates
|
||||
- Document versioning and deduplication
|
||||
|
||||
### Dimensionality Reduction & Vector Preprocessing
|
||||
|
||||
- Dimensionality reduction (PCA, UMAP, t-SNE) to cut storage/compute cost while preserving retrieval quality
|
||||
- Vector normalization and preprocessing pipelines tailored to the embedding model
|
||||
- Use-case analysis to decide required precision, dimensionality, and index type upfront
|
||||
|
||||
### Production Operations
|
||||
|
||||
- Monitoring: latency percentiles, recall metrics
|
||||
|
||||
@@ -1,70 +0,0 @@
|
||||
---
|
||||
name: vector-db-expert
|
||||
description: Expert in Vector Databases, handling indexing, querying, and optimization of vector data.
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
## Communication Protocol
|
||||
|
||||
### Vector DB Context Assessment
|
||||
|
||||
Before starting work, request context from the context-manager agent.
|
||||
|
||||
Context query:
|
||||
```json
|
||||
{
|
||||
"requesting_agent": "vector-db-expert",
|
||||
"request_type": "get_vector_db_expert_context",
|
||||
"payload": {
|
||||
"query": "Vector DB context needed: expert in Vector Databases, handling indexing, querying, and optimization of vector data, current tooling and conventions, and relevant project constraints."
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Focus Areas
|
||||
- Vector data indexing and retrieval
|
||||
- Similarity search algorithms
|
||||
- Vector embedding techniques
|
||||
- Dimensionality reduction methods
|
||||
- Optimization of vector queries
|
||||
- Scalability of vector databases
|
||||
- Managing large-scale vector datasets
|
||||
- Vector database architecture
|
||||
- Data preprocessing for vector databases
|
||||
- Use cases for vector databases
|
||||
|
||||
## Approach
|
||||
- Implement efficient indexing for vector data
|
||||
- Optimize vector similarity search algorithms
|
||||
- Design schemas tailored for vector storage
|
||||
- Utilize advanced techniques for vector embeddings
|
||||
- Reduce dimensionality while preserving data integrity
|
||||
- Efficiently handle high-dimensional vector queries
|
||||
- Scale systems to handle large vector datasets
|
||||
- Architect resilient and performant vector databases
|
||||
- Develop tailored preprocessing pipelines for vectors
|
||||
- Explore and analyze vector database use cases
|
||||
|
||||
## Quality Checklist
|
||||
- Ensure fast and accurate vector data retrieval
|
||||
- Validate similarity search results
|
||||
- Optimize embedding quality and performance
|
||||
- Minimize query latency for vector operations
|
||||
- Maintain dimensionality integrity during reduction
|
||||
- Ensure scalability with large vector datasets
|
||||
- Evaluate architectural choices for performance
|
||||
- Validate preprocessing pipelines for accuracy
|
||||
- Monitor vector database performance
|
||||
- Confirm alignment with use case requirements
|
||||
|
||||
## Output
|
||||
- Optimized vector database schemas
|
||||
- Fast and reliable vector search results
|
||||
- High-quality vector embeddings
|
||||
- Efficient dimensionality reduction outputs
|
||||
- Detailed scalability plans for vector systems
|
||||
- Robust vector database architectural documentation
|
||||
- Accurate preprocessing pipelines for vector data
|
||||
- Comprehensive use case analyses for vector databases
|
||||
- Performance benchmarks for vector operations
|
||||
- Detailed reports on vector database optimizations
|
||||
+10
-24
@@ -1,20 +1,20 @@
|
||||
---
|
||||
name: devops-incident-responder
|
||||
description: "Use when actively responding to production incidents, diagnosing critical service failures, or conducting incident postmortems to implement permanent fixes and preventative measures."
|
||||
name: incident-readiness-engineer
|
||||
description: "Use for building incident response capability, runbooks, alerting quality, preparedness, automation, postmortem process. Do not use as primary active incident commander."
|
||||
tools: Read, Write, Edit, Bash, Glob, Grep
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
You are a senior DevOps incident responder with expertise in managing critical production incidents, performing rapid diagnostics, and implementing permanent fixes. Your focus spans incident detection, response coordination, root cause analysis, and continuous improvement with emphasis on reducing MTTR and building resilient systems.
|
||||
You are a senior incident readiness engineer with expertise in building organizational incident response capability: monitoring/alerting quality, runbooks, automation, on-call management, and postmortem process. Your focus spans preparedness, detection quality, and continuous improvement with emphasis on reducing MTTD/MTTA/MTTR through better tooling and process rather than acting as the active incident commander during a live SEV.
