Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →WNBA data via ESPN public endpoints — scores, standings, rosters, schedules, game summaries, play-by-play, win probability, injuries, transactions, futures, team/player stats, leaders, and news. Zero config, no API keys. Use when: user asks about WNBA scores, standings, team rosters, schedules, game stats, box scores, play-by-play, injuries, transactions, betting futures, team/player statistics, or WNBA news. Don't use when: user asks about NBA (use nba-data), college basketball (use cbb-data),
.claude/skills/machina-sports-wnba-data/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 189% | 0% |
Before writing queries, consult references/api-reference.md for endpoints, ID conventions, and data shapes.
Before first use, check if the CLI is available:
bashwhich 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:
bashpython3 --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.
Prefer the CLI — it avoids Python import path issues:
bashsports-skills wnba get_scoreboard sports-skills wnba get_standings --season=2025 sports-skills wnba get_teams
CRITICAL: Before calling any data endpoint, verify:
currentDate — never hardcoded.get_teams to resolve the team ID before using team-specific commands.Derive the current year from the system prompt's date (e.g., currentDate: 2026-02-18 → current year is 2026).
season = current_year. If November–April (offseason), use season = current_year - 1.| Command | Description | |---|---| | get_scoreboard | Live/recent WNBA scores | | get_standings | Standings by conference | | get_teams | All WNBA teams | | get_team_roster | Full roster for a team | | get_team_schedule | Schedule for a specific team | | get_game_summary | Detailed box score and scoring plays | | get_leaders | WNBA statistical leaders | | get_news | WNBA news articles | | get_play_by_play | Full play-by-play for a game | | get_win_probability | Win probability chart data | | get_schedule | Schedule for a specific date or season | | get_injuries | Injury reports across all teams | | get_transactions | Recent transactions | | get_futures | Futures/odds markets | | get_team_stats | Team statistical profile | | get_player_stats | Player statistical profile |
See references/api-reference.md for full parameter lists and return shapes.
Example 1: Today's scores User says: "What are today's WNBA scores?" Actions:
get_scoreboard()Result: All live and recent WNBA games with scores and status
Example 2: Standings User says: "Show me the WNBA standings" Actions:
currentDateget_standings(season=<derived_year>)Result: Eastern and Western conference standings with W-L, PCT, GB
Example 3: Team roster User says: "Who's on the Indiana Fever roster?" Actions:
get_team_roster(team_id="5")Result: Full Indiana Fever roster with name, position, jersey number
Example 4: Statistical leaders User says: "Show me WNBA statistical leaders" Actions:
currentDateget_leaders(season=<derived_year>)Result: Leaders ranked by stat category (points, rebounds, assists, etc.)
Example 5: Championship odds User says: "What are the WNBA championship odds?" Actions:
get_futures(limit=10)Result: Top WNBA championship contenders with odds values
Example 6: Player statistics User says: "Show me A'ja Wilson's stats" Actions:
currentDateget_player_stats(player_id="3149391", season_year=<derived_year>)Result: Season stats by category with value, rank, and per-game averages
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.
When a command fails, do not surface raw errors to the user. Instead:
get_teams to find the ID firstError: sports-skills command not found Cause: Package not installed Solution: Run pip install sports-skills
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 WNBA 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: Offseason (November–April) — scoreboard returns 0 events Cause: No games scheduled during the offseason Solution: Use get_standings(season=<prior_year>) or get_news instead
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 9,988 | 3,929 | -61% | 1 | 1 | 0% | 2,122 | 1,612 | -24% | 0 | 0 | — |
case-02 | fail→fail | 6,440 | 5,192 | -19% | 1 | 1 | 0% | 1,088 | 1,700 | +56% | 0 | 0 | — |
case-03 | fail→fail | 10,168 | 4,977 | -51% | 1 | 1 | 0% | 2,197 | 1,712 | -22% | 0 | 0 | — |
case-04 | fail→pass | 11,636 | 4,469 | -62% | 1 | 1 | 0% | 1,892 | 2,116 | +12% | 0 | 0 | — |
case-05 | fail→pass | 10,897 | 1,799 | -83% | 1 | 1 | 0% | 2,000 | 1,743 | -13% | 0 | 0 | — |
case-06 | fail→pass | 8,719 | 4,275 | -51% | 1 | 1 | 0% | 1,598 | 2,223 | +39% | 0 | 0 | — |
case-07 | pass→fail | 3,981 | 12,762 | +221% | 1 | 1 | 0% | 598 | 2,103 | +252% | 0 | 0 | — |
case-08 | pass→fail | 10,276 | 4,836 | -53% | 1 | 1 | 0% | 1,508 | 1,721 | +14% | 0 | 0 | — |
case-09 | pass→pass | 7,411 | 6,601 | -11% | 1 | 1 | 0% | 1,293 | 2,485 | +92% | 0 | 0 | — |
case-15 | fail→pass | 9,839 | 1,339 | -86% | 1 | 1 | 0% | 1,776 | 1,617 | -9% | 0 | 0 | — |
case-10 | pass→pass | 3,301 | 2,957 | -10% | 1 | 1 | 0% | 604 | 1,852 | +207% | 0 | 0 | — |
case-11 | pass→pass | 2,215 | 2,973 | +34% | 1 | 1 | 0% | 366 | 1,897 | +418% | 0 | 0 | — |
case-12 | fail→pass | 4,042 | 2,431 | -40% | 1 | 1 | 0% | 651 | 1,881 | +189% | 0 | 0 | — |
case-13 | fail→pass | 9,001 | 3,753 | -58% | 1 | 1 | 0% | 1,338 | 1,991 | +49% | 0 | 0 | — |
case-14 | fail→fail | 7,892 | 1,876 | -76% | 1 | 1 | 0% | 1,129 | 1,712 | +52% | 0 | 0 | — |
case-16 | fail→pass | 8,833 | 4,385 | -50% | 1 | 1 | 0% | 1,439 | 2,173 | +51% | 0 | 0 | — |
case-17 | fail→pass | 7,395 | 3,243 | -56% | 1 | 1 | 0% | 1,498 | 1,987 | +33% | 0 | 0 | — |
case-18 | fail→pass | 8,824 | 2,005 | -77% | 1 | 1 | 0% | 1,719 | 1,791 | +4% | 0 | 0 | — |
case-19 | fail→pass | 9,276 | 3,128 | -66% | 1 | 1 | 0% | 1,323 | 1,894 | +43% | 0 | 0 | — |
case-20 | fail→pass | 6,197 | 3,702 | -40% | 1 | 1 | 0% | 1,013 | 1,972 | +95% | 0 | 0 | — |
case-21 | pass→pass | 11,923 | 2,765 | -77% | 1 | 1 | 0% | 2,009 | 1,853 | -8% | 0 | 0 | — |
case-22 | pass→pass | 5,998 | 1,527 | -75% | 1 | 1 | 0% | 948 | 1,650 | +74% | 0 | 0 | — |
case-23 | pass→pass | 5,833 | 2,496 | -57% | 1 | 1 | 0% | 936 | 1,781 | +90% | 0 | 0 | — |
case-24 | fail→pass | 8,906 | 2,227 | -75% | 1 | 1 | 0% | 1,774 | 1,718 | -3% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted, and 19 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +42 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.