SaucePackets

Use when making data-driven official sports picks for MLB, NFL, NBA, NHL, or soccer/World Cup; deciding pick vs pass; maintaining a portable picks ledger; or reviewing settled picks.

Use when searching Kalshi sports prediction markets, reading event contracts or OHLC/candlestick data, or comparing CFTC-regulated prediction-market prices.

Use when retrieving MLB scores, schedules, standings, rosters, game summaries, play-by-play, win probability, injuries, transactions, depth charts, team/player stats, leaders, or news from public ESPN endpoints.

Use when retrieving NBA scores, schedules, standings, rosters, game summaries, play-by-play, win probability, injuries, transactions, depth charts, team/player stats, leaders, futures, or news from public ESPN endpoints.

Use when retrieving NFL scores, schedules, standings, rosters, game summaries, play-by-play, win probability, injuries, transactions, depth charts, team/player stats, leaders, or news from public ESPN endpoints.

Use when retrieving NHL scores, schedules, standings, rosters, game summaries, play-by-play, injuries, transactions, team/player stats, leaders, futures, or news from public ESPN endpoints.

Use when searching Polymarket sports prediction markets, reading prices/order books/events, comparing market-implied probabilities, or checking exact sports moneyline markets.

Use when fetching recent sports news, headlines, articles, transfer rumors, or Google News/RSS results for teams, players, leagues, and events.

Use when teaching or practicing Bitcoin wallet engineering through Rust/BDK-shaped mini-katas: UTXOs, descriptors, PSBTs, wallet sync, fee estimation, tests, and open-source contribution readiness. ⚠️ REQUIRES teach-mode — load it before any BDK Dojo turn.

Use when the user is learning, practicing, reinforcing a course, or building skill through a guided exercise. Establishes the umbrella learning-first stance: learner attempts first; agent scaffolds, hints, reviews, verifies, and explains before rescuing.

Use when teaching or practicing prompt writing through short active reps: prompt structure, roles, context, constraints, output formats, examples, hallucination control, evals, and agent/tool workflow prompts.

Query the Knowledge Vault MCP server — search sources, indexed dev-notes, transcripts/artifacts, and ask questions over scoped vault content.