Danh Hoàng Hiếu Nghị
Community@ihatesea69 · Ho Chi Minh City
I turn ideas into scalable AI systems with high ROI - GenAIOps - GenAI Security Engineer-
Agent Skills by Danh Hoàng Hiếu Nghị
Showing 114 vetted skills indexed across 1 GitHub repositories.
ihatesea69illustration-generator
Generate prompts for hand-drawn infographic-style illustrations for dev.to articles.
ihatesea69thumbnail-generator
Generate AI image prompts for dev.to blog post thumbnails.
ihatesea69blog-writer
Generate SEO-optimized technical blog posts with YAML frontmatter for dev.to.
ihatesea69hugging-face-tool-builder
Generate shell, Python, or TSX scripts for Hugging Face API workflows.
ihatesea69hugging-face-evaluation
Manage structured evaluation results in Hugging Face model cards.
ihatesea69hugging-face-datasets
Manage Hugging Face datasets with SQL queries via DuckDB and hf:// protocol.
ihatesea69hugging-face-cli
Manage Hugging Face Hub repositories, uploads/downloads, cache and cloud jobs via hf CLI.
ihatesea69hugging-face-trackio
Log ML training metrics via Python API and retrieve them via CLI.
ihatesea69hugging-face-jobs
Execute Python workloads on Hugging Face Jobs with CPU, GPU, or TPU hardware.
ihatesea69hugging-face-paper-publisher
Index arXiv papers onto Hugging Face Paper Pages and link models.
ihatesea69hugging-face-model-trainer
Train and fine-tune language models with TRL on Hugging Face Jobs.
ihatesea69ml-paper-writing
Draft Machine Learning and AI papers with LaTeX templates and citation verification.
ihatesea69serving-llms-vllm
Serve LLMs with vLLM PagedAttention and continuous batching.
ihatesea69tensorrt-llm
Optimize LLM inference on NVIDIA GPUs with TensorRT-LLM quantization and batching.
ihatesea69sglang
Serve LLMs with RadixAttention prefix caching and constrained decoding.
ihatesea69llama-cpp
Run GGUF quantized LLM inference on CPU, Apple Silicon, and consumer GPUs.
ihatesea69lambda-labs-gpu-cloud
Provision on-demand and reserved NVIDIA GPU cloud instances for ML training and inference.
ihatesea69skypilot-multi-cloud-orchestration
Orchestrate machine learning workloads across multiple cloud providers with cost optimization and spot instance recovery.
ihatesea69modal-serverless-gpu
Deploy machine learning models as auto-scaling serverless GPU APIs.
ihatesea69nemo-curator
Curate multimodal LLM training datasets with GPU-accelerated deduplication and filtering.
ihatesea69ray-data
Process large datasets with distributed Ray Data pipelines for ML workloads.
ihatesea69dspy
Develop AI systems with declarative programming and automatic prompt optimization in DSPy.
ihatesea69guidance
Generate structured JSON or XML outputs using Pythonic syntax, regex, and grammars.
ihatesea69outlines
Enforce JSON, XML, and code output formats using Python.