Data & AI Skills

Data & AI

Prompt engineering best practices and templates to maximize AI outputs.

Data & AI

Generates data visualizations and charts tailored to your data.

Data & AI

Setup guide for RAG (Retrieval-Augmented Generation) architectures.

Data & AI

Generates ETL/ELT configurations and robust data pipeline architectures.

Data & AI

Document and track your machine learning experiments in a structured way.

Data & AI

Generates matplotlib figure code following project conventions for publication-ready figures.

Data & AI

Fast, calibration-free weight quantization for LLMs with multiple backends. Supports 8/4/3/2/1-bit precision and integrates with HuggingFace and vLLM.

Data & AI

Implements real-time streaming transcription using Deepgram's WebSocket API. Use when building live transcription, voice interfaces, or real-time audio processing applications. Handles WebSocket connections, interim results, and audio data streaming.

Data & AI

figforge: full source-to-image pipeline to analyze papers, repos, algorithms and generate publication-quality figures.

Data & AI

Proficiency in creating various chart types (bar, line, pie, heatmap, scatter) using pyecharts and generating self-contained HTML reports. Includes theme configuration, number formatting, troubleshooting common issues (chart size, label overlapping), and critical data conversion to Python lists for browser rendering.

Data & AI

Automates the adaptation of pre-trained models using transfer learning, including fine-tuning, data validation, and performance optimization. Helps when fine-tuning a model on a new dataset or adapting it for a specific task.

Data & AI

Reads documents and splits them into manageable chunks based on line count, character size, markdown sections, or paragraphs. Supports overlapping chunks to maintain context. Useful for processing large files, analysis, or transfer tasks.