Nfl Data

NFL 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 (package not found or Python version error), install from GitHub:

pip install git+https://github.com/machina-sports/sports-skills.git

The package requires Python 3.10+. If your default Python is older, use a specific version:

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.

For nflverse-backed commands (get_nflverse_*), install the NFL extra:

pip install sports-skills[nfl]

This installs nfl-data-py (or use nflreadpy if preferred). Parquet support (pyarrow) is also needed for most nflverse data beyond schedules.

Quick Start

Prefer the CLI — it avoids Python import path issues:

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

Python SDK (alternative):

from sports_skills import nfl

scores = nfl.get_scoreboard({})
standings = nfl.get_standings({"params": {"season": "2025"}})

CRITICAL: Before Any Query

CRITICAL: Before calling any data endpoint, verify:

• Season year is derived from the system prompt's currentDate — never hardcoded.
• If only a team name is provided, call get_teams to resolve the team ID before using team-specific commands.

Choosing the Season

Derive the current year from the system prompt's date (e.g., currentDate: 2026-02-16 → current year is 2026).

• If the user specifies a season, use it as-is.
• If the user says "current", "this season", or doesn't specify: The NFL season runs September–February. If the current month is March–August, use season = current_year (upcoming season). If September–February, the active season started in the previous calendar year if you're in Jan/Feb, otherwise current year.

Commands

See references/api-reference.md for full parameter lists and return shapes.

Examples

Example 1: Today's scores User says: "What are today's NFL scores?" Actions: 1. Call get_scoreboard() Result: All live and recent NFL games with scores and status

Example 2: Conference standings User says: "Show me the AFC standings" Actions: 1. Derive season year from currentDate 2. Call get_standings(season=<derived_year>) 3. Filter results for AFC conference Result: AFC standings table with W-L-T, PCT, PF, PA per team

Example 3: Team roster User says: "Who's on the Chiefs roster?" Actions: 1. Call get_team_roster(team_id="12") Result: Full Chiefs roster with name, position, jersey number, height, weight

Example 4: Super Bowl box score User says: "How did the Super Bowl go?" Actions: 1. Call get_schedule(week=23) to find the Super Bowl event_id 2. Call get_game_summary(event_id=<id>) for full box score Result: Complete box score with passing/rushing/receiving stats and scoring plays

Example 5: Injury report User says: "Who's injured on the Chiefs?" Actions: 1. Call get_injuries() 2. Filter results for Kansas City Chiefs (team_id=12) Result: Chiefs injury list with player name, position, status, and injury type

Example 6: Player statistics User says: "Show me Patrick Mahomes' stats this season" Actions: 1. Derive season year from currentDate 2. Call get_player_stats(player_id="3139477", season_year=<derived_year>) Result: Season stats by category with value, rank, and per-game averages

Example 7: nflverse weekly rosters User says: "Give me the Week 1 Chiefs roster from the data table backend" Actions: 1. Derive season year from currentDate 2. Call get_nflverse_weekly_rosters(season=<derived_year>, week=1, team="KC") Result: Weekly roster rows normalized for team, player, position, jersey, and status

Example 8: nflverse play-by-play User says: "Pull Bills Week 3 play-by-play" Actions: 1. Derive season year from currentDate 2. Call get_nflverse_play_by_play(season=<derived_year>, week=3, team="BUF") Result: Play rows with game_id, down/distance, description, EPA, WP/WPA, and score state

Commands that DO NOT exist — never call these

• ~~get_odds~~ / ~~get_betting_odds~~ — not available. For prediction market odds, use the polymarket or kalshi skill.
• ~~search_teams~~ — does not exist. Use get_teams instead.
• ~~get_box_score~~ — does not exist. Use get_game_summary instead.
• ~~get_player_ratings~~ — does not exist. Use get_player_stats instead.

If a command is not listed in the Commands table above, it does not exist.

Error Handling

When a command fails, do not surface raw errors to the user. Instead: 1. Catch silently and try alternatives 2. If team name given instead of ID, use get_teams to find the ID first 3. Only report failure with a clean message after exhausting alternatives

Troubleshooting

Error: sports-skills command not found Cause: Package not installed Solution: Run pip install sports-skills. If not on PyPI, install from GitHub: pip install git+https://github.com/machina-sports/sports-skills.git

Error: nflverse backend unavailable Cause: Optional NFL backend extra not installed Solution: Install sports-skills[nfl] so the nflverse provider (nflreadpy or compatibility fallback) is available

Error: Team not found by ID Cause: Wrong or outdated ESPN team ID used Solution: Call get_teams to get the current list of all 32 NFL teams with their IDs

Error: No data returned for a future game Cause: ESPN only returns data for completed or in-progress games Solution: Use get_schedule to see upcoming game details; get_scoreboard only covers active/recent games

Error: Postseason week number returns no results Cause: Postseason uses unified week numbers (19-23) that differ from regular season Solution: Use week 19 for Wild Card, 20 for Divisional, 21 for Conference Championship, 23 for Super Bowl

NFL Data — API Reference

Commands

get_scoreboard

Get live/recent NFL scores.

• date (str, optional): Date in YYYY-MM-DD format
• week (int, optional): Week number (1-18 regular season, 19-23 postseason)

Returns events[] with game info, scores, status, and competitors.

get_standings

Get NFL standings by conference and division.

• season (int, optional): Season year

Returns groups[] with AFC/NFC conferences, divisions, and team standings including W-L-T, PCT, PF, PA.

get_teams

Get all 32 NFL teams. No parameters.

Returns teams[] with id, name, abbreviation, logo, and location.

get_team_roster

Get full roster for a team.

