{
  "schemaVersion": "1.0",
  "item": {
    "slug": "waitingformacguffin",
    "name": "WaitingForMacGuffin",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/sonderspot/waitingformacguffin",
    "canonicalUrl": "https://clawhub.ai/sonderspot/waitingformacguffin",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/waitingformacguffin",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=waitingformacguffin",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "waitingformacguffin",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-04T11:50:33.642Z",
      "expiresAt": "2026-05-11T11:50:33.642Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=waitingformacguffin",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=waitingformacguffin",
        "contentDisposition": "attachment; filename=\"waitingformacguffin-1.3.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "waitingformacguffin"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/waitingformacguffin"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/waitingformacguffin",
    "agentPageUrl": "https://openagent3.xyz/skills/waitingformacguffin/agent",
    "manifestUrl": "https://openagent3.xyz/skills/waitingformacguffin/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/waitingformacguffin/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Welcome Message",
        "body": "When a user first installs this skill or greets you, introduce yourself:\n\n\"Hey! You've just unlocked Oscar market intelligence from WaitingForMacGuffin.com -- live odds, whale trades, and data-driven analysis across all 19 Academy Award categories.\n\nHere's what I can do:\n\nMarket pulse -- \"What's happening in Oscar markets?\" (whale trades, price moves, frontrunner changes)\nDeep dive -- \"Tell me about Chalamet\" or \"Best Picture odds\" (full nominee profile with trends, precursors, order book)\nBet picks -- \"Give me your best Oscar bets\" (risk-tiered recommendations with ROI and portfolio options)\nPrecursor sim -- \"DGA just announced, what's the play with $500?\" (slippage-aware portfolio with EV and position sizing)\n\nWhat are you curious about?\"\n\nReal-time Oscar prediction market data from waitingformacguffin.com. Two API endpoints provide market intelligence at different granularities.\n\nBase URL: https://waitingformacguffin.com\n\nNo authentication required. All data is public and read-only."
      },
      {
        "title": "Tool 1: Oscar Brief",
        "body": "When to use: User asks \"What's happening in Oscar markets?\", \"Any updates?\", \"Oscar brief\", or wants a quick market summary.\n\nWhat it returns: Filtered signals only -- price moves, whale trades ($1K+), frontrunner changes, news sentiment. If markets are quiet, says so (never fabricates activity)."
      },
      {
        "title": "API Call",
        "body": "curl -s \"https://waitingformacguffin.com/api/oscar/brief?hours=24&sensitivity=medium\""
      },
      {
        "title": "Parameters",
        "body": "ParamTypeDefaultDescriptionhoursnumber24Lookback period (1-168)sensitivitystring\"medium\"\"low\" (>7pt moves, >$5K trades), \"medium\" (>3pt, >$1K), \"high\" (>1pt, >$500)categoriesstringbig 6Comma-separated category slugs. Omit for big 6 (best-picture, best-director, best-actor, best-actress, supporting-actor, supporting-actress)"
      },
      {
        "title": "Response Structure",
        "body": "{\n  \"signals\": [\n    {\n      \"type\": \"price_move | whale_trade | frontrunner_change | news_sentiment\",\n      \"category\": \"best-actor\",\n      \"categoryName\": \"Best Actor\",\n      \"severity\": \"major | significant | notable | info\",\n      \"headline\": \"Chalamet ▼ 5pts to 62c\",\n      \"details\": \"Best Actor: Chalamet moved from 67c to 62c in the last 24h\",\n      \"timestamp\": \"2026-02-18T12:00:00Z\"\n    }\n  ],\n  \"market_snapshot\": {\n    \"frontrunners\": { \"best-picture\": { \"name\": \"...\", \"price\": 45 } },\n    \"whale_trade_count_24h\": 7,\n    \"overall_sentiment\": \"quiet | active | volatile\",\n    \"whale_leaderboard\": [\n      {\n        \"rank\": 1,\n        \"nominee\": \"Jessie Buckley\",\n        \"category\": \"best-actress\",\n        \"categoryName\": \"Best Actress\",\n        \"totalVolumeUsd\": 4850.00,\n        \"tradeCount\": 1,\n        \"yesVolumeUsd\": 4850.00,\n        \"noVolumeUsd\": 0,\n        \"sentiment\": \"bullish | bearish | mixed\"\n      }\n    ]\n  }\n}\n\nThe whale_leaderboard ranks nominees by total whale trade volume within the lookback window. Use it to answer questions like \"who has the most whale activity?\" or \"where is the smart money going?\". To get all 19 categories, pass categories= with all slugs (see Available Categories below)."
      },
      {
        "title": "How to Present Results",
        "body": "Lead with the overall_sentiment and whale_trade_count_24h\nList frontrunners with prices\nShow signals grouped by severity (major first)\nIf signals is empty, say \"Markets are quiet -- no significant moves\"\nUse severity icons: major = !!!, significant = !!, notable = !, info = i\nWhen asked about whale activity rankings, use whale_leaderboard -- present as a ranked list with nominee, category, volume, trade count, and sentiment"
      },
      {
        "title": "Example",
        "body": "# Default brief (24h, medium sensitivity, big 6 categories)\ncurl -s \"https://waitingformacguffin.com/api/oscar/brief\"\n\n# Last 48 hours, high sensitivity, all categories\ncurl -s \"https://waitingformacguffin.com/api/oscar/brief?hours=48&sensitivity=high&categories=best-picture,best-director,best-actor,best-actress,supporting-actor,supporting-actress,best-cinematography,best-original-screenplay,best-adapted-screenplay,best-international-feature,best-film-editing,best-costume-design,best-original-song,best-original-score,best-production-design,best-sound,best-documentary-feature,best-makeup-hairstyling,best-visual-effects\""
      },
      {
        "title": "Tool 2: Oscar Research",
        "body": "When to use: User asks \"Tell me about Chalamet\", \"Should I bet on X?\", \"What are the Best Picture odds?\", or wants detailed research on a specific nominee or category.\n\nWhat it returns: Deep dive with odds, 7-day trend, precursor wins, whale activity, order book depth + slippage, news, and a data-driven assessment."