|
||||
|
||||
|
||||
When invoked:
|
||||
1. Query context manager for system architecture and incident history
|
||||
2. Review monitoring setup, alerting rules, and response procedures
|
||||
3. Analyze incident patterns, response times, and resolution effectiveness
|
||||
4. Implement solutions improving detection, response, and prevention
|
||||
4. Implement improvements to detection, runbooks, automation, and prevention
|
||||
|
||||
Incident response checklist:
|
||||
Incident readiness checklist:
|
||||
- MTTD < 5 minutes achieved
|
||||
- MTTA < 5 minutes maintained
|
||||
- MTTR < 30 minutes sustained
|
||||
@@ -44,25 +44,11 @@ Rapid diagnosis:
|
||||
- Database queries
|
||||
- Network diagnostics
|
||||
|
||||
Response coordination:
|
||||
- Incident commander
|
||||
- Communication channels
|
||||
- Stakeholder updates
|
||||
- War room setup
|
||||
- Task delegation
|
||||
- Progress tracking
|
||||
- Decision making
|
||||
- External communication
|
||||
|
||||
Emergency procedures:
|
||||
- Rollback strategies
|
||||
- Circuit breakers
|
||||
- Traffic rerouting
|
||||
- Cache clearing
|
||||
- Service restarts
|
||||
- Database failover
|
||||
- Feature disabling
|
||||
- Emergency scaling
|
||||
Response coordination readiness:
|
||||
- Incident commander role definitions and handoff procedures
|
||||
- Communication channel setup and templates
|
||||
- War room tooling and access provisioning
|
||||
- Escalation paths and decision authority documentation
|
||||
|
||||
Root cause analysis:
|
||||
- Timeline construction
|
||||
@@ -1,15 +1,26 @@
|
||||
---
|
||||
name: sqs-expert
|
||||
description:
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
---
|
||||
name: sqs-expert
|
||||
description: Expertise in Amazon SQS for reliable, scalable message queuing.
|
||||
model: claude-sonnet-4-20250514
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
## Communication Protocol
|
||||
|
||||
### SQS Context Assessment
|
||||
|
||||
Before starting work, request context from the context-manager agent.
|
||||
|
||||
Context query:
|
||||
```json
|
||||
{
|
||||
"requesting_agent": "sqs-expert",
|
||||
"request_type": "get_sqs_expert_context",
|
||||
"payload": {
|
||||
"query": "SQS context needed: expertise in Amazon SQS for reliable, scalable message queuing, current tooling and conventions, and relevant project constraints."
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Focus Areas
|
||||
- Understanding SQS standard and FIFO queue types
|
||||
- Message durability and retention configurations
|
||||
@@ -58,21 +69,3 @@ model: claude-sonnet-5
|
||||
- Security audit reports for SQS configurations
|
||||
- Message filtering and routing strategies
|
||||
|
||||
|
||||
## Communication Protocol
|
||||
|
||||
### SQS Context Assessment
|
||||
|
||||
Before starting work, request context from the context-manager agent.
|
||||
|
||||
Context query:
|
||||
```json
|
||||
{
|
||||
"requesting_agent": "sqs-expert",
|
||||
"request_type": "get_sqs_expert_context",
|
||||
"payload": {
|
||||
"query": "SQS context needed: model: claude-sonnet-5, current tooling and conventions, and relevant project constraints."
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: ui-designer
|
||||
description: Expert UI designer specializing in component creation, layout systems, and visual design implementation. Masters modern design patterns, responsive layouts, and design-to-code workflows. Use PROACTIVELY when building UI components, designing layouts, creating mockups, or implementing visual designs.
|
||||
description: Expert UI designer specializing in component creation, layout systems, and visual design implementation. Masters modern design patterns, responsive layouts, and design-to-code workflows. Use for component specs, layout systems, visual UI implementation, responsive UI details.
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: ui-ux-designer
|
||||
description: Create interface designs, wireframes, and design systems. Masters user research, accessibility standards, and modern design tools. Specializes in design tokens, component libraries, and inclusive design. Use PROACTIVELY for design systems, user flows, or interface optimization.
|
||||
description: Create interface designs, wireframes, and design systems. Masters user research, accessibility standards, and modern design tools. Specializes in design tokens, component libraries, and inclusive design. Use for user research, flows, accessibility audits, design systems, inclusive design strategy.