• team_id (str, required): ESPN team ID (e.g., "12" for Chiefs)

Returns athletes[] with name, position, jersey number, height, weight, experience.

get_team_schedule

Get schedule for a specific team.

• team_id (str, required): ESPN team ID
• season (int, optional): Season year

Returns events[] with opponent, date, score (if played), and venue.

get_game_summary

Get detailed box score and scoring plays.

• event_id (str, required): ESPN event ID

Returns game_info, competitors, boxscore (passing/rushing/receiving stats), scoring_plays, and leaders.

get_leaders

Get NFL statistical leaders (passing, rushing, receiving).

• season (int, optional): Season year

Returns categories[] with leader rankings per stat category.

get_news

Get NFL news articles.

• team_id (str, optional): Filter by team

Returns articles[] with headline, description, published date, and link.

get_play_by_play

Get full play-by-play data for a game.

• event_id (str, required): ESPN event ID

Returns drives[] with play-by-play detail including down, distance, yard line, play description, and scoring plays.

get_win_probability

Get win probability chart data for a game.

• event_id (str, required): ESPN event ID

Returns timestamped home/away win probability percentages throughout the game.

get_schedule

Get NFL season schedule by week.

• season (int, optional): Season year
• week (int, optional): Week number (1-18 regular season, 19-23 postseason)

Returns events[] for the specified week/season.

get_injuries

Get current NFL injury reports across all teams. No parameters.

Returns teams[] with per-team injury lists including player name, position, status (Out/Doubtful/Questionable/Day-To-Day), injury type, and detail.

get_transactions

Get recent NFL transactions (trades, signings, waivers).

• limit (int, optional): Max transactions to return. Defaults to 50.

Returns transactions[] with date, team, and description.

get_futures

Get NFL futures/odds markets (Super Bowl winner, MVP, etc.).

• limit (int, optional): Max entries per market. Defaults to 25.
• season_year (int, optional): Season year. Defaults to current.

Returns futures[] with market name and entries (team/player name + odds value).

get_depth_chart

Get depth chart for a specific team.

• team_id (str, required): ESPN team ID

Returns charts[] with offense/defense/special teams positions and player depth order.

get_team_stats

Get full team statistical profile for a season.

• team_id (str, required): ESPN team ID
• season_year (int, optional): Season year. Defaults to current.
• season_type (int, optional): 1=preseason, 2=regular (default), 3=postseason.

Returns categories[] (Passing, Rushing, Receiving, etc.) with detailed stats including value, rank, and per-game averages.

get_player_stats

Get full player statistical profile for a season.

• player_id (str, required): ESPN athlete ID
• season_year (int, optional): Season year. Defaults to current.
• season_type (int, optional): 1=preseason, 2=regular (default), 3=postseason.

Returns categories[] with detailed stats including value, rank, and per-game averages.

get_nflverse_schedule

Get schedules/results through the nflverse backend.

• season (int, optional): Season year
• week (int, optional): NFL week filter

Returns events[] with game_id, teams, scores, date/time, line fields, and location.

get_nflverse_weekly_rosters

Get weekly roster snapshots through the nflverse backend.

• season (int, optional): Season year
• week (int, optional): NFL week filter
• team (str, optional): Team abbreviation filter (e.g. KC)

Returns players[] with normalized roster fields: team, player_id, player_name, position, jersey_number, status, college, and experience fields when available.

get_nflverse_player_stats

Get normalized nflverse player stat rows.

• season (int, optional): Season year
• player_id (str, optional): nflverse/GSIS player identifier
• team (str, optional): Team abbreviation filter
• position (str, optional): Position filter

Returns players[], each with identity fields (player_id, player_name, position, team) plus a stats object containing backend columns (completions, passing_yards, passing_tds, rushing_yards, etc.).

get_nflverse_team_stats

Get normalized nflverse team stat rows.

• season (int, optional): Season year
• team (str, optional): Team abbreviation filter
• week (int, optional): Week filter when available

Returns teams[], each with team/season context plus a stats object containing backend columns. Note: with nfl_data_py, team stats fall back to schedule data (game-by-game results) since a dedicated team stats endpoint is not available.

get_nflverse_play_by_play

Get normalized nflverse play-by-play rows.

• season (int, optional): Season year
• week (int, optional): Week filter
• team (str, optional): Team abbreviation filter
• game_id (str, optional): nflverse game identifier
• limit (int, optional): Max rows to return

Returns plays[] with game/play identifiers, quarter/clock, teams, down/distance, description, EPA, WP/WPA, and score state.

Notes:

• The nflverse backend requires the [nfl] optional extra: pip install sports-skills[nfl]. It prefers nflreadpy when installed and falls back to nfl_data_py for compatibility.
• These commands keep nfl-data as the user-facing skill while exposing table-style datasets under the same module.
• The ESPN-backed commands (e.g. get_scoreboard, get_standings) work with zero extra dependencies. The nflverse commands provide deeper historical/analytical data (seasonal aggregates, EPA, win probability per play) but require the optional install.
• Parquet support (pyarrow or fastparquet) is needed for most nflverse data beyond schedules.

Team IDs

Use get_teams for the complete, authoritative list.

Week Numbers

Regular season: weeks 1-18. Postseason unified numbering: Wild Card=19, Divisional=20, Conference Championship=21, Pro Bowl=22, Super Bowl=23. The connector translates these to ESPN's internal seasontype=3 automatically.

NFL Team IDs (ESPN)

Tip: Use get_teams to get the full, accurate list of team IDs.

Week Numbering

• Regular season: Weeks 1-18
• Postseason: Wild Card = 19, Divisional = 20, Conference Championship = 21, Pro Bowl = 22, Super Bowl = 23
• The connector translates these to ESPN's internal seasontype=3 automatically.
• get_team_schedule returns both regular-season and postseason games.