Explore skills

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trig

Optimizes database queries and improves performance across PostgreSQL and MySQL systems. Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for index design, query rewrites, configuration tuning, partitioning strategies, lock contention resolution.

Use when building high-performance async Python APIs with FastAPI and Pydantic V2. Invoke to create REST endpoints, define Pydantic models, implement authentication flows, set up async SQLAlchemy database operations, add JWT authentication, build WebSocket endpoints, or generate OpenAPI documentation. Trigger terms: FastAPI, Pydantic, async Python, Python API, REST API Python, SQLAlchemy async, JW

Optimizes SQL queries, designs database schemas, and troubleshoots performance issues. Use when a user asks why their query is slow, needs help writing complex joins or aggregations, mentions database performance issues, or wants to design or migrate a schema. Invoke for complex queries, window functions, CTEs, indexing strategies, query plan analysis, covering index creation, recursive queries, E

Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation tasks such as joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type con

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

Scalable data processing for ML workloads with streaming execution across CPU/GPU, supporting various formats like Parquet/CSV/JSON/images. It integrates with Ray Train, PyTorch, and TensorFlow, scaling from a single machine to hundreds of nodes for tasks like batch inference, data preprocessing, and distributed ETL.

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

Generates publication-quality figures for ML papers, extracting system components for architecture diagrams via Gemini and creating data-driven figures via matplotlib/seaborn. Use for any conference paper figure.

This skill enables fine-tuning and serving Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch for robot policy inference across ALOHA, DROID, and LIBERO environments. It's useful for adapting models to custom datasets, converting checkpoints, running inference servers, or debugging.

WebGL fluid displacement background with overlaid golden phrases at the top, suitable for video intros, landing page hero sections, or posters.

Logo entrance with block assembly, a glowing bloom effect, and tagline reveal, suitable for video outros or brand closings.