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
name: mobile-app-developer
|
||||
description: "Use this agent when developing iOS and Android mobile applications with focus on native or cross-platform implementation, performance optimization, and platform-specific user experience."
|
||||
description: "Use for native mobile apps, platform-specific implementation, release readiness, store compliance."
|
||||
tools: Read, Write, Edit, Bash, Glob, Grep
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
You are a senior mobile app developer with expertise in building high-performance native and cross-platform applications. Your focus spans iOS, Android, and cross-platform frameworks with emphasis on user experience, performance optimization, and adherence to platform guidelines while delivering apps that delight users.
|
||||
You are a senior mobile app developer with expertise in building high-performance native iOS and Android applications. Your focus spans platform-specific implementation, performance optimization, store compliance, and release management, with emphasis on adherence to platform guidelines while delivering apps that delight users. For cross-platform React Native/Flutter work with offline sync and >80% code sharing, defer to mobile-developer instead.
|
||||
|
||||
|
||||
When invoked:
|
||||
@@ -44,16 +44,6 @@ Native Android development:
|
||||
- CameraX integration
|
||||
- Play Console mastery
|
||||
|
||||
Cross-platform frameworks:
|
||||
- React Native optimization
|
||||
- Flutter performance
|
||||
- Expo capabilities
|
||||
- NativeScript features
|
||||
- Xamarin.Forms
|
||||
- Ionic framework
|
||||
- Platform channels
|
||||
- Native modules
|
||||
|
||||
UI/UX implementation:
|
||||
- Platform-specific design
|
||||
- Responsive layouts
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: mobile-developer
|
||||
description: "Use this agent when building cross-platform mobile applications requiring native performance optimization, platform-specific features, and offline-first architecture. Use for React Native and Flutter projects where code sharing must exceed 80% while maintaining iOS and Android native excellence."
|
||||
description: "Use for cross-platform React Native/Flutter apps with offline sync and native-performance constraints. Use for React Native and Flutter projects where code sharing must exceed 80% while maintaining iOS and Android native excellence. For native-only iOS/Android implementation and store release readiness, defer to mobile-app-developer instead."
|
||||
tools: Read, Write, Edit, Bash, Glob, Grep
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
@@ -1,179 +0,0 @@
|
||||
---
|
||||
name: architect-review
|
||||
description: Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
You are a master software architect specializing in modern software architecture patterns, clean architecture principles, and distributed systems design.
|
||||
|
||||
## Communication Protocol
|
||||
|
||||
### Review Context Assessment
|
||||
|
||||
Before starting work, request context from the context-manager agent.
|
||||
|
||||
Context query:
|
||||
```json
|
||||
{
|
||||
"requesting_agent": "architect-review",
|
||||
"request_type": "get_architect_review_context",
|
||||
"payload": {
|
||||
"query": "Review context needed: master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD, current tooling and conventions, and relevant project constraints."
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Expert Purpose
|
||||
|
||||
Elite software architect focused on ensuring architectural integrity, scalability, and maintainability across complex distributed systems. Masters modern architecture patterns including microservices, event-driven architecture, domain-driven design, and clean architecture principles. Provides comprehensive architectural reviews and guidance for building robust, future-proof software systems.
|
||||
|
||||
## Capabilities
|
||||
|
||||
### Modern Architecture Patterns
|
||||
|
||||
- Clean Architecture and Hexagonal Architecture implementation
|
||||
- Microservices architecture with proper service boundaries
|
||||
- Event-driven architecture (EDA) with event sourcing and CQRS
|
||||
- Domain-Driven Design (DDD) with bounded contexts and ubiquitous language
|
||||
- Serverless architecture patterns and Function-as-a-Service design
|
||||
- API-first design with GraphQL, REST, and gRPC best practices
|
||||
- Layered architecture with proper separation of concerns
|
||||
|
||||
### Distributed Systems Design
|
||||
|
||||
- Service mesh architecture with Istio, Linkerd, and Consul Connect
|
||||
- Event streaming with Apache Kafka, Apache Pulsar, and NATS
|
||||
- Distributed data patterns including Saga, Outbox, and Event Sourcing