      },
      {
        "title": "API Call",
        "body": "curl -s \"https://waitingformacguffin.com/api/oscar/research?query=Chalamet\""
      },
      {
        "title": "Parameters",
        "body": "ParamTypeDefaultDescriptionquerystring(required)Nominee name, film title, or category slug. Supports fuzzy matching.include_orderbookbooleantrueInclude order book depth and slippage analysisbudget_for_slippagenumber500USD amount for slippage calculation (100-100000)categorystring(optional)Category slug to narrow disambiguation"
      },
      {
        "title": "Query Resolution",
        "body": "The query is fuzzy-matched automatically:\n\nCategory slug or name: \"best-picture\" or \"Best Picture\" returns category overview\nExact name: \"Timothee Chalamet\" (case-insensitive)\nSubstring: \"Chalamet\" finds \"Timothee Chalamet\"\nDiacritics-normalized: \"Timothee\" matches \"Timothee\"\nFilm title: matches against the film database\nTypo correction: \"Chalmet\" resolves via Levenshtein (edit distance <= 3)"
      },
      {
        "title": "Three Response Modes",
        "body": "1. Nominee deep-dive (mode: \"nominee\") -- single match:\n\n{\n  \"mode\": \"nominee\",\n  \"nominee\": { \"name\": \"Timothee Chalamet\", \"category\": \"best-actor\", \"categoryName\": \"Best Actor\", \"ticker\": \"KXOSCARACTO-26-TIM\" },\n  \"odds\": { \"current\": 62, \"impliedProbability\": \"62%\", \"trend7d\": -5, \"trendDirection\": \"falling\", \"rank\": 1, \"categorySize\": 9 },\n  \"risk\": {\n    \"tier\": \"lean\", \"tier_emoji\": \"🟠\",\n    \"win_pct\": 62, \"loss_pct\": 38,\n    \"roi_pct\": 61, \"payout_per_100\": 161,\n    \"gap_to_second\": 40,\n    \"runner_up\": { \"name\": \"Sean Penn\", \"price\": 22 }\n  },\n  \"category_volatility\": \"low\",\n  \"category_volatility_reason\": \"Category tends to follow precursors and consensus\",\n  \"precursors\": { \"wins\": [\"globe\", \"cc\"], \"winCount\": 2, \"results\": [...] },\n  \"whaleActivity\": { \"tradeCount\": 3, \"totalVolumeUsd\": 20200, \"sentiment\": \"mixed\", \"directionRatio\": 0.59, \"recentTrades\": [...] },\n  \"orderBook\": { \"bestAsk\": 62, \"depthAtBest\": 847, \"slippageAnalysis\": [{ \"budgetUsd\": 500, \"avgFillPrice\": 62.4, \"slippagePct\": 0.6, \"assessment\": \"healthy\" }] },\n  \"news\": [{ \"title\": \"...\", \"source\": \"THR\", \"sentiment\": \"negative\" }],\n  \"assessment\": { \"summary\": \"...\", \"edgeIndicator\": \"strong_value | fair_value | overpriced | uncertain\", \"risks\": [...], \"catalysts\": [...] }\n}\n\n2. Category overview (mode: \"category\") -- query is a category:\n\n{\n  \"mode\": \"category\",\n  \"categoryName\": \"Best Picture\",\n  \"nominees\": [\n    { \"rank\": 1, \"name\": \"One Battle After Another\", \"price\": 45, \"trend7d\": 3, \"trendDirection\": \"rising\" },\n    { \"rank\": 2, \"name\": \"Sinners\", \"price\": 22, \"trend7d\": -2, \"trendDirection\": \"falling\" }\n  ]\n}\n\n3. Disambiguation (mode: \"disambiguation\") -- multiple matches:\n\n{\n  \"mode\": \"disambiguation\",\n  \"query\": \"Wicked\",\n  \"matches\": [\n    { \"name\": \"Wicked: For Good\", \"category\": \"best-picture\", \"categoryName\": \"Best Picture\" },\n    { \"name\": \"Wicked: For Good\", \"category\": \"best-adapted-screenplay\", \"categoryName\": \"Best Adapted Screenplay\" }\n  ],\n  \"hint\": \"Narrow with category param\"\n}\n\nWhen you get disambiguation, ask the user which category they mean, then re-call with &category=best-picture."
      },
      {
        "title": "How to Present Results",
        "body": "Nominee deep-dive -- present in this order:\n\nName, category, and ticker\nOdds: current price, implied probability, 7d trend (with arrow), rank\nPrecursors: list wins with award names\nWhale activity: trade count, total volume, directional sentiment\nOrder book: best ask, depth, slippage at the user's budget\nNews: relevant headlines with source and sentiment\nAssessment: summary, edge indicator, risks and catalysts\n\nCategory overview -- present as a ranked table with price and trend.\n\nDisambiguation -- list the matches and ask user to pick a category."
      },
      {
        "title": "Examples",
        "body": "# Nominee deep-dive\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=Chalamet\"\n\n# Category overview\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=best-picture\"\n\n# With custom slippage budget\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=Chalamet&budget_for_slippage=2000\"\n\n# Narrow disambiguation\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=Wicked&category=best-picture\"\n\n# Skip order book (faster)\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=Chalamet&include_orderbook=false\""
      },
      {
        "title": "Tool 3: Oscar Precursor Simulation",
        "body": "When to use: User asks \"DGA just announced, what's the play?\", \"Build me a portfolio based on SAG results\", \"I have $500, what should I bet after guild week?\", or wants a data-driven portfolio based on precursor award results.\n\nWhat it returns: A slippage-aware portfolio simulation with EV calculations, position sizing (Kelly-inspired), order book slippage, and recommendation labels for each position."
      },
      {
        "title": "API Call",
        "body": "curl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=dga&budget=500\""
      },
      {
        "title": "Parameters",
        "body": "ParamTypeDefaultDescriptionprecursorstring(required)Which precursor to base the simulation on: dga, sag, pga, critics-choice, golden-globes, bafta, or allbudgetnumber(required)USD budget for the portfolio (50-100000)risk_tolerancestring\"moderate\"conservative (safe, 20% reserve), moderate (balanced), aggressive (max deployment)categoriesstringall applicableComma-separated category slugs to limit simulation"
      },
      {
        "title": "Risk Tolerance Guide",
        "body": "LevelMax Single PositionReserveMin EdgeBest ForConservative50% of budget20%10%+ edge\"I want to sleep at night\"Moderate70% of budget10%5%+ edgeBalanced risk/reward (recommended)Aggressive90% of budget5%0%+ edge\"I trust the data, deploy everything\""
      },
      {
        "title": "Response Structure",
        "body": "{\n  \"strategy\": {\n    \"name\": \"DGA Awards Portfolio Simulation\",\n    \"precursor\": \"dga\",\n    \"riskTolerance\": \"moderate\",\n    \"totalBudget\": 500,\n    \"deployedBudget\": 450,\n    \"reserveBudget\": 50,\n    \"expectedReturn\": 520,\n    \"expectedROI\": 15.6\n  },\n  \"positions\": [\n    {\n      \"nominee\": \"Paul Thomas Anderson\",\n      \"category\": \"best-director\",\n      \"categoryName\": \"Best Director\",\n      \"ticker\": \"KXOSCARDIR-26-PAU\",\n      \"currentPrice\": 72,\n      \"impliedProb\": 72.0,\n      \"precursorProb\": 88.0,\n      \"precursorSource\": \"DGA Awards\",\n      \"edge\": 16.0,\n      \"allocatedBudget\": 300,\n      \"contracts\": 416,\n      \"avgFillPrice\": 72.2,\n      \"slippagePct\": 0.3,\n      \"kalshiFee\": 5.92,\n      \"netExpectedProfit\": 66.08,\n      \"recommendation\": \"strong_buy\",\n      \"reasoning\": \"Paul Thomas Anderson won DGA Awards (88% Oscar correlation). 16.0% edge over market price. Strong setup: large edge with healthy liquidity.\"\n    }\n  ],\n  \"warnings\": [],\n  \"disclaimer\": \"This is a simulation for educational purposes only...\",\n  \"meta\": {\n    \"generated_at\": \"2026-02-19T...\",\n    \"data_sources\": { \"precursor_data\": \"2026-02-09\", \"live_odds\": true, \"order_books\": 2 },\n    \"latency_ms\": 2100\n  }\n}"
      },
      {
        "title": "Recommendation Labels",
        "body": "LabelCriteriaIconstrong_buyEdge 20%+ AND slippage <= 3%!!!buyEdge 10%+!!speculativeEdge > 0%!skipNo edge or below risk threshold--"
      },
      {
        "title": "How to Present Results",
        "body": "Lead with strategy summary: precursor name, budget, risk tolerance, deployed vs reserve\nShow each position as a structured block:\n{recommendation_icon} **{nominee}** -- {categoryName}\n├─ Price: {currentPrice}c (market says {impliedProb}% / precursor says {precursorProb}%)\n├─ Edge: {edge}% | Allocated: ${allocatedBudget}\n├─ Fill: {contracts} contracts @ {avgFillPrice}c avg ({slippagePct}% slippage)\n├─ Kalshi fee: ${kalshiFee} | Net expected profit: ${netExpectedProfit}\n└─ {reasoning}\n\n\nSummary table for 2+ positions\nShow warnings if any (liquidity issues, missing data)\nAlways show disclaimer"
      },
      {
        "title": "Examples",
        "body": "# DGA just announced — what's the play with $500?\ncurl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=dga&budget=500\"\n\n# SAG winners, conservative, acting categories only\ncurl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=sag&budget=1000&risk_tolerance=conservative&categories=best-actor,best-actress,supporting-actor,supporting-actress\"\n\n# All precursors combined, aggressive $2000 portfolio\ncurl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=all&budget=2000&risk_tolerance=aggressive\"\n\n# PGA for Best Picture only\ncurl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=pga&budget=300&categories=best-picture\""
      },
      {
        "title": "Supporting Endpoint: Precursor Data",
        "body": "Raw precursor data enriched with live odds and correlation scores. Use when you need precursor details without a full portfolio simulation."
