Skill Claude CodeCodex
Create balanced benchmark datasets with labels, splits, and negative examples.
127 1mo ago A 17 tokens
original MIT
Skill Claude CodeCodex
Cluster failures and explain model or router error patterns.
127 1mo ago A 13 tokens
original MIT
Skill Claude CodeCodex
Design benchmark suites with metrics, splits, and robustness diagnostics.
127 1mo ago A 16 tokens
original MIT
Skill Claude CodeCodex
Design judge rubrics and analyze model-graded evaluation outputs.
127 1mo ago A 17 tokens
original MIT
Skill Claude CodeCodex
Profile GPU memory, kernels, and throughput for ML workloads.
127 1mo ago A 16 tokens
original MIT
Skill Claude CodeCodex
Plan and run multi-GPU training jobs for model adaptation.
127 1mo ago A 15 tokens
original MIT
Skill Claude CodeCodex
Create CI workflows that run tests and package checks.
127 1mo ago A 14 tokens
original MIT
Skill Claude CodeCodex
Serve local or remote ML models behind inference endpoints.
127 1mo ago A 13 tokens
original MIT
Skill Claude CodeCodex
Instrument systems with logs, counters, metrics, and latency traces.
127 1mo ago A 16 tokens
original MIT
Skill Claude CodeCodex
Package Python projects with optional dependencies and console scripts.
127 1mo ago A 13 tokens
original MIT
Docker
59Skill Claude CodeCodex
Package applications and model evaluation jobs into reproducible containers.
127 1mo ago A 13 tokens
original MIT
MLflow
60Skill Claude CodeCodex
Track, compare, and package machine learning experiment runs with MLflow.
127 1mo ago A 17 tokens
original MIT