Prediction Market Oracle Research
affaan-m/ECC
Research prediction markets as data sources or oracle signals for products, agents, dashboards, and corporate decision intelligence.
Oscar prediction market intelligence from waitingformacguffin.com.
$ npx skills add LeoYeAI/openclaw-master-skills --skill waitingformacguffin -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills waitingformacguffin --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/waitingformacguffin .claude/skills/waitingformacguffin && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "waitingformacguffin" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/waitingformacguffin into .claude/skills/waitingformacguffin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waitingformacguffin", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/waitingformacguffinType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill waitingformacguffin -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills waitingformacguffin --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/waitingformacguffin .agents/skills/waitingformacguffin && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "waitingformacguffin" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/waitingformacguffin into .agents/skills/waitingformacguffin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waitingformacguffin", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill waitingformacguffin -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills waitingformacguffin --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/waitingformacguffin .cursor/skills/waitingformacguffin && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "waitingformacguffin" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/waitingformacguffin into .cursor/skills/waitingformacguffin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waitingformacguffin", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/waitingformacguffin--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill waitingformacguffin -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills waitingformacguffin --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/waitingformacguffin .gemini/skills/waitingformacguffin && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "waitingformacguffin" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/waitingformacguffin into .gemini/skills/waitingformacguffin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waitingformacguffin", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills waitingformacguffinInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill waitingformacguffin -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/waitingformacguffin .github/skills/waitingformacguffin && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "waitingformacguffin" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/waitingformacguffin into .github/skills/waitingformacguffin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waitingformacguffin", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill waitingformacguffin -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills waitingformacguffin --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/waitingformacguffin .opencode/skills/waitingformacguffin && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "waitingformacguffin" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/waitingformacguffin into .opencode/skills/waitingformacguffin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waitingformacguffin", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
waitingformacguffinOscar prediction market intelligence from waitingformacguffin.com.
Waitingformacguffin is an agent skill from LeoYeAI/openclaw-master-skills. Oscar prediction market intelligence from waitingformacguffin.com. Get live odds, whale activity, price movements, precursor awards, order book depth, and frontrunner changes across all 19 Oscar categories. Use when user asks about Oscar markets, betting odds, nominees, or wants a market update.
Its SKILL.md is about 6.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `_meta.json`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
Bash(curl *)ReadFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
curlFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
waitingformacguffin.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Waitingformacguffin loads about 6.5k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 1,853 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,853 words, ~6,533 tokens.
.claude/skills/waitingformacguffin/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.When a user first installs this skill or greets you, introduce yourself:
"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.
Here's what I can do:
What are you curious about?"
Real-time Oscar prediction market data from waitingformacguffin.com. Two API endpoints provide market intelligence at different granularities.
Base URL: https://waitingformacguffin.com
No authentication required. All data is public and read-only.
When to use: User asks "What's happening in Oscar markets?", "Any updates?", "Oscar brief", or wants a quick market summary.
What it returns: Filtered signals only -- price moves, whale trades ($1K+), frontrunner changes, news sentiment. If markets are quiet, says so (never fabricates activity).
curl -s "https://waitingformacguffin.com/api/oscar/brief?hours=24&sensitivity=medium"| Param | Type | Default | Description |
|---|---|---|---|
hours | number | 24 | Lookback period (1-168) |
sensitivity | string | "medium" | "low" (>7pt moves, >$5K trades), "medium" (>3pt, >$1K), "high" (>1pt, >$500) |
categories | string | big 6 | Comma-separated category slugs. Omit for big 6 (best-picture, best-director, best-actor, best-actress, supporting-actor, supporting-actress) |
{
"signals": [
{
"type": "price_move | whale_trade | frontrunner_change | news_sentiment",
"category": "best-actor",
"categoryName": "Best Actor",
"severity": "major | significant | notable | info",
"headline": "Chalamet ▼ 5pts to 62c",
"details": "Best Actor: Chalamet moved from 67c to 62c in the last 24h",
"timestamp": "2026-02-18T12:00:00Z"
}
],
"market_snapshot": {
"frontrunners": { "best-picture": { "name": "...", "price": 45 } },
"whale_trade_count_24h": 7,
"overall_sentiment": "quiet | active | volatile",
"whale_leaderboard": [
{
"rank": 1,
"nominee": "Jessie Buckley",
"category": "best-actress",
"categoryName": "Best Actress",
"totalVolumeUsd": 4850.00,
"tradeCount": 1,
"yesVolumeUsd": 4850.00,
"noVolumeUsd": 0,
"sentiment": "bullish | bearish | mixed"
}
]
}
}The 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).
overall_sentiment and whale_trade_count_24hsignals is empty, say "Markets are quiet -- no significant moves"whale_leaderboard -- present as a ranked list with nominee, category, volume, trade count, and sentiment# Default brief (24h, medium sensitivity, big 6 categories)
curl -s "https://waitingformacguffin.com/api/oscar/brief"
# Last 48 hours, high sensitivity, all categories
curl -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"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.
What it returns: Deep dive with odds, 7-day trend, precursor wins, whale activity, order book depth + slippage, news, and a data-driven assessment.
curl -s "https://waitingformacguffin.com/api/oscar/research?query=Chalamet"| Param | Type | Default | Description |
|---|---|---|---|
query | string | (required) | Nominee name, film title, or category slug. Supports fuzzy matching. |
include_orderbook | boolean | true | Include order book depth and slippage analysis |
budget_for_slippage | number | 500 | USD amount for slippage calculation (100