Loading...
Loading...
Found 5 Skills
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, and Gemini backends with file references (@syntax) and structured output.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
Instructions for using the DeepBase multi-driver persistence library. Use when a task requires data persistence, storage abstraction, multi-backend setups, data migration between drivers, or integrating DeepBase into a Node.js project.
Keras high-level neural network API. Use for deep learning.
Manage backlog items across multiple backends (GitHub Issues, Linear, Beads). Configure task_management in .agents.yml.