machina-sports/sports-skills
23 skills15k installs4.6k starsGitHub
Install
npx skills add https://github.com/machina-sports/sports-skillsSkills in this repo
1Football Data| --- name: football-data description: | Football (soccer) data across 13 leagues - standings, schedules, match stats, xG, transfers, player profiles. Covers Premier League, La Liga, Bundesliga, Serie A, Ligue 1, MLS, Champions League, World Cup, Championship, Eredivisie, Primeira Liga, Serie A Brazil, European Championship. Use when: user asks about football/soccer standings, fixtures, match stats, xG, lineups, player values, transfers, injury news, league tables, daily fixtures, or player profiles. Don't use when: user asks about American football/NFL (use nfl-data), college football (use cfb-data), NBA (use nba-data), WNBA (use wnba-data), college basketball (use cbb-data), NHL (use nhl-data), MLB (use mlb-data), tennis (use tennis-data), golf (use golf-data), cricket (use cricket-data), Formula 1 (use fastf1), or betting odds (use polymarket or kalshi). Don't use for live/real-time scores - data updates post-match. Don't use get_season_leaders or get_missing_players for non-Premier League leagues (they return empty). Don't use get_event_xg for leagues outside the top 5 (EPL, La Liga, Bundesliga, Serie A, Ligue 1).1.9kinstalls2BettingThe betting skill | # Betting Analysis Before writing queries, consult `references/api-reference.md` for odds formats, command parameters, and key concepts. ## Quick Start ```bash sports-skills betting convert_odds --odds=-150 --from_format=american sports-skills betting devig --odds=-150,+130 --format=american sports-skills betting find_edge --fair_prob=0.58 --market_prob=0.52 sports-skills betting evaluate_bet --book_odds=-150,+130 --market_prob=0.52 sports-skills betting find_arbitrage --market_probs=0.48,0.49 sports-skills betting parlay_analysis --legs=0.58,0.62,0.55 --parlay_odds=600 sports-skills betting line_movement --open_odds=-140 --close_odds=-160 ``` Python SDK: ```python from sports_skills import betting betting.convert_odds(odds=-150, from_format="american") betting.devig(odds="-150,+130", format="american") betting.find_edge(fair_prob=0.58, market_prob=0.52) betting.find_arbitrage(market_probs="0.48,0.49") betting.parlay_analysis(legs="0.58,0.62,0.55", parlay_odds=600) betting.line_movement(open_odds=-140, close_odds=-160) ``` ## CRITICAL: Before Any Analysis CRITICAL: Before calling any analysis command, verify: - Odds format is correctly identified (american, dec.1.2kinstalls3PolymarketThe polymarket skill exposes Polymarket sports prediction market data including live odds, prices, order books, events, series, and market search across NFL, NBA, MLB, football leagues, tennis, cricket, MMA, and esports. Core read commands work without API keys via sports-skills CLI or Python SDK, covering moneyline, spreads, totals, and player props. Critical rules require passing sport on search_markets and get_todays_events, treat prices as zero-to-one probabilities, and use token_id from get_market_details for CLOB price endpoints rather than market_id. Trading commands need py-clob-client-v2 plus POLYMARKET_PRIVATE_KEY and optional funder address for proxy wallets. The skill distinguishes prediction market sentiment from actual match results, directing score questions to sport-specific data skills instead.1.1kinstalls4Sports Newssports-news is a machina-sports skill that exposes two commands for pulling sports news into agent workflows: fetch_feed loads an RSS or Atom URL and returns feed metadata plus recent entries, and fetch_items retrieves news from either a feed URL or a Google News search query. Each entry includes title, link, published date, summary, and source, with optional limit and after-date filtering on items. Developers reach for sports-news when building sports dashboards, alert bots, fantasy tools, or content aggregators that need fresh headlines without maintaining brittle HTML parsers. The API reference defines required and optional parameters explicitly, including the rule that google_news queries require a query string when enabled. Because feeds and Google News are mutually exclusive inputs, agents pick one source path per call and return structured JSON-ready item lists.967installs5KalshiKalshi is a sports-skills agent integration for the US-regulated Kalshi prediction exchange, exposing events, series, markets, trades, and candlestick OHLC data through a public read API requiring no authentication. It covers football leagues including EPL, UCL, and La Liga, plus basketball, baseball, tennis, NFL, and hockey event contracts. Developers reach for Kalshi when building analytics on market-implied sports probabilities—not actual match scores or statistics, which belong to sport-specific data skills like football-data or nfl-data. Use it for Kalshi-specific markets, CFTC-regulated contracts, or candlestick price history on sports outcomes.809installs6Nba Datanba-data is a machina-sports/sports-skills reference that exposes four core commands: `get_scoreboard` for live or dated game events, `get_standings` by conference and season, `get_teams` for all 30 NBA franchises, and `get_team_roster` by ESPN team ID. Scoreboard responses include competitors, scores, and game status; standings return Eastern and Western groups with W-L, PCT, GB, streak, and home/away splits. Developers reach for