mirror of
https://github.com/wshobson/agents.git
synced 2026-03-18 17:47:16 +00:00
d2f3886ae1
Repository Restructure: - Move all 83 agent .md files to agents/ subdirectory - Add 15 workflow orchestrators from commands repo to workflows/ - Add 42 development tools from commands repo to tools/ - Update README for unified repository structure The commands repository functionality is now fully integrated, providing complete workflow orchestration and development tooling alongside agents. Directory Structure: - agents/ - 83 specialized AI agents - workflows/ - 15 multi-agent orchestration commands - tools/ - 42 focused development utilities No breaking changes to agent functionality - all agents remain accessible with same names and behavior. Adds workflow and tool commands for enhanced multi-agent coordination capabilities.
1.6 KiB
1.6 KiB
model
| model |
|---|
| claude-sonnet-4-0 |
AI/ML Code Review
Perform a specialized AI/ML code review for: $ARGUMENTS
Conduct comprehensive review focusing on:
-
Model Code Quality:
- Reproducibility checks
- Random seed management
- Data leakage detection
- Train/test split validation
- Feature engineering clarity
-
AI Best Practices:
- Prompt injection prevention
- Token limit handling
- Cost optimization
- Fallback strategies
- Timeout management
-
Data Handling:
- Privacy compliance (PII handling)
- Data versioning
- Preprocessing consistency
- Batch processing efficiency
- Memory optimization
-
Model Management:
- Version control for models
- A/B testing setup
- Rollback capabilities
- Performance benchmarks
- Drift detection
-
LLM-Specific Checks:
- Context window management
- Prompt template security
- Response validation
- Streaming implementation
- Rate limit handling
-
Vector Database Review:
- Embedding consistency
- Index optimization
- Query performance
- Metadata management
- Backup strategies
-
Production Readiness:
- GPU/CPU optimization
- Batching strategies
- Caching implementation
- Monitoring hooks
- Error recovery
-
Testing Coverage:
- Unit tests for preprocessing
- Integration tests for pipelines
- Model performance tests
- Edge case handling
- Mocked LLM responses
Provide specific recommendations with severity levels (Critical/High/Medium/Low). Include code examples for improvements and links to relevant best practices.