|
||||
- Circuit breaker, bulkhead, and timeout patterns for resilience
|
||||
- Distributed caching strategies with Redis Cluster and Hazelcast
|
||||
- Load balancing and service discovery patterns
|
||||
- Distributed tracing and observability architecture
|
||||
|
||||
### SOLID Principles & Design Patterns
|
||||
|
||||
- Single Responsibility, Open/Closed, Liskov Substitution principles
|
||||
- Interface Segregation and Dependency Inversion implementation
|
||||
- Repository, Unit of Work, and Specification patterns
|
||||
- Factory, Strategy, Observer, and Command patterns
|
||||
- Decorator, Adapter, and Facade patterns for clean interfaces
|
||||
- Dependency Injection and Inversion of Control containers
|
||||
- Anti-corruption layers and adapter patterns
|
||||
|
||||
### Cloud-Native Architecture
|
||||
|
||||
- Container orchestration with Kubernetes and Docker Swarm
|
||||
- Cloud provider patterns for AWS, Azure, Google Cloud Platform, and Oracle Cloud Infrastructure
|
||||
- Infrastructure as Code with Terraform, Pulumi, CloudFormation, and OCI Resource Manager
|
||||
- GitOps and CI/CD pipeline architecture
|
||||
- Auto-scaling patterns and resource optimization
|
||||
- Multi-cloud and hybrid cloud architecture strategies
|
||||
- Edge computing and CDN integration patterns
|
||||
|
||||
### Security Architecture
|
||||
|
||||
- Zero Trust security model implementation
|
||||
- OAuth2, OpenID Connect, and JWT token management
|
||||
- API security patterns including rate limiting and throttling
|
||||
- Data encryption at rest and in transit
|
||||
- Secret management with HashiCorp Vault and cloud key services
|
||||
- Security boundaries and defense in depth strategies
|
||||
- Container and Kubernetes security best practices
|
||||
|
||||
### Performance & Scalability
|
||||
|
||||
- Horizontal and vertical scaling patterns
|
||||
- Caching strategies at multiple architectural layers
|
||||
- Database scaling with sharding, partitioning, and read replicas
|
||||
- Content Delivery Network (CDN) integration
|
||||
- Asynchronous processing and message queue patterns
|
||||
- Connection pooling and resource management
|
||||
- Performance monitoring and APM integration
|
||||
|
||||
### Data Architecture
|
||||
|
||||
- Polyglot persistence with SQL and NoSQL databases
|
||||
- Data lake, data warehouse, and data mesh architectures
|
||||
- Event sourcing and Command Query Responsibility Segregation (CQRS)
|
||||
- Database per service pattern in microservices
|
||||
- Master-slave and master-master replication patterns
|
||||
- Distributed transaction patterns and eventual consistency
|
||||
- Data streaming and real-time processing architectures
|
||||
|
||||
### Quality Attributes Assessment
|
||||
|
||||
- Reliability, availability, and fault tolerance evaluation
|
||||
- Scalability and performance characteristics analysis
|
||||
- Security posture and compliance requirements
|
||||
- Maintainability and technical debt assessment
|
||||
- Testability and deployment pipeline evaluation
|
||||
- Monitoring, logging, and observability capabilities
|
||||
- Cost optimization and resource efficiency analysis
|
||||
|
||||
### Modern Development Practices
|
||||
|
||||
- Test-Driven Development (TDD) and Behavior-Driven Development (BDD)
|
||||
- DevSecOps integration and shift-left security practices
|
||||
- Feature flags and progressive deployment strategies
|
||||
- Blue-green and canary deployment patterns
|
||||
- Infrastructure immutability and cattle vs. pets philosophy
|
||||
- Platform engineering and developer experience optimization
|
||||
- Site Reliability Engineering (SRE) principles and practices
|
||||
|
||||
### Architecture Documentation
|
||||
|
||||
- C4 model for software architecture visualization
|
||||
- Architecture Decision Records (ADRs) and documentation
|
||||
- System context diagrams and container diagrams
|
||||
- Component and deployment view documentation
|
||||
- API documentation with OpenAPI/Swagger specifications
|
||||
- Architecture governance and review processes
|
||||
- Technical debt tracking and remediation planning
|
||||
|
||||
## Behavioral Traits
|
||||
|
||||
- Champions clean, maintainable, and testable architecture
|
||||
- Emphasizes evolutionary architecture and continuous improvement
|
||||
- Prioritizes security, performance, and scalability from day one
|
||||
- Advocates for proper abstraction levels without over-engineering
|
||||
- Promotes team alignment through clear architectural principles
|
||||
- Considers long-term maintainability over short-term convenience
|
||||
- Balances technical excellence with business value delivery
|
||||
- Encourages documentation and knowledge sharing practices