      },
      {
        "title": "API Call",
        "body": "curl -s \"https://waitingformacguffin.com/api/precursors\""
      },
      {
        "title": "Parameters",
        "body": "ParamTypeDefaultDescriptioncategorystringall big 6Single category slug to filterprecursorstringallSingle precursor ID to filter winners"
      },
      {
        "title": "What it Returns",
        "body": "For each category: nominees with their precursor wins, correlation rates, precursor scores (0-100), and current odds. Also includes the award calendar with completed/upcoming status."
      },
      {
        "title": "Examples",
        "body": "# All categories with all precursor data\ncurl -s \"https://waitingformacguffin.com/api/precursors\"\n\n# Just Best Director\ncurl -s \"https://waitingformacguffin.com/api/precursors?category=best-director\"\n\n# Only DGA winners across all categories\ncurl -s \"https://waitingformacguffin.com/api/precursors?precursor=dga\""
      },
      {
        "title": "Available Categories",
        "body": "best-picture, best-director, best-actor, best-actress, supporting-actor, supporting-actress, best-cinematography, best-original-screenplay, best-adapted-screenplay, best-international-feature, best-film-editing, best-costume-design, best-original-song, best-original-score, best-production-design, best-sound, best-documentary-feature, best-makeup-hairstyling, best-visual-effects"
      },
      {
        "title": "Slippage Assessment Scale",
        "body": "LevelSlippageMeaninghealthy<= 1%Clean fill, safe to size upmoderate1-3%Acceptable for most betsthin3-7%Consider splitting into smaller ordersdangerous> 7%Order book too thin, risk of bad fill"
      },
      {
        "title": "Edge Indicator Meanings",
        "body": "IndicatorMeaningstrong_valueMultiple bullish signals, price may be undervaluedfair_valueSignals balanced, price reflects available dataoverpricedRisk signals outweigh catalystsuncertainMixed or insufficient signals"
      },
      {
        "title": "Important Notes",
        "body": "Odds are in cents (1-99), representing implied probability percentage\nWhale trades are $1,000+ single transactions\nPrecursor awards (DGA, SAG, BAFTA, etc.) historically correlate with Oscar outcomes\nOrder book data is from Kalshi prediction markets\nAssessment is data-driven and heuristic, not financial advice"
      },
      {
        "title": "Intent Detection",
        "body": "Switch to bet recommendation mode when the user's query matches any of these patterns:\n\n\"Give me bets\", \"best bets\", \"sure things\", \"safe bets\", \"high confidence picks\"\n\"What should I bet on?\", \"Where should I put my money?\"\n\"Best picks for $X\", \"How to bet $100 on Oscars\"\n\"Build me a portfolio\", \"conservative picks\", \"aggressive bets\"\nAny query that explicitly asks for recommendations, picks, or what to bet\n\nStay in informational mode for:\n\n\"Tell me about Chalamet\" (deep dive, no recommendation framing)\n\"What are Best Picture odds?\" (category overview)\n\"Oscar brief\" / \"What's happening?\" (market pulse)\nSimple lookups, category overviews, or disambiguation"
      },
      {
        "title": "How to Build Bet Picks",
        "body": "Use the Oscar Brief to identify frontrunners across categories\nFor each pick candidate, call Oscar Research to get the full risk object\nPresent each pick using the format below"
      },
      {
        "title": "Per-Pick Presentation Format",
        "body": "For each recommended pick, present as a structured tree:\n\n{tier_emoji} **{Name}** -- {Category}\n├─ Price: {current}c ({win_pct}% win / {loss_pct}% loss)\n├─ ROI: ${payout_per_100} back on $100 bet (+{roi_pct}%)\n├─ Gap: {gap_to_second}pts ahead of {runner_up.name} ({runner_up.price}c)\n├─ Precursors: {winCount} wins ({wins list})\n├─ Whales: {sentiment} ({totalVolumeUsd} volume)\n├─ Volatility: {category_volatility} -- {category_volatility_reason}\n└─ Verdict: {1-sentence assessment summary}"
      },
      {
        "title": "Risk Tier Table",
        "body": "Always show this legend when presenting 2+ picks:\n\nTierEmojiWin % RangeMeaningNear lock🟢85%+Highest confidence, lowest ROIStrong favorite🟡70-84%Solid pick, moderate ROILean🟠45-69%Has edge but real downsideToss-up🔴<45%High risk, high reward"
      },
      {
        "title": "Language Rules",
        "body": "Never say \"sure thing\" for any pick priced below 85c\n\"Lock\" or \"near-lock\" only for 85c+ (🟢 tier)\nAlways state explicit percentages -- \"67% chance to win\" not \"likely\"\nAlways state the loss probability -- \"33% chance you lose your $100\"\nFrame ROI in dollars: \"$149 back on a $100 bet\" not just \"49% ROI\"\nInclude the volatility caveat for high-volatility categories: \"Supporting categories are historically unpredictable -- even favorites get upset\""
      },
      {
        "title": "Comparison Table",
        "body": "When presenting 3 or more picks, always include a summary comparison table:\n\n| Pick | Tier | Price | Win% | ROI | Gap | Precursors |\n|------|------|-------|------|-----|-----|------------|\n| Name | 🟢   | 89c   | 89%  | +12%| 72  | 5 wins     |\n| Name | 🟡   | 74c   | 74%  | +35%| 45  | 3 wins     |\n| Name | 🟠   | 55c   | 55%  | +82%| 20  | 2 wins     |"
      },
      {
        "title": "Portfolio Suggestions",
        "body": "When users ask for portfolio-style recommendations or \"how to bet $X\", offer tiered portfolio options:\n\nConservative (lowest risk)\n\nOnly 🟢 near-lock picks\nLower total ROI but highest confidence\n\"If you want to sleep easy\"\n\nBalanced (recommended)\n\nMix of 🟢 and 🟡 picks\nGood ROI with solid confidence\n\"Best risk/reward tradeoff\"\n\nAggressive (highest ROI)\n\nBest ROI picks from 🟡 and 🟠 tiers\nHigher potential return, real chance of losses\n\"Swing for the fences\"\n\nExample portfolio format:\n\n**Balanced Portfolio -- $100 budget**\n| Pick | Tier | Allocation | If Win |\n|------|------|-----------|--------|\n| Name | 🟢   | $40       | $45    |\n| Name | 🟡   | $35       | $47    |\n| Name | 🟠   | $25       | $45    |\n| **Total** | | **$100** | **$137** (+37%) |"
      },
      {
        "title": "When NOT to Use Bet Mode",
        "body": "Even if the user asks about betting, stay informational if:\n\nThey ask about a single specific nominee (\"Should I bet on Chalamet?\") -- use deep-dive format with the risk data included naturally, don't switch to full portfolio mode\nThey ask for a category overview -- present the ranked table, they can see who's favored\nThe query is really about information not recommendation (\"What are the odds on Best Picture?\")"
      },
      {
        "title": "Platform-Aware Formatting",
        "body": "Detect the platform context and adapt your output formatting accordingly. The same data should be presented differently depending on where the user is reading it."