nba-data when wiring sports dashboards, fantasy tools, or content sites that need structured NBA data without maintaining brittle ESPN endpoint parsers. Team roster lookups accept ESPN IDs such as "13" for the Lakers.808installs7Marketsmarkets is a sports prediction-market orchestration skill from machina-sports/sports-skills that connects ESPN live game schedules with Kalshi and Polymarket inside agent and CLI workflows. Developers invoke it to build unified dashboards, compare odds across platforms, search teams or players on prediction markets, spot arbitrage between ESPN lines and market prices, and evaluate a specific game’s market value. The skill deliberately layers ESPN schedule context on top of market APIs rather than replacing dedicated polymarket or kalshi skills for raw market data or the betting skill for pure odds math like de-vigging or Kelly sizing. Reach for markets when an agent needs schedule-aware prediction market intelligence in one orchestrated pass.668installs8Golf Datagolf-data is a machina-sports/sports-skills agent skill focused on golf domain data for software engineers building analytics platforms, editorial golf products, or predictive scoring models. It guides exploration of player profiles, course characteristics, and tournament histories so implementations use accurate, domain-specific metrics instead of generic sports stubs. Developers reach for golf-data when scaffolding APIs, dashboards, or ML features that must reference real golf entities and stat categories. The skill bridges sports data modeling and application code during build phases. Use it when golf-specific fields, aggregations, or dataset joins are required in backend or data-layer work.590installs9Mlb Datamlb-data is a Machina Sports agent skill from machina-sports/sports-skills for ingesting Major League Baseball data into applications. It provides standardized recipes to fetch schedules, box scores, play-by-play events, and player statistics so fantasy tools, betting research dashboards, or editorial baseball products stay current without hand-rolling MLB API clients. Developers reach for mlb-data when they need repeatable pipelines for game-day updates, historical stat joins, or content feeds grounded in official game data. The skill focuses on ingestion patterns and normalized outputs agents can wire into databases, APIs, or editorial workflows rather than one-off CSV downloads.570installs10Tennis Datatennis-data is a skill from machina-sports/sports-skills for exploring tennis match results, rankings, and player statistics before building a sports product. It helps developers assess data availability, signal richness, and feature priority—such as live scores, head-to-head history, ranking trends, or player biometrics—when scoping an API, dashboard, or content app. Reach for tennis-data during product discovery for tennis verticals, competitive analysis of sports data offerings, or deciding which endpoints and caches a tennis service needs on day one. The skill produces a scoped signal inventory and opportunity assessment rather than production ETL pipelines, making it a validate-phase research aid for sports engineering teams.564installs11Nfl Datanfl-data is a Python skill from machina-sports/sports-skills (version 0.1.0, MIT) that exposes 22 CLI commands for NFL data through the sports-skills package with zero API keys. ESPN-backed commands include get_scoreboard, get_standings, get_teams for all 32 NFL teams, get_team_roster, get_play_by_play, get_injuries, and get_game_summary. nflverse-backed commands—requiring pip install sports-skills[nfl]—return normalized schedules, weekly rosters, player stats, team stats, and play-by-play rows with EPA and win-probability fields. The skill requires Python 3.10+, derives season years from currentDate rather than hardcoding, and documents postseason week numbers 19–23. Developers reach for nfl-data when building fantasy apps, broadcast dashboards, or ML pipelines that need consistent NFL ingestion templates.554installs12World Cupworld-cup is a premium prompt-only skill in machina-sports/sports-skills that routes coding agents to the hosted World Cup Intelligence project for FIFA World Cup 2026. It fuses official match truth—fixtures, standings, squads, injuries, and player performance—with live prediction market data from Kalshi and Polymarket including prices, order books, movers, and cross-venue edges. Every entity carries a canonical Machina URN cross-walked across api-football, Sportradar, Opta, Entain, and ESPN so a market resolves to a fixture and two teams. Developers reach for world-cup when building sports apps, newsletters, or editorial workflows that need prematch briefs, move explanations, and fan pulse context without wiring five data vendors manually. The skill is read-only and premium, designed for agent prompts that need grounded match and market context in one call pattern.540installs13Nhl Datanhl-data in machina-sports/sports-skills helps developers pull structured NHL game data into downstream analytics and content systems. The skill covers schedules, player shifts, shot events, and goalie statistics—the core event streams hockey analytics sites and fantasy league backends require. Developers reach for nhl-data when building recap generators, highlight automation, shot-chart visualizations, or fantasy scoring engines that need consistent NHL feed ingestion