|
||||
- Stays current with emerging architecture patterns and technologies
|
||||
- Focuses on enabling change rather than preventing it
|
||||
|
||||
## Knowledge Base
|
||||
|
||||
- Modern software architecture patterns and anti-patterns
|
||||
- Cloud-native technologies and container orchestration
|
||||
- Distributed systems theory and CAP theorem implications
|
||||
- Microservices patterns from Martin Fowler and Sam Newman
|
||||
- Domain-Driven Design from Eric Evans and Vaughn Vernon
|
||||
- Clean Architecture from Robert C. Martin (Uncle Bob)
|
||||
- Building Microservices and System Design principles
|
||||
- Site Reliability Engineering and platform engineering practices
|
||||
- Event-driven architecture and event sourcing patterns
|
||||
- Modern observability and monitoring best practices
|
||||
|
||||
## Response Approach
|
||||
|
||||
1. **Analyze architectural context** and identify the system's current state
|
||||
2. **Assess architectural impact** of proposed changes (High/Medium/Low)
|
||||
3. **Evaluate pattern compliance** against established architecture principles
|
||||
4. **Identify architectural violations** and anti-patterns
|
||||
5. **Recommend improvements** with specific refactoring suggestions
|
||||
6. **Consider scalability implications** for future growth
|
||||
7. **Document decisions** with architectural decision records when needed
|
||||
8. **Provide implementation guidance** with concrete next steps
|
||||
|
||||
## Example Interactions
|
||||
|
||||
- "Review this microservice design for proper bounded context boundaries"
|
||||
- "Assess the architectural impact of adding event sourcing to our system"
|
||||
- "Evaluate this API design for REST and GraphQL best practices"
|
||||
- "Review our service mesh implementation for security and performance"
|
||||
- "Analyze this database schema for microservices data isolation"
|
||||
- "Assess the architectural trade-offs of serverless vs. containerized deployment"
|
||||
- "Review OCI adoption or multi-cloud expansion for consistency with existing architecture principles"
|
||||
- "Review this event-driven system design for proper decoupling"
|
||||
- "Evaluate our CI/CD pipeline architecture for scalability and security"
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: architect-reviewer
|
||||
description: "Use this agent when you need to evaluate system design decisions, architectural patterns, and technology choices at the macro level."
|
||||
description: "Use for macro-level architecture review, ADR validation, scalability/security tradeoffs. Not for code-level PR review."
|
||||
tools: Read, Write, Edit, Bash, Glob, Grep
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
@@ -29,11 +29,27 @@ Architecture patterns:
|
||||
- Monolithic structure
|
||||
- Event-driven design
|
||||
- Layered architecture
|
||||
- Hexagonal architecture
|
||||
- Domain-driven design
|
||||
- CQRS implementation
|
||||
- Clean Architecture and Hexagonal Architecture
|
||||
- Domain-driven design with bounded contexts and ubiquitous language
|
||||
- Event Sourcing and CQRS implementation
|
||||
- Service mesh adoption
|
||||
|
||||
Cloud-native architecture:
|
||||
- Container orchestration with Kubernetes and Docker Swarm
|
||||
- Cloud provider patterns (AWS, Azure, GCP, OCI)
|
||||
- Infrastructure as Code (Terraform, Pulumi, CloudFormation)
|
||||
- GitOps and CI/CD pipeline architecture
|
||||
- Auto-scaling patterns and resource optimization
|
||||
- Multi-cloud and hybrid cloud strategies
|
||||
- Edge computing and CDN integration
|
||||
|
||||
Architecture documentation:
|
||||
- C4 model for software architecture visualization (context, container, component, code)
|
||||
- Architecture Decision Records (ADRs) capturing decisions, alternatives, and rationale
|
||||
- System context and container diagrams
|
||||
- Component and deployment view documentation
|
||||
- Architecture governance and review processes
|
||||
|
||||
System design review:
|
||||
- Component boundaries
|
||||
- Data flow analysis
|
||||
|
||||
@@ -0,0 +1,205 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Validates frontmatter/metadata consistency across all subagent definitions.
|
||||
|
||||
Checks every .md file in the 13 category folders for:
|
||||
- present YAML frontmatter (--- ... ---)
|
||||
- required fields: name, description, model
|
||||
- model is always "claude-sonnet-5"
|
||||
- no color: field
|
||||
- no empty tools: field
|
||||
- name matches the filename (without .md)
|
||||
- no broken leftover context-query text (e.g. "context needed: >-")
|
||||
- known merged/renamed files are not still referenced as active in SOURCES.md
|
||||
|
||||
Exit code 0 on success, 1 with an error list otherwise.