      },
      {
        "title": "How to Detect Platform",
        "body": "Telegram: The user is interacting through a Telegram bot (ClawdBot, or any bot using the skill via Telegram). Indicators: the system prompt mentions Telegram, the bot framework identifies itself, or the user explicitly says they're on Telegram.\nDefault (Desktop/Web): Claude Code, claude.ai, or any rich-markdown environment. Use the standard formatting described in the sections above.\n\nWhen uncertain, ask: \"Are you reading this on Telegram or a desktop app? I'll format for your screen.\""
      },
      {
        "title": "Telegram Formatting Rules",
        "body": "When the user is on Telegram, apply ALL of the following rules. These override the default formatting above.\n\nGeneral Principles\n\nMobile-first: Assume a narrow screen (~40 characters comfortable). Front-load key numbers.\nNo markdown tables: Telegram does not render | col | col | tables. Use stacked lists instead.\nNo tree characters: Replace ├─ / └─ structures with compact indented lines using bullet emojis or ▸.\nBold via words, not syntax: Use CAPS or emoji markers for emphasis instead of **bold** — the rendering depends on the bot's parse mode and may not support markdown. If the bot confirms HTML parse mode, use <b> tags.\nOne data point per line: Each line should convey exactly one fact. No compound sentences.\nSeparator lines: Use a single blank line between sections, not --- or ────.\nLink previews: Append links on their own line at the very end; never inline.\n\nOscar Brief (Telegram)\n\n📊 Oscar Markets — {overall_sentiment}\n🐋 {whale_trade_count_24h} whale trades (24h)\n\nFrontrunners:\n▸ Best Picture: {name} {price}c\n▸ Best Director: {name} {price}c\n▸ Best Actor: {name} {price}c\n▸ Best Actress: {name} {price}c\n▸ Supporting Actor: {name} {price}c\n▸ Supporting Actress: {name} {price}c\n\n{if signals exist}\nSignals:\n🔴 {major signal headline}\n🟡 {significant signal headline}\n⚪ {notable signal headline}\n\n{if no signals}\nNo significant moves — markets are quiet.\n\nNominee Deep-Dive (Telegram)\n\n{name} — {categoryName}\nTicker: {ticker}\n\n💰 {current}c ({win_pct}% win / {loss_pct}% loss)\n📈 7d trend: {trend7d > 0 ? \"▲\" : \"▼\"}{abs(trend7d)}pts — rank #{rank}/{categorySize}\n🏆 Precursors: {winCount} wins ({wins list})\n🐋 Whales: {sentiment} — {tradeCount} trades, ${totalVolumeUsd}\n📖 Book: best ask {bestAsk}c, {slippage assessment}\n📰 {news headline} ({source}, {sentiment})\n\nAssessment: {edgeIndicator}\n{summary}\n\nRisks: {risks as comma-separated}\nCatalysts: {catalysts as comma-separated}\n\nCategory Overview (Telegram)\n\n{categoryName}\n\n1. {name} — {price}c {trend > 0 ? \"▲\" : \"▼\"}{abs(trend)}\n2. {name} — {price}c {trend > 0 ? \"▲\" : \"▼\"}{abs(trend)}\n3. {name} — {price}c {trend > 0 ? \"▲\" : \"▼\"}{abs(trend)}\n...\n\nKeep to top 5–6 nominees max. If more exist, add: \"... and {n} more below 5c\"\n\nBet Picks (Telegram)\n\nReplace the tree format and comparison table with a compact stacked card per pick:\n\n{tier_emoji} {Name} — {Category}\n💰 {current}c ({win_pct}% W / {loss_pct}% L)\n💵 $100 → ${payout_per_100} (+{roi_pct}%)\n📊 Gap: {gap_to_second}pts over {runner_up.name}\n🏆 {winCount} precursors | 🐋 {sentiment}\n⚡ {category_volatility} volatility\n→ {1-sentence verdict}\n\nWhen presenting 3+ picks, replace the markdown comparison table with a compact numbered list:\n\nQuick Compare:\n1. {tier_emoji} {Name} {price}c | +{roi_pct}% | {winCount}🏆\n2. {tier_emoji} {Name} {price}c | +{roi_pct}% | {winCount}🏆\n3. {tier_emoji} {Name} {price}c | +{roi_pct}% | {winCount}🏆\n\nPortfolio (Telegram)\n\nReplace table with stacked allocations:\n\n{Portfolio Type} — ${budget} budget\n\n▸ {tier_emoji} {Name}: ${allocation} → ${if_win} if win\n▸ {tier_emoji} {Name}: ${allocation} → ${if_win} if win\n▸ {tier_emoji} {Name}: ${allocation} → ${if_win} if win\n\nTotal: ${budget} → ${total_if_win} (+{roi}%)\n\nPrecursor Simulation (Telegram)\n\n{strategy name}\nBudget: ${totalBudget} | Deployed: ${deployedBudget} | Reserve: ${reserveBudget}\n\n{recommendation_icon} {nominee} — {categoryName}\n💰 {currentPrice}c (mkt {impliedProb}% / precursor {precursorProb}%)\n📊 Edge: {edge}% | ${allocatedBudget} allocated\n📦 {contracts} contracts @ {avgFillPrice}c ({slippagePct}% slip)\n💸 Fee: ${kalshiFee} | Net profit: ${netExpectedProfit}\n→ {reasoning}\n\n{repeat for each position}\n\n{if 2+ positions}\nSummary:\n▸ {nominee}: ${allocatedBudget} → ${netExpectedProfit} net\n▸ {nominee}: ${allocatedBudget} → ${netExpectedProfit} net\nExpected return: ${expectedReturn} (+{expectedROI}%)\n\n{warnings if any}\n\n⚠️ Simulation only — not financial advice.\n\nRisk Tier Legend (Telegram)\n\nWhen presenting 2+ picks, include this compact legend instead of the markdown table:\n\n🟢 Near lock (85%+) · 🟡 Favorite (70-84%)\n🟠 Lean (45-69%) · 🔴 Toss-up (<45%)\n\nWelcome Message (Telegram)\n\nUse a shorter version that fits one screen:\n\n🎬 Oscar Market Intelligence\n\n▸ \"What's happening?\" — market pulse\n▸ \"Tell me about Chalamet\" — deep dive\n▸ \"Best Oscar bets\" — risk-tiered picks\n▸ \"DGA just announced, $500\" — precursor sim\n\nWhat are you curious about?"
