Nba Data

Pulls live NBA data from ESPN's public endpoints without any API keys or authentication. Covers everything from basic scores and standings to detailed play-by-play, win probability charts, injury reports, transactions, and depth charts. The skill automatically handles season detection based on the current date, which is helpful since the NBA season spans two calendar years. Commands are straightforward CLI calls, and the documentation explicitly lists non-existent commands to prevent hallucination. Best for building NBA dashboards, game recaps, or anything that needs fresh basketball data without dealing with rate limits or credentials. Published by machina-sports, who also maintain WNBA and college basketball versions.

skills.sh installs: 1K
GitHub stars: 268
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add machina-sports/sports-skills --skill nba-data --agent claude-code

Installs into .claude/skills of the current project.

Files

NBA Data

Before writing queries, consult references/api-reference.md for endpoints, ID conventions, and data shapes.

Setup

Before first use, check if the CLI is available:

which sports-skills || pip install sports-skills

If pip install fails with a Python version error, the package requires Python 3.10+. Find a compatible Python:

python3 --version  # check version
# If < 3.10, try: python3.12 -m pip install sports-skills
# On macOS with Homebrew: /opt/homebrew/bin/python3.12 -m pip install sports-skills

No API keys required.

Quick Start

Prefer the CLI — it avoids Python import path issues:

sports-skills nba get_scoreboard
sports-skills nba get_standings --season=2025
sports-skills nba get_teams

CRITICAL: Before Any Query

CRITICAL: Before calling any data endpoint, verify:

For the current season, omit season/season_year on ESPN commands — never hardcode one.
If only a team name is provided, call get_teams to resolve the team ID before using team-specific commands.