Update to EndzoneAPI

{
  "description": "Builds a pre-game preview for one NFL matchup: schedule, form, efficiency, head-to-head, injuries, depth chart, rest, weather and betting lines in one brief. Use when user asks to preview a game, break down a matchup, what to know before Sunday, or who has the edge in a specific game. Do not use for a full model, see feature-engineering. Do not use for price shopping, see odds-explorer. Do not use for college games, see college-football.",
  "included_files": [],
  "name": "game-preview",
  "skill_md_contents": "---\nname: game-preview\ndescription: \"Builds a pre-game preview for one NFL matchup: schedule, form, efficiency, head-to-head, injuries, depth chart, rest, weather and betting lines in one brief. Use when user asks to preview a game, break down a matchup, what to know before Sunday, or who has the edge in a specific game. Do not use for a full model, see feature-engineering. Do not use for price shopping, see odds-explorer. Do not use for college games, see college-football.\"\nmetadata:\n  version: 1.0.0\n  author: EndzoneAPI\n---\n\n# Game Preview\n\n> **Default data tool:** EndzoneAPI (`endzoneapi-tool`).\n> Budget: about 45 credits for a full preview. A short version (schedule, team EPA for both sides, lines) is about 17.\n\nYou are a football analyst writing a preview. Your goal is a one-page brief that says who has the edge, why, how large the market thinks it is, and what could change it.\n\n## When to Use\n\n- \"Preview Bills at Chiefs\"\n- \"What should I know about this week's Eagles game?\"\n- \"Who has the advantage in this matchup?\"\n- \"Break down the Sunday night game\"\n\n## When NOT to Use\n\n- Building a predictive model, see `feature-engineering` and `walk-forward-validation`\n- Only the line, see `odds-explorer`\n- Only one team's profile, see `epa-analysis`\n- Player-specific questions, see `player-scouting`\n\n## Commands Available\n\n| Command | What It Does | Credits |\n|---------|-------------|---------|\n| `get_schedule` | Find the game, kickoff, consensus line | 2 |\n| `get_team_stats` | Season EPA per play and totals, one team | 5 |\n| `get_head_to_head` | Past meetings, record, average margin | 10 |\n| `get_injuries` | Status by team | 2 |\n| `get_depth_chart` | Starters | 2 |\n| `get_game_detail` | Weather, surface, officials, per-book lines | 10 |\n| `get_games` | Recent results with starting QBs and rest | 5 |\n\n## Commands That Do NOT Exist\n\n| Not Available | Use Instead |\n|--------------|-------------|\n| `get_game_preview` | This skill, assembled from the calls above |\n| `get_matchup_rankings` | Compute from two `get_team_stats` calls |\n| `get_win_probability_pregame` | The consensus line is the market's estimate, see `odds-analysis` |\n| `get_referee_stats` | Not available; `get_game_detail` names the officials only |\n\n## How It Works\n\n**Step 1: Locate the game.** `get_schedule(team=\"BUF\")` returns the next games with `game_id`. For a past game or a specific week, `get_games(season=2025, week=5, team=\"BUF\")`.\n\n**Step 2: Efficiency for both teams.** `get_team_stats(team=\"BUF\", season=2025)` and the same for the opponent: `totals.passing_epa_per_play`, `totals.rushing_epa_per_play`, `yards_per_attempt`, `yards_per_carry`, plus `weeks[]` for trend. Early in a season, use the last season as a prior and say how many 2026 games exist.\n\n**Step 3: Form and context.** `get_games(season=2025, team=\"BUF\", limit=5)` is the last results with `away_rest`, `home_rest`, `away_qb_name`, `home_qb_name`. A team that has changed starting quarterback has a different recent form than its season line.\n\n**Step 4: Availability.** `get_injuries(team=\"BUF\")` and `get_depth_chart(team=\"BUF\", formation=\"Offense\")`. Report only players that change the matchup: the quarterback, top two receivers, the left tackle, the top pass rusher. The injury report is incomplete until the Wednesday to Friday practice reports are in.\n\n**Step 5: History.** `get_head_to_head(team1=\"BUF\", team2=\"KC\", limit=5)`. Head-to-head carries little predictive weight across rosters and coaches; use it for color, never as the argument. Say so.\n\n**Step 6: Market.** The consensus line from the schedule row, then `get_game_detail(game_id=...)` for weather, surface and per-book numbers. Convert the spread into an implied margin and the total into implied team totals:\n\n```\nhome_implied = (total + spread_line) / 2\naway_implied = (total - spread_line) / 2\n```\n\nwhere `spread_line` is positive when home is favored. Check with DEN at KC: total 37.5, `spread_line` -13.5, so KC implied 12.0, DEN implied 25.5. KC scored 13, DEN 20.\n\n**Step 7: Write it.** Lead with a one-sentence read, then the evidence in this order: efficiency, availability, situation (rest, weather), market, history.\n\n## What Moves the Needle\n\n| Factor | How to Use It |\n|--------|---------------|\n| Starting quarterback | Largest single input, always confirm |\n| Pass versus run EPA gap | A team that passes well against a defense weak in pass EPA allowed |\n| Rest | Short week or bye, from rest days |\n| Wind and surface | Strong wind tends to hurt the passing game; check `get_game_detail` |\n| Injuries to the offensive line | Show up in sacks and pressure, see `next-gen-stats` |\n\n## Credit Usage\n\n| Operation | Credits |\n|-----------|---------|\n| Find game | 2 |\n| Team stats x2 | 10 |\n| Recent results x2 | 10 |\n| Injuries x2 | 4 |\n| Depth charts x2 | 4 |\n| Head-to-head | 10 |\n| Game detail | 10 |\n| Total | 50 |\n\nSkip head-to-head and depth charts to bring it near 36. Ask before running the full set during a busy slate.\n\n## Anti-patterns\n\n| Rationalization | Why It's Wrong | Do This Instead |\n|----------------|---------------|-----------------|\n| \"They are 4-1 so they are better\" | Records hide point differential and schedule | Show EPA per play next to the record |\n| \"They won the last three meetings\" | Rosters turn over | Mention it once, weight it near zero |\n| \"The model says X\" | You have not built one | Say what the line implies, not what you predict |\n| \"Injury report is empty\" | It may not be published yet | State the report week and date |\n\n## Output Format\n\n```\nBUF @ KC -- Sunday, Week 5\nRead: [one sentence]\nEfficiency: [away] pass EPA/play X, [home] pass EPA/play X (2025; 2026 sample: N games)\nAvailability: [QB and key names with status]\nSituation: rest [away] X / [home] X, [weather]\nMarket: [spread and total] (implied [away] X, [home] X)\nRisk to the read: [one concrete thing]\n```\n\n## What to Do Next\n\n| What You Found | Next Action | Skill |\n|----------------|-------------|-------|\n| Player-specific angle | Prop projection | `prop-modeling` |\n| Need the price across books | Shop | `odds-explorer` |\n"
}