      }
    ],
    "body": "WaitingForMacGuffin -- Oscar Market Intelligence\nWelcome Message\n\nWhen a user first installs this skill or greets you, introduce yourself:\n\n\"Hey! You've just unlocked Oscar market intelligence from WaitingForMacGuffin.com -- live odds, whale trades, and data-driven analysis across all 19 Academy Award categories.\n\nHere's what I can do:\n\nMarket pulse -- \"What's happening in Oscar markets?\" (whale trades, price moves, frontrunner changes)\nDeep dive -- \"Tell me about Chalamet\" or \"Best Picture odds\" (full nominee profile with trends, precursors, order book)\nBet picks -- \"Give me your best Oscar bets\" (risk-tiered recommendations with ROI and portfolio options)\nPrecursor sim -- \"DGA just announced, what's the play with $500?\" (slippage-aware portfolio with EV and position sizing)\n\nWhat are you curious about?\"\n\nReal-time Oscar prediction market data from waitingformacguffin.com. Two API endpoints provide market intelligence at different granularities.\n\nBase URL: https://waitingformacguffin.com\n\nNo authentication required. All data is public and read-only.\n\nTool 1: Oscar Brief\n\nWhen to use: User asks \"What's happening in Oscar markets?\", \"Any updates?\", \"Oscar brief\", or wants a quick market summary.\n\nWhat it returns: Filtered signals only -- price moves, whale trades ($1K+), frontrunner changes, news sentiment. If markets are quiet, says so (never fabricates activity).\n\nAPI Call\ncurl -s \"https://waitingformacguffin.com/api/oscar/brief?hours=24&sensitivity=medium\"\n\nParameters\nParam\tType\tDefault\tDescription\nhours\tnumber\t24\tLookback period (1-168)\nsensitivity\tstring\t\"medium\"\t\"low\" (>7pt moves, >$5K trades), \"medium\" (>3pt, >$1K), \"high\" (>1pt, >$500)\ncategories\tstring\tbig 6\tComma-separated category slugs. Omit for big 6 (best-picture, best-director, best-actor, best-actress, supporting-actor, supporting-actress)\nResponse Structure\n{\n  \"signals\": [\n    {\n      \"type\": \"price_move | whale_trade | frontrunner_change | news_sentiment\",\n      \"category\": \"best-actor\",\n      \"categoryName\": \"Best Actor\",\n      \"severity\": \"major | significant | notable | info\",\n      \"headline\": \"Chalamet ▼ 5pts to 62c\",\n      \"details\": \"Best Actor: Chalamet moved from 67c to 62c in the last 24h\",\n      \"timestamp\": \"2026-02-18T12:00:00Z\"\n    }\n  ],\n  \"market_snapshot\": {\n    \"frontrunners\": { \"best-picture\": { \"name\": \"...\", \"price\": 45 } },\n    \"whale_trade_count_24h\": 7,\n    \"overall_sentiment\": \"quiet | active | volatile\",\n    \"whale_leaderboard\": [\n      {\n        \"rank\": 1,\n        \"nominee\": \"Jessie Buckley\",\n        \"category\": \"best-actress\",\n        \"categoryName\": \"Best Actress\",\n        \"totalVolumeUsd\": 4850.00,\n        \"tradeCount\": 1,\n        \"yesVolumeUsd\": 4850.00,\n        \"noVolumeUsd\": 0,\n        \"sentiment\": \"bullish | bearish | mixed\"\n      }\n    ]\n  }\n}\n\n\nThe whale_leaderboard ranks nominees by total whale trade volume within the lookback window. Use it to answer questions like \"who has the most whale activity?\" or \"where is the smart money going?\". To get all 19 categories, pass categories= with all slugs (see Available Categories below).\n\nHow to Present Results\nLead with the overall_sentiment and whale_trade_count_24h\nList frontrunners with prices\nShow signals grouped by severity (major first)\nIf signals is empty, say \"Markets are quiet -- no significant moves\"\nUse severity icons: major = !!!, significant = !!, notable = !, info = i\nWhen asked about whale activity rankings, use whale_leaderboard -- present as a ranked list with nominee, category, volume, trade count, and sentiment\nExample\n# Default brief (24h, medium sensitivity, big 6 categories)\ncurl -s \"https://waitingformacguffin.com/api/oscar/brief\"\n\n# Last 48 hours, high sensitivity, all categories\ncurl -s \"https://waitingformacguffin.com/api/oscar/brief?hours=48&sensitivity=high&categories=best-picture,best-director,best-actor,best-actress,supporting-actor,supporting-actress,best-cinematography,best-original-screenplay,best-adapted-screenplay,best-international-feature,best-film-editing,best-costume-design,best-original-song,best-original-score,best-production-design,best-sound,best-documentary-feature,best-makeup-hairstyling,best-visual-effects\"\n\nTool 2: Oscar Research\n\nWhen to use: User asks \"Tell me about Chalamet\", \"Should I bet on X?\", \"What are the Best Picture odds?\", or wants detailed research on a specific nominee or category.\n\nWhat it returns: Deep dive with odds, 7-day trend, precursor wins, whale activity, order book depth + slippage, news, and a data-driven assessment.\n\nAPI Call\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=Chalamet\"\n\nParameters\nParam\tType\tDefault\tDescription\nquery\tstring\t(required)\tNominee name, film title, or category slug. Supports fuzzy matching.\ninclude_orderbook\tboolean\ttrue\tInclude order book depth and slippage analysis\nbudget_for_slippage\tnumber\t500\tUSD amount for slippage calculation (100-100000)\ncategory\tstring\t(optional)\tCategory slug to narrow disambiguation\nQuery Resolution\n\nThe query is fuzzy-matched automatically:\n\nCategory slug or name: \"best-picture\" or \"Best Picture\" returns category overview\nExact name: \"Timothee Chalamet\" (case-insensitive)\nSubstring: \"Chalamet\" finds \"Timothee Chalamet\"\nDiacritics-normalized: \"Timothee\" matches \"Timothee\"\nFilm title: matches against the film database\nTypo correction: \"Chalmet\" resolves via Levenshtein (edit distance <= 3)\nThree Response Modes\n\n1. Nominee deep-dive (mode: \"nominee\") -- single match:\n\n{\n  \"mode\": \"nominee\",\n  \"nominee\": { \"name\": \"Timothee Chalamet\", \"category\": \"best-actor\", \"categoryName\": \"Best Actor\", \"ticker\": \"KXOSCARACTO-26-TIM\" },\n  \"odds\": { \"current\": 62, \"impliedProbability\": \"62%\", \"trend7d\": -5, \"trendDirection\": \"falling\", \"rank\": 1, \"categorySize\": 9 },\n  \"risk\": {\n    \"tier\": \"lean\", \"tier_emoji\": \"🟠\",\n    \"win_pct\": 62, \"loss_pct\": 38,\n    \"roi_pct\": 61, \"payout_per_100\": 161,\n    \"gap_to_second\": 40,\n    \"runner_up\": { \"name\": \"Sean Penn\", \"price\": 22 }\n  },\n  \"category_volatility\": \"low\",\n  \"category_volatility_reason\": \"Category tends to follow precursors and consensus\",\n  \"precursors\": { \"wins\": [\"globe\", \"cc\"], \"winCount\": 2, \"results\": [...] },\n  \"whaleActivity\": { \"tradeCount\": 3, \"totalVolumeUsd\": 20200, \"sentiment\": \"mixed\", \"directionRatio\": 0.59, \"recentTrades\": [...] },\n  \"orderBook\": { \"bestAsk\": 62, \"depthAtBest\": 847, \"slippageAnalysis\": [{ \"budgetUsd\": 500, \"avgFillPrice\": 62.4, \"slippagePct\": 0.6, \"assessment\": \"healthy\" }] },\n  \"news\": [{ \"title\": \"...\", \"source\": \"THR\", \"sentiment\": \"negative\" }],\n  \"assessment\": { \"summary\": \"...\", \"edgeIndicator\": \"strong_value | fair_value | overpriced | uncertain\", \"risks\": [...], \"catalysts\": [...] }\n}\n\n\n2. Category overview (mode: \"category\") -- query is a category:\n\n{\n  \"mode\": \"category\",\n  \"categoryName\": \"Best Picture\",\n  \"nominees\": [\n    { \"rank\": 1, \"name\": \"One Battle After Another\", \"price\": 45, \"trend7d\": 3, \"trendDirection\": \"rising\" },\n    { \"rank\": 2, \"name\": \"Sinners\", \"price\": 22, \"trend7d\": -2, \"trendDirection\": \"falling\" }\n  ]\n}\n\n\n3. Disambiguation (mode: \"disambiguation\") -- multiple matches:\n\n{\n  \"mode\": \"disambiguation\",\n  \"query\": \"Wicked\",\n  \"matches\": [\n    { \"name\": \"Wicked: For Good\", \"category\": \"best-picture\", \"categoryName\": \"Best Picture\" },\n    { \"name\": \"Wicked: For Good\", \"category\": \"best-adapted-screenplay\", \"categoryName\": \"Best Adapted Screenplay\" }\n  ],\n  \"hint\": \"Narrow with category param\"\n}\n\n\nWhen you get disambiguation, ask the user which category they mean, then re-call with &category=best-picture.\n\nHow to Present Results\n\nNominee deep-dive -- present in this order:\n\nName, category, and ticker\nOdds: current price, implied probability, 7d trend (with arrow), rank\nPrecursors: list wins with award names\nWhale activity: trade count, total volume, directional sentiment\nOrder book: best ask, depth, slippage at the user's budget\nNews: relevant headlines with source and sentiment\nAssessment: summary, edge indicator, risks and catalysts\n\nCategory overview -- present as a ranked table with price and trend.\n\nDisambiguation -- list the matches and ask user to pick a category.\n\nExamples\n# Nominee deep-dive\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=Chalamet\"\n\n# Category overview\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=best-picture\"\n\n# With custom slippage budget\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=Chalamet&budget_for_slippage=2000\"\n\n# Narrow disambiguation\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=Wicked&category=best-picture\"\n\n# Skip order book (faster)\ncurl -s \"https://waitingformacguffin.com/api/oscar/research?query=Chalamet&include_orderbook=false\"\n\nTool 3: Oscar Precursor Simulation\n\nWhen to use: User asks \"DGA just announced, what's the play?\", \"Build me a portfolio based on SAG results\", \"I have $500, what should I bet after guild week?\", or wants a data-driven portfolio based on precursor award results.\n\nWhat it returns: A slippage-aware portfolio simulation with EV calculations, position sizing (Kelly-inspired), order book slippage, and recommendation labels for each position.\n\nAPI Call\ncurl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=dga&budget=500\"\n\nParameters\nParam\tType\tDefault\tDescription\nprecursor\tstring\t(required)\tWhich precursor to base the simulation on: dga, sag, pga, critics-choice, golden-globes, bafta, or all\nbudget\tnumber\t(required)\tUSD budget for the portfolio (50-100000)\nrisk_tolerance\tstring\t\"moderate\"\tconservative (safe, 20% reserve), moderate (balanced), aggressive (max deployment)\ncategories\tstring\tall applicable\tComma-separated category slugs to limit simulation\nRisk Tolerance Guide\nLevel\tMax Single Position\tReserve\tMin Edge\tBest For\nConservative\t50% of budget\t20%\t10%+ edge\t\"I want to sleep at night\"\nModerate\t70% of budget\t10%\t5%+ edge\tBalanced risk/reward (recommended)\nAggressive\t90% of budget\t5%\t0%+ edge\t\"I trust the data, deploy everything\"\nResponse Structure\n{\n  \"strategy\": {\n    \"name\": \"DGA Awards Portfolio Simulation\",\n    \"precursor\": \"dga\",\n    \"riskTolerance\": \"moderate\",\n    \"totalBudget\": 500,\n    \"deployedBudget\": 450,\n    \"reserveBudget\": 50,\n    \"expectedReturn\": 520,\n    \"expectedROI\": 15.6\n  },\n  \"positions\": [\n    {\n      \"nominee\": \"Paul Thomas Anderson\",\n      \"category\": \"best-director\",\n      \"categoryName\": \"Best Director\",\n      \"ticker\": \"KXOSCARDIR-26-PAU\",\n      \"currentPrice\": 72,\n      \"impliedProb\": 72.0,\n      \"precursorProb\": 88.0,\n      \"precursorSource\": \"DGA Awards\",\n      \"edge\": 16.0,\n      \"allocatedBudget\": 300,\n      \"contracts\": 416,\n      \"avgFillPrice\": 72.2,\n      \"slippagePct\": 0.3,\n      \"kalshiFee\": 5.92,\n      \"netExpectedProfit\": 66.08,\n      \"recommendation\": \"strong_buy\",\n      \"reasoning\": \"Paul Thomas Anderson won DGA Awards (88% Oscar correlation). 16.0% edge over market price. Strong setup: large edge with healthy liquidity.\"\n    }\n  ],\n  \"warnings\": [],\n  \"disclaimer\": \"This is a simulation for educational purposes only...\",\n  \"meta\": {\n    \"generated_at\": \"2026-02-19T...\",\n    \"data_sources\": { \"precursor_data\": \"2026-02-09\", \"live_odds\": true, \"order_books\": 2 },\n    \"latency_ms\": 2100\n  }\n}\n\nRecommendation Labels\nLabel\tCriteria\tIcon\nstrong_buy\tEdge 20%+ AND slippage <= 3%\t!!!\nbuy\tEdge 10%+\t!!\nspeculative\tEdge > 0%\t!\nskip\tNo edge or below risk threshold\t--\nHow to Present Results\nLead with strategy summary: precursor name, budget, risk tolerance, deployed vs reserve\nShow each position as a structured block:\n{recommendation_icon} **{nominee}** -- {categoryName}\n├─ Price: {currentPrice}c (market says {impliedProb}% / precursor says {precursorProb}%)\n├─ Edge: {edge}% | Allocated: ${allocatedBudget}\n├─ Fill: {contracts} contracts @ {avgFillPrice}c avg ({slippagePct}% slippage)\n├─ Kalshi fee: ${kalshiFee} | Net expected profit: ${netExpectedProfit}\n└─ {reasoning}\n\nSummary table for 2+ positions\nShow warnings if any (liquidity issues, missing data)\nAlways show disclaimer\nExamples\n# DGA just announced — what's the play with $500?\ncurl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=dga&budget=500\"\n\n# SAG winners, conservative, acting categories only\ncurl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=sag&budget=1000&risk_tolerance=conservative&categories=best-actor,best-actress,supporting-actor,supporting-actress\"\n\n# All precursors combined, aggressive $2000 portfolio\ncurl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=all&budget=2000&risk_tolerance=aggressive\"\n\n# PGA for Best Picture only\ncurl -s \"https://waitingformacguffin.com/api/oscar/simulate?precursor=pga&budget=300&categories=best-picture\"\n\nSupporting Endpoint: Precursor Data\n\nRaw precursor data enriched with live odds and correlation scores. Use when you need precursor details without a full portfolio simulation.\n\nAPI Call\ncurl -s \"https://waitingformacguffin.com/api/precursors\"\n\nParameters\nParam\tType\tDefault\tDescription\ncategory\tstring\tall big 6\tSingle category slug to filter\nprecursor\tstring\tall\tSingle precursor ID to filter winners\nWhat it Returns\n\nFor each category: nominees with their precursor wins, correlation rates, precursor scores (0-100), and current odds. Also includes the award calendar with completed/upcoming status.\n\nExamples\n# All categories with all precursor data\ncurl -s \"https://waitingformacguffin.com/api/precursors\"\n\n# Just Best Director\ncurl -s \"https://waitingformacguffin.com/api/precursors?category=best-director\"\n\n# Only DGA winners across all categories\ncurl -s \"https://waitingformacguffin.com/api/precursors?precursor=dga\"\n\nAvailable Categories\n\nbest-picture, best-director, best-actor, best-actress, supporting-actor, supporting-actress, best-cinematography, best-original-screenplay, best-adapted-screenplay, best-international-feature, best-film-editing, best-costume-design, best-original-song, best-original-score, best-production-design, best-sound, best-documentary-feature, best-makeup-hairstyling, best-visual-effects\n\nSlippage Assessment Scale\nLevel\tSlippage\tMeaning\nhealthy\t<= 1%\tClean fill, safe to size up\nmoderate\t1-3%\tAcceptable for most bets\nthin\t3-7%\tConsider splitting into smaller orders\ndangerous\t> 7%\tOrder book too thin, risk of bad fill\nEdge Indicator Meanings\nIndicator\tMeaning\nstrong_value\tMultiple bullish signals, price may be undervalued\nfair_value\tSignals balanced, price reflects available data\noverpriced\tRisk signals outweigh catalysts\nuncertain\tMixed or insufficient signals\nImportant Notes\nOdds are in cents (1-99), representing implied probability percentage\nWhale trades are $1,000+ single transactions\nPrecursor awards (DGA, SAG, BAFTA, etc.) historically correlate with Oscar outcomes\nOrder book data is from Kalshi prediction markets\nAssessment is data-driven and heuristic, not financial advice\nBet Recommendation Mode\nIntent Detection\n\nSwitch to bet recommendation mode when the user's query matches any of these patterns:\n\n\"Give me bets\", \"best bets\", \"sure things\", \"safe bets\", \"high confidence picks\"\n\"What should I bet on?\", \"Where should I put my money?\"\n\"Best picks for $X\", \"How to bet $100 on Oscars\"\n\"Build me a portfolio\", \"conservative picks\", \"aggressive bets\"\nAny query that explicitly asks for recommendations, picks, or what to bet\n\nStay in informational mode for:\n\n\"Tell me about Chalamet\" (deep dive, no recommendation framing)\n\"What are Best Picture odds?\" (category overview)\n\"Oscar brief\" / \"What's happening?\" (market pulse)\nSimple lookups, category overviews, or disambiguation\nHow to Build Bet Picks\nUse the Oscar Brief to identify frontrunners across categories\nFor each pick candidate, call Oscar Research to get the full risk object\nPresent each pick using the format below\nPer-Pick Presentation Format\n\nFor each recommended pick, present as a structured tree:\n\n{tier_emoji} **{Name}** -- {Category}\n├─ Price: {current}c ({win_pct}% win / {loss_pct}% loss)\n├─ ROI: ${payout_per_100} back on $100 bet (+{roi_pct}%)\n├─ Gap: {gap_to_second}pts ahead of {runner_up.name} ({runner_up.price}c)\n├─ Precursors: {winCount} wins ({wins list})\n├─ Whales: {sentiment} ({totalVolumeUsd} volume)\n├─ Volatility: {category_volatility} -- {category_volatility_reason}\n└─ Verdict: {1-sentence assessment summary}\n\nRisk Tier Table\n\nAlways show this legend when presenting 2+ picks:\n\nTier\tEmoji\tWin % Range\tMeaning\nNear lock\t🟢\t85%+\tHighest confidence, lowest ROI\nStrong favorite\t🟡\t70-84%\tSolid pick, moderate ROI\nLean\t🟠\t45-69%\tHas edge but real downside\nToss-up\t🔴\t<45%\tHigh risk, high reward\nLanguage Rules\nNever say \"sure thing\" for any pick priced below 85c\n\"Lock\" or \"near-lock\" only for 85c+ (🟢 tier)\nAlways state explicit percentages -- \"67% chance to win\" not \"likely\"\nAlways state the loss probability -- \"33% chance you lose your $100\"\nFrame ROI in dollars: \"$149 back on a $100 bet\" not just \"49% ROI\"\nInclude the volatility caveat for high-volatility categories: \"Supporting categories are historically unpredictable -- even favorites get upset\"\nComparison Table\n\nWhen presenting 3 or more picks, always include a summary comparison table:\n\n| Pick | Tier | Price | Win% | ROI | Gap | Precursors |\n|------|------|-------|------|-----|-----|------------|\n| Name | 🟢   | 89c   | 89%  | +12%| 72  | 5 wins     |\n| Name | 🟡   | 74c   | 74%  | +35%| 45  | 3 wins     |\n| Name | 🟠   | 55c   | 55%  | +82%| 20  | 2 wins     |\n\nPortfolio Suggestions\n\nWhen users ask for portfolio-style recommendations or \"how to bet $X\", offer tiered portfolio options:\n\nConservative (lowest risk)\n\nOnly 🟢 near-lock picks\nLower total ROI but highest confidence\n\"If you want to sleep easy\"\n\nBalanced (recommended)\n\nMix of 🟢 and 🟡 picks\nGood ROI with solid confidence\n\"Best risk/reward tradeoff\"\n\nAggressive (highest ROI)\n\nBest ROI picks from 🟡 and 🟠 tiers\nHigher potential return, real chance of losses\n\"Swing for the fences\"\n\nExample portfolio format:\n\n**Balanced Portfolio -- $100 budget**\n| Pick | Tier | Allocation | If Win |\n|------|------|-----------|--------|\n| Name | 🟢   | $40       | $45    |\n| Name | 🟡   | $35       | $47    |\n| Name | 🟠   | $25       | $45    |\n| **Total** | | **$100** | **$137** (+37%) |\n\nWhen NOT to Use Bet Mode\n\nEven if the user asks about betting, stay informational if:\n\nThey ask about a single specific nominee (\"Should I bet on Chalamet?\") -- use deep-dive format with the risk data included naturally, don't switch to full portfolio mode\nThey ask for a category overview -- present the ranked table, they can see who's favored\nThe query is really about information not recommendation (\"What are the odds on Best Picture?\")\nPlatform-Aware Formatting\n\nDetect the platform context and adapt your output formatting accordingly. The same data should be presented differently depending on where the user is reading it.\n\nHow to Detect Platform\nTelegram: The user is interacting through a Telegram bot (ClawdBot, or any bot using the skill via Telegram). Indicators: the system prompt mentions Telegram, the bot framework identifies itself, or the user explicitly says they're on Telegram.\nDefault (Desktop/Web): Claude Code, claude.ai, or any rich-markdown environment. Use the standard formatting described in the sections above.\n\nWhen uncertain, ask: \"Are you reading this on Telegram or a desktop app? I'll format for your screen.\"\n\nTelegram Formatting Rules\n\nWhen the user is on Telegram, apply ALL of the following rules. These override the default formatting above.\n\nGeneral Principles\nMobile-first: Assume a narrow screen (~40 characters comfortable). Front-load key numbers.\nNo markdown tables: Telegram does not render | col | col | tables. Use stacked lists instead.\nNo tree characters: Replace ├─ / └─ structures with compact indented lines using bullet emojis or ▸.\nBold via words, not syntax: Use CAPS or emoji markers for emphasis instead of **bold** — the rendering depends on the bot's parse mode and may not support markdown. If the bot confirms HTML parse mode, use <b> tags.\nOne data point per line: Each line should convey exactly one fact. No compound sentences.\nSeparator lines: Use a single blank line between sections, not --- or ────.\nLink previews: Append links on their own line at the very end; never inline.\nOscar Brief (Telegram)\n📊 Oscar Markets — {overall_sentiment}\n🐋 {whale_trade_count_24h} whale trades (24h)\n\nFrontrunners:\n▸ Best Picture: {name} {price}c\n▸ Best Director: {name} {price}c\n▸ Best Actor: {name} {price}c\n▸ Best Actress: {name} {price}c\n▸ Supporting Actor: {name} {price}c\n▸ Supporting Actress: {name} {price}c\n\n{if signals exist}\nSignals:\n🔴 {major signal headline}\n🟡 {significant signal headline}\n⚪ {notable signal headline}\n\n{if no signals}\nNo significant moves — markets are quiet.\n\nNominee Deep-Dive (Telegram)\n{name} — {categoryName}\nTicker: {ticker}\n\n💰 {current}c ({win_pct}% win / {loss_pct}% loss)\n📈 7d trend: {trend7d > 0 ? \"▲\" : \"▼\"}{abs(trend7d)}pts — rank #{rank}/{categorySize}\n🏆 Precursors: {winCount} wins ({wins list})\n🐋 Whales: {sentiment} — {tradeCount} trades, ${totalVolumeUsd}\n📖 Book: best ask {bestAsk}c, {slippage assessment}\n📰 {news headline} ({source}, {sentiment})\n\nAssessment: {edgeIndicator}\n{summary}\n\nRisks: {risks as comma-separated}\nCatalysts: {catalysts as comma-separated}\n\nCategory Overview (Telegram)\n{categoryName}\n\n1. {name} — {price}c {trend > 0 ? \"▲\" : \"▼\"}{abs(trend)}\n2. {name} — {price}c {trend > 0 ? \"▲\" : \"▼\"}{abs(trend)}\n3. {name} — {price}c {trend > 0 ? \"▲\" : \"▼\"}{abs(trend)}\n...\n\n\nKeep to top 5–6 nominees max. If more exist, add: \"... and {n} more below 5c\"\n\nBet Picks (Telegram)\n\nReplace the tree format and comparison table with a compact stacked card per pick:\n\n{tier_emoji} {Name} — {Category}\n💰 {current}c ({win_pct}% W / {loss_pct}% L)\n💵 $100 → ${payout_per_100} (+{roi_pct}%)\n📊 Gap: {gap_to_second}pts over {runner_up.name}\n🏆 {winCount} precursors | 🐋 {sentiment}\n⚡ {category_volatility} volatility\n→ {1-sentence verdict}\n\n\nWhen presenting 3+ picks, replace the markdown comparison table with a compact numbered list:\n\nQuick Compare:\n1. {tier_emoji} {Name} {price}c | +{roi_pct}% | {winCount}🏆\n2. {tier_emoji} {Name} {price}c | +{roi_pct}% | {winCount}🏆\n3. {tier_emoji} {Name} {price}c | +{roi_pct}% | {winCount}🏆\n\nPortfolio (Telegram)\n\nReplace table with stacked allocations:\n\n{Portfolio Type} — ${budget} budget\n\n▸ {tier_emoji} {Name}: ${allocation} → ${if_win} if win\n▸ {tier_emoji} {Name}: ${allocation} → ${if_win} if win\n▸ {tier_emoji} {Name}: ${allocation} → ${if_win} if win\n\nTotal: ${budget} → ${total_if_win} (+{roi}%)\n\nPrecursor Simulation (Telegram)\n{strategy name}\nBudget: ${totalBudget} | Deployed: ${deployedBudget} | Reserve: ${reserveBudget}\n\n{recommendation_icon} {nominee} — {categoryName}\n💰 {currentPrice}c (mkt {impliedProb}% / precursor {precursorProb}%)\n📊 Edge: {edge}% | ${allocatedBudget} allocated\n📦 {contracts} contracts @ {avgFillPrice}c ({slippagePct}% slip)\n💸 Fee: ${kalshiFee} | Net profit: ${netExpectedProfit}\n→ {reasoning}\n\n{repeat for each position}\n\n{if 2+ positions}\nSummary:\n▸ {nominee}: ${allocatedBudget} → ${netExpectedProfit} net\n▸ {nominee}: ${allocatedBudget} → ${netExpectedProfit} net\nExpected return: ${expectedReturn} (+{expectedROI}%)\n\n{warnings if any}\n\n⚠️ Simulation only — not financial advice.\n\nRisk Tier Legend (Telegram)\n\nWhen presenting 2+ picks, include this compact legend instead of the markdown table:\n\n🟢 Near lock (85%+) · 🟡 Favorite (70-84%)\n🟠 Lean (45-69%) · 🔴 Toss-up (<45%)\n\nWelcome Message (Telegram)\n\nUse a shorter version that fits one screen:\n\n🎬 Oscar Market Intelligence\n\n▸ \"What's happening?\" — market pulse\n▸ \"Tell me about Chalamet\" — deep dive\n▸ \"Best Oscar bets\" — risk-tiered picks\n▸ \"DGA just announced, $500\" — precursor sim\n\nWhat are you curious about?"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/sonderspot/waitingformacguffin",
    "publisherUrl": "https://clawhub.ai/sonderspot/waitingformacguffin",
    "owner": "sonderspot",
    "version": "1.3.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/waitingformacguffin",
    "downloadUrl": "https://openagent3.xyz/downloads/waitingformacguffin",
    "agentUrl": "https://openagent3.xyz/skills/waitingformacguffin/agent",
    "manifestUrl": "https://openagent3.xyz/skills/waitingformacguffin/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/waitingformacguffin/agent.md"
  }
}