NBA Live Data Skill for Openclaw

A high-performance NBA data skill that provides real-time scores, schedules, and conference standings directly from official CDN and StatMuse sources.

goog
v1.0.2
Mar 31, 2026
0
920
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install nba

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install nba using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is NBA Live Data Skill?

The NBA Live Data Skill is a specialized tool designed for the Openclaw Skills ecosystem to provide developers and users with instant access to the professional basketball landscape. By leveraging official NBA CDN endpoints and StatMuse data, this skill enables AI agents to report on live game statuses, final results, and detailed conference rankings without the need for complex API keys or authenticated third-party services.

Built with a focus on reliability and speed, the skill utilizes Python's standard library to fetch and parse game metadata, including period clocks, individual game leaders, and home/away records. It is an essential addition for any workspace requiring real-time sports updates or automated basketball data retrieval.

NBA Live Data Skill Use Cases

  • Tracking live NBA scores and game progress (quarter/clock) during the regular season and playoffs.
  • Checking current Eastern and Western Conference standings to analyze playoff seeding.
  • Automating daily game schedule summaries for sports-focused AI agents.
  • Verifying game leaders in points, rebounds, and assists for active matchups.

How NBA Live Data Skill Works

  1. The skill executes a Python script that targets the NBA CDN scoreboard JSON for real-time game data.
  2. It concurrently scrapes StatMuse HTML tables to retrieve the latest win/loss records and winning percentages for both conferences.
  3. The raw data is processed to extract game IDs, status (upcoming, live, or final), and team statistics.
  4. Timestamps are converted from UTC to the local system timezone to ensure accuracy for the end user.
  5. A clean, formatted summary is returned, with optional deep-links to box scores on official NBA platforms.

NBA Live Data Skill Setup

To integrate this into your environment, ensure you have Python 3.x installed. No external dependencies are required as it uses the standard library.

# Navigate to the skill directory
cd skills/nba

# Run the data fetcher for all data (scores and standings)
python3 scripts/nba_data.py all

# For Windows users, set the encoding before running
set PYTHONIOENCODING=utf-8
python scripts/nba_data.py all

NBA Live Data Skill Data Schema & Taxonomy

The skill organizes basketball data into two primary streams. This structure is part of the broader Openclaw Skills data standard for sports telemetry:

Component Data Points Captured
Scoreboard Game ID, Home/Away Score, Period, Clock, Top Performers (PTS/REB/AST)
Standings Rank, Team Name, Wins, Losses, Win %, Home/Away Record
Metadata Game Status (Pre/Live/Final), UTC Start Times, Broadcast Info

NBA Live Data Skill Advanced Features

  • Multi-source data aggregation combining JSON APIs and HTML scraping for maximum data coverage.
  • Automatic timezone conversion to provide localized game start times for users globally.
  • Zero-dependency architecture ensuring the skill remains lightweight and easy to deploy within Openclaw Skills environments.
  • Direct deep-linking capabilities to NBA.com box scores and StatMuse historical queries for advanced statistical analysis.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*