rather than manual CSV imports. Agents use it to structure integration conversations around which event types to capture and how pipelines should normalize shifts and shots for querying. Typical outputs include ingestion plans and normalized datasets ready for warehouse loads or real-time APIs. Part of the machina-sports sports-skills collection, nhl-data complements other league-specific skills when products expand beyond hockey but stays focused on NHL event schemas. Triggers include NHL data pipeline, hockey shot events, goalie stats ingestion, fantasy league feeds, and automated game recap generation.531installs14Cfb Datacfb-data is a machina-sports/sports-skills data access workflow for college football (CFB) datasets. The skill retrieves team stats, game schedules, and historical results so developers can populate prototype dashboards, benchmark analytics features, or sanity-check a sports product concept with real season data. Developers reach for cfb-data during early sports-app work when mock data is insufficient and they need authoritative CFB figures to demo stakeholders or test query performance. It supports validation and prototyping rather than production ETL pipelines or live betting integrations.530installs15Sports Reportersports-reporter is a machina-sports agent skill that turns sports stats, fixtures, and injury data into publish-ready editorial content. The skill produces match recaps, game previews, injury update notes, and trend-driven articles formatted for fan sites, newsletters, or automated publishing pipelines. Developers and editorial engineers reach for sports-reporter when building content automation that ingests structured sports data and outputs narrative copy at scale. It fits backend cron jobs, CMS integrations, or agent workflows that need consistent sports journalism templates rather than hand-written posts. Input expectations center on stats feeds and fixture lists; outputs are article drafts ready for human review or direct publishing.520installs16Cbb Datacbb-data is a machina-sports skill (version 0.1.0) for NCAA Division I men's college basketball data via ESPN public endpoints with zero API keys. The sports-skills CLI exposes 14 commands including get_scoreboard, get_standings, get_rankings, get_teams across 360+ D1 teams, get_team_roster, get_game_summary, get_play_by_play, get_win_probability, get_futures, and get_team_stats. Developers install with pip install sports-skills requiring Python 3.10+. The skill handles season-year derivation from currentDate, per-conference standings via group IDs, March Madness tournament context, and ranked-team fields on scoreboard competitors. Reach for cbb-data when building CBB dashboards, content products, or predictive modeling prototypes needing schedules, box scores, AP Top 25 rankings, or betting futures.519installs17Wnba Datawnba-data is a sports-skills agent skill for fetching and structuring Women's National Basketball Association datasets inside developer applications. The skill covers box scores, league standings, team rosters, and play-by-play event feeds that power betting analytics dashboards, media widgets, or fan-facing stats experiences. Developers reach for wnba-data when a product needs current-season WNBA metrics without manually scraping league sites or maintaining fragile HTML parsers. The workflow normalizes game, player, and team records into consumable shapes for APIs, charts, or recommendation engines. Use it when building sports data features focused on the WNBA rather than generic multi-league aggregators.519installs18Volleyball Datavolleyball-data is an agent skill (version 0.1.0) that connects developers to Dutch volleyball data through the open Nevobo API with no API keys required. It exposes ten CLI commands—get_competitions, get_standings, get_schedule, get_results, get_clubs, get_club_schedule, get_club_results, get_poules, get_tournaments, and get_news—plus a Python SDK via the sports-skills package (Python 3.10+). Eight preconfigured leagues cover Eredivisie, Topdivisie, and Superdivisie tiers, while get_poules can discover 6,400+ lower-division poules. Developers reach for volleyball-data when building match trackers, league tables, club schedules, or content bots that need verified competition_id and club_id values from bundled reference files instead of guessed identifiers.440installs19Xctf DataXCTF-data skill covers cross-country and track-and-field meet results, athlete records, and endurance-sport statistics for ideation research—assessing coverage depth before building niche running or collegiate athletics products.355installs20Fastf1FastF1 integration skill for Formula 1 data: fetch lap times, telemetry, session results, and standings via Python to power sports analytics dashboards, content tools, and modeling pipelines.340installs21MetadataSports metadata skill from machina-sports teaches Claude to craft SEO-ready titles, descriptions, social cards, and structured data for fixtures, teams, and athletes so sports content sites launch with strong search and sharing signals.339installs22MachinaMachina sports platform skill for integrating multi-league feeds, normalizing schedules and stats, and building ETL plus API workflows that power cross-sport analytics, content, and agent tooling.300installs23Cricket Datacricket-data is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.267installs