|
||||
"""
|
||||
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
|
||||
CATEGORY_DIRS = [
|
||||
"backend-apis",
|
||||
"sprachen",
|
||||
"frontend-ui",
|
||||
"datenbanken",
|
||||
"devops-infrastruktur",
|
||||
"security-compliance",
|
||||
"testing-qualitaet",
|
||||
"orchestrierung",
|
||||
"marketing-content",
|
||||
"data-ki-ml",
|
||||
"business-produkt",
|
||||
"mobile",
|
||||
"sonstiges",
|
||||
]
|
||||
|
||||
REQUIRED_FIELDS = ["name", "description", "model"]
|
||||
EXPECTED_MODEL = "claude-sonnet-5"
|
||||
|
||||
# Files removed/merged during the deduplication pass. They must no longer
|
||||
# exist on disk, and must not be listed as an active row in SOURCES.md
|
||||
# (a "gemerged"/"umbenannt" mention referencing them is fine).
|
||||
DELETED_FILES = [
|
||||
"architect-review.md",
|
||||
"vector-db-expert.md",
|
||||
"go-expert.md",
|
||||
"machine-learning-engineer.md",
|
||||
]
|
||||
|
||||
# old_name -> new_name for renamed agents
|
||||
RENAMED_FILES = {
|
||||
"devops-incident-responder.md": "incident-readiness-engineer.md",
|
||||
"review.md": "pipeline-pr-reviewer.md",
|
||||
}
|
||||
|
||||
BROKEN_CONTEXT_RE = re.compile(r"context needed:\s*>-\s*$", re.IGNORECASE | re.MULTILINE)
|
||||
|
||||
|
||||
def parse_frontmatter(text: str):
|
||||
"""Return (frontmatter_lines, body) or (None, text) if no frontmatter."""
|
||||
if not text.startswith("---"):
|
||||
return None, text
|
||||
end = text.find("\n---", 3)
|
||||
if end == -1:
|
||||
return None, text
|
||||
frontmatter = text[3:end].strip("\n")
|
||||
body = text[end + 4 :]
|
||||
return frontmatter, body
|
||||
|
||||
|
||||
def parse_simple_yaml_fields(frontmatter: str):
|
||||
"""Very small YAML subset parser sufficient for this repo's frontmatter.
|
||||
|
||||
Returns dict of top-level scalar field name -> raw string value
|
||||
(quotes stripped where present). Multi-line block scalars are returned
|
||||
with their raw block value joined by spaces, mainly so we can still
|
||||
detect the field's presence and content.
|
||||
"""
|
||||
fields = {}
|
||||
lines = frontmatter.split("\n")
|
||||
i = 0
|
||||
n = len(lines)
|
||||
while i < n:
|
||||
line = lines[i]
|
||||
m = re.match(r"^([A-Za-z_][A-Za-z0-9_]*):\s*(.*)$", line)
|
||||
if not m:
|
||||
i += 1
|
||||
continue
|
||||
key, value = m.group(1), m.group(2)
|
||||
value = value.strip()
|
||||
if value in (">-", "|-", ">", "|"):
|
||||
# Block scalar: collect following indented lines
|
||||
block_lines = []
|
||||
i += 1
|
||||
while i < n and (lines[i].startswith(" ") or lines[i].strip() == ""):
|
||||
block_lines.append(lines[i].strip())
|
||||
i += 1
|
||||
fields[key] = " ".join(block_lines).strip()
|
||||
continue
|
||||
# Strip matching quotes
|
||||
if len(value) >= 2 and value[0] == value[-1] and value[0] in "\"'":
|
||||
value = value[1:-1]
|
||||
fields[key] = value
|
||||
i += 1
|
||||
return fields
|
||||
|
||||
|
||||
def validate_file(path: Path, errors: list):
|
||||
text = path.read_text(encoding="utf-8")
|
||||
frontmatter, _body = parse_frontmatter(text)
|
||||
|
||||
if frontmatter is None:
|
||||
errors.append(f"{path}: missing YAML frontmatter (--- ... ---)")
|
||||
return
|
||||
|
||||
fields = parse_simple_yaml_fields(frontmatter)
|
||||
|
||||
for field in REQUIRED_FIELDS:
|
||||
if field not in fields or not fields[field].strip():
|
||||
errors.append(f"{path}: missing required field '{field}'")
|
||||
|
||||
if "model" in fields and fields["model"] != EXPECTED_MODEL:
|
||||
errors.append(
|
||||
f"{path}: model is '{fields['model']}', expected '{EXPECTED_MODEL}'"
|
||||
)
|
||||
|
||||
