Add new skills for backend patterns, coding standards, continuous learning, and NestJS best practices
- Introduced backend patterns skill with guidelines on API design, database optimization, and server-side best practices. - Added coding standards skill outlining universal coding principles for TypeScript, NestJS, and Node.js development. - Implemented continuous learning skill to automatically extract reusable patterns from Cursor sessions. - Created NestJS best practices skill detailing architecture patterns, dependency injection, error handling, and security measures. - Included various rules and templates for NestJS best practices to ensure production-ready applications.
This commit is contained in:
@@ -0,0 +1,52 @@
|
||||
---
|
||||
description: Model selection, context window management, and build troubleshooting
|
||||
alwaysApply: true
|
||||
---
|
||||
|
||||
# Performance Optimization
|
||||
|
||||
## Model Selection Strategy
|
||||
|
||||
**Haiku 4.5** (90% of Sonnet capability, 3x cost savings):
|
||||
- Lightweight agents with frequent invocation
|
||||
- Pair programming and code generation
|
||||
- Worker agents in multi-agent systems
|
||||
|
||||
**Sonnet 4.5** (Best coding model):
|
||||
- Main development work
|
||||
- Orchestrating multi-agent workflows
|
||||
- Complex coding tasks
|
||||
|
||||
**Opus 4.5** (Deepest reasoning):
|
||||
- Complex architectural decisions
|
||||
- Maximum reasoning requirements
|
||||
- Research and analysis tasks
|
||||
|
||||
## Context Window Management
|
||||
|
||||
Avoid last 20% of context window for:
|
||||
- Large-scale refactoring
|
||||
- Feature implementation spanning multiple files
|
||||
- Debugging complex interactions
|
||||
|
||||
Lower context sensitivity tasks:
|
||||
- Single-file edits
|
||||
- Independent utility creation
|
||||
- Documentation updates
|
||||
- Simple bug fixes
|
||||
|
||||
## Ultrathink + Plan Mode
|
||||
|
||||
For complex tasks requiring deep reasoning:
|
||||
1. Use `ultrathink` for enhanced thinking
|
||||
2. Enable **Plan Mode** for structured approach
|
||||
3. "Rev the engine" with multiple critique rounds
|
||||
4. Use split role sub-agents for diverse analysis
|
||||
|
||||
## Build Troubleshooting
|
||||
|
||||
If build fails:
|
||||
1. Use **build-error-resolver** agent
|
||||
2. Analyze error messages
|
||||
3. Fix incrementally
|
||||
4. Verify after each fix
|
||||
Reference in New Issue
Block a user