What problem does it solve?
Users often struggle to understand what data has been captured, if pipelines are working correctly, or if data is missing between processing stages. This Skill provides clear, immediate visibility into the data artifact lifecycle, eliminating guesswork.
Core Features & Use Cases
- Scan & Summarize: Automatically scans artifact directories, counting games, players, and files for each sport and date.
- Pipeline Stage Analysis: Identifies which pipeline stages (raw, derived, packages) have data and highlights any gaps, such as data captured but not yet derived.
- Integrity Checks: Validates artifact integrity (e.g., corrupt JSON) and compares artifact counts against the database.
- Use Case: After a capture script runs, use this Skill to quickly verify that artifacts were created, check for missing data, or debug why data isn't showing up in the database.
Quick Start
Explore all artifacts
python .claude/skills/artifact-explorer/scripts/explore_artifacts.py
Check NBA artifacts for a specific date
python .claude/skills/artifact-explorer/scripts/explore_artifacts.py --sport nba --date 2025-10-22