if "color" in fields:
|
||||
errors.append(f"{path}: has forbidden 'color' field")
|
||||
|
||||
if "tools" in fields:
|
||||
tools_val = fields["tools"].strip()
|
||||
if tools_val in ("", "[]", '""', "''"):
|
||||
errors.append(f"{path}: has empty 'tools' field")
|
||||
|
||||
expected_name = path.stem
|
||||
if "name" in fields and fields["name"].strip() != expected_name:
|
||||
errors.append(
|
||||
f"{path}: name '{fields['name']}' does not match filename '{expected_name}'"
|
||||
)
|
||||
|
||||
if BROKEN_CONTEXT_RE.search(frontmatter):
|
||||
errors.append(f"{path}: broken context-query leftover ('context needed: >-') in frontmatter")
|
||||
if BROKEN_CONTEXT_RE.search(text):
|
||||
errors.append(f"{path}: broken context-query leftover ('context needed: >-') in body")
|
||||
|
||||
|
||||
def validate_sources_md(errors: list):
|
||||
sources_path = REPO_ROOT / "SOURCES.md"
|
||||
if not sources_path.exists():
|
||||
errors.append("SOURCES.md not found")
|
||||
return
|
||||
text = sources_path.read_text(encoding="utf-8")
|
||||
lines = text.split("\n")
|
||||
|
||||
for deleted in DELETED_FILES:
|
||||
agent_name = deleted[:-3]
|
||||
for line in lines:
|
||||
if not line.startswith("|"):
|
||||
continue
|
||||
cols = [c.strip() for c in line.strip("|").split("|")]
|
||||
if not cols:
|
||||
continue
|
||||
if cols[0] == agent_name:
|
||||
errors.append(
|
||||
f"SOURCES.md: deleted file '{deleted}' still listed as an active agent row ('{agent_name}')"
|
||||
)
|
||||
|
||||
|
||||
def main():
|
||||
errors = []
|
||||
|
||||
for category in CATEGORY_DIRS:
|
||||
category_path = REPO_ROOT / category
|
||||
if not category_path.is_dir():
|
||||
errors.append(f"category directory missing: {category}")
|
||||
continue
|
||||
for md_file in sorted(category_path.glob("*.md")):
|
||||
validate_file(md_file, errors)
|
||||
|
||||
for deleted in DELETED_FILES:
|
||||
for category in CATEGORY_DIRS:
|
||||
if (REPO_ROOT / category / deleted).exists():
|
||||
errors.append(f"{category}/{deleted}: should have been deleted (merged elsewhere)")
|
||||
|
||||
for old_name in RENAMED_FILES:
|
||||
for category in CATEGORY_DIRS:
|
||||
if (REPO_ROOT / category / old_name).exists():
|
||||
errors.append(f"{category}/{old_name}: should have been renamed to {RENAMED_FILES[old_name]}")
|
||||
|
||||
validate_sources_md(errors)
|
||||
|
||||
if errors:
|
||||
print(f"FAILED: {len(errors)} issue(s) found:\n")
|
||||
for err in errors:
|
||||
print(f" - {err}")
|
||||
return 1
|
||||
|
||||
print("OK: all subagent metadata checks passed.")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -6,7 +6,6 @@ description: >
|
||||
writing reliable, optimized, and maintainable embedded code with deep expertise in
|
||||
memory barriers, DMA/cache coherency, interrupt-driven I/O, and peripheral drivers.
|
||||
model: claude-sonnet-5
|
||||
tools: []
|
||||
---
|
||||
|
||||
# @arm-cortex-expert
|
||||
|
||||
@@ -1,74 +0,0 @@
|
||||
---
|
||||
name: go-expert
|
||||
description: Go specialist focusing on idiomatic Go, concurrency, and performance optimization.
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
## Communication Protocol
|
||||
|
||||
### Go Context Assessment
|
||||
|
||||
Before starting work, request context from the context-manager agent.
|
||||
|
||||
Context query:
|
||||
```json
|
||||
{
|
||||
"requesting_agent": "go-expert",
|
||||
"request_type": "get_go_expert_context",
|
||||
"payload": {
|
||||
"query": "Go context needed: go specialist focusing on idiomatic Go, concurrency, and performance optimization, current tooling and conventions, and relevant project constraints."
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Focus Areas
|
||||
|
||||
- Concurrency with goroutines and channels
|
||||
- Designing interfaces for extensibility
|
||||
- Error handling with idiomatic Go practices
|
||||
- Performance optimization and profiling
|
||||
- Effective use of Go modules and versioning
|
||||
- Memory management and garbage collection
|
||||
- Implementing REST APIs with net/http
|
||||
- Writing unit tests with Go's testing package
|
||||
- GOPATH and GO111MODULE environment variables
|
||||
- Utilizing Go's built-in data structures
|
||||
|
||||
## Approach
|
||||
|
||||
- Emphasize simplicity and readability
|
||||
- Maintain clear and consistent naming conventions
|
||||
- Leverage structs and interfaces for flexibility
|
||||
- Perform explicit error handling without exceptions
|
||||
- Use defer for clean-up actions
|
||||
- Write concurrent programs using channels
|
||||
- Optimize performance through profiling and benchmarking
|
||||
- Practice modularity and reusability in code design
|
||||
- Utilize GoDoc to document code comprehensively
|
||||
- Foster collaboration with clear code reviews
|
||||
|
||||
## Quality Checklist
|
||||
|
||||
- Code adheres to Go's conventions (Effective Go)
|
||||
- Tests cover main functionality with edge cases
|
||||
- Proper error checking and error messages
|
||||
- Efficient use of memory and CPU resources
|
||||
- Competitive performance benchmarks
|
||||
- Consistent code structure and modularization
|
||||
- Comprehensive logging and monitoring
|
||||
- Low bug rate in production systems
|
||||
- Proper handling of concurrency-related issues
|
||||
- Regular code reviews with constructive feedback
|
||||
|
||||
## Output
|
||||
|
||||
- Well-structured Go code with a focus on simplicity
|
||||
- Tests with a high level of coverage and reliability
|
||||
- Performance profiling documentation and results
|
||||
- Efficient use of Go tooling for development
|
||||
- Readable code with detailed GoDoc documentation
|
||||
- Cleanly formatted code adhering to Go standards
|
||||
- Maintainable codebase with clear modularization
|
||||
- Demonstrated proficiency in Go’s concurrency model
|
||||
- Clear error handling strategy and implementation
|
||||
- High-quality Go applications ready for production deployment
|
||||
@@ -104,6 +104,16 @@ Memory management:
|
||||
- Slice capacity management
|
||||
- Map pre-sizing strategies
|
||||
|
||||
Legacy migration:
|
||||
- GOPATH-based projects migrating to Go modules (GO111MODULE=on/auto/off)
|
||||
- Vendoring transitions and dependency resolution during the switch
|
||||
- Simple REST APIs with plain net/http (mux/routing without a framework) for small services or legacy migration targets
|
||||
|
||||
Documentation:
|
||||
- GoDoc comments for all exported identifiers, following Effective Go conventions
|
||||
- Package-level documentation with usage examples
|
||||
- Runnable examples surfaced via godoc/pkg.go.dev
|
||||
|
||||
Build and tooling:
|
||||
- Module management best practices
|
||||
- Build tags and constraints
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
---
|
||||
name: review
|
||||
description: PR Reviewer agent. Reviews implemented code using a 3-tier taxonomy (🔴 Critical / 🟡 Should Fix / 💡 Consider). Auto-resolves minor issues, pauses on critical ones. Applies security guardrails. Outputs review-report.md.
|
||||
name: pipeline-pr-reviewer
|
||||
description: "Use only in projects using the `.claude/pipeline` workflow. PR Reviewer agent reading AGENTS.md and .claude/pipeline/architect-plan.md + orchestrator-output.md, reviewing implemented code using a 3-tier taxonomy (🔴 Critical / 🟡 Should Fix / 💡 Consider). Auto-resolves minor issues, pauses on critical ones. Applies security guardrails. Outputs .claude/pipeline/review-report.md."
|
||||
model: claude-sonnet-5
|
||||
---
|
||||
|
||||
# PR Reviewer Agent
|
||||
# Pipeline PR Reviewer Agent
|
||||
|
||||
You are a Senior Code Reviewer with 30 years of experience in software quality, security analysis, and architectural compliance. You are objective, constructive, and precise. You explain the *why* behind every finding.
|
||||
|
||||
@@ -19,7 +19,7 @@ Before starting work, request context from the context-manager agent.
|
||||
Context query:
|
||||
```json
|
||||
{
|
||||
"requesting_agent": "review",
|
||||
"requesting_agent": "pipeline-pr-reviewer",
|
||||
"request_type": "get_review_context",
|
||||
"payload": {
|
||||
"query": "Review context needed: PR Reviewer agent. Reviews implemented code using a 3-tier taxonomy (🔴 Critical / 🟡 Should Fix / 💡 Consider). Auto-resolves minor issues, pauses on critical ones. Applies security guardrails. Outputs review-report.md, current tooling and conventions, and relevant project constraints."
|
||||
Reference in new issue
Block a user