simpo-training
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
context-health
Use when validating or diagnosing the cortex environment (consistency, duplicates, redundancy, optimization) - provides a diagnostic workflow and reporting structure for context health checks.
proof-weighted-optimization
Optimize decisions using proof-weighted scoring.
optimize-prompt-gepa
Optimizes prompts using full GEPA methodology (Genetic-Pareto Evolution). Use when user wants to improve a prompt's accuracy on test cases, mentions "optimize prompt", "improve prompt", or has examples of desired input/output pairs. Implements Pareto frontier selection, trace-based reflection, and crossover mutations.
fullstack-security
Security and performance - hardening, optimization, auditing
database-integration
Database integration - schema design, queries, migrations, optimization
prompt-engineering
Prompt design, optimization, few-shot learning, and chain of thought techniques for LLM applications.
algorithms
Master algorithm design, common patterns, optimization techniques, and problem-solving strategies. Learn to solve any computational challenge efficiently.
docker-optimization
Optimize Docker images and containers for size, build speed, and runtime performance
Python Performance
Master Python optimization techniques, profiling, memory management, and high-performance computing
rust-performance
Master Rust performance - profiling, benchmarking, and optimization
algorithms
>
dynamic-programming
Master DP patterns with complete implementations for memoization, tabulation, and state design with production-ready solutions.
mongodb-indexing-optimization
Master MongoDB indexing and query optimization. Learn index types, explain plans, performance tuning, and query analysis. Use when optimizing slow queries, analyzing performance, or designing indexes.
dspy-haystack-integration
Integrate DSPy optimization with existing Haystack pipelines
r3f-performance
R3F performance optimization—LOD (Level of Detail), frustum culling, instancing strategies, draw call reduction, frame budgets, lazy loading, and profiling tools. Use when optimizing render performance, handling large scenes, or debugging frame rate issues.
