data-formats

What problem does it solve?

Many datasets and files come in unknown or mixed formats which makes ingestion, analysis, and model loading error-prone and time-consuming; this Skill provides practical detection and parsing guidance to reliably identify and handle binary, structured text, model checkpoints, and multi-file datasets.

Core Features & Use Cases

• Format detection techniques: Inspect magic bytes, MIME type, hexdumps, and small binary samples to identify file types.
• Structured text handling: Delimiters and schema inference for CSV/TSV, safe JSON/YAML/TOML/XML parsing and encoding checks.
• Model & database files: Recognize common ML checkpoints and SQLite files and recommend safe loading approaches.
• Large and multi-file datasets: Sampling strategies, manifest discovery, and incremental processing patterns for scalable workflows.

Quick Start

Analyze the attached file, determine its format using magic bytes and a quick hexdump, and recommend a safe, step-by-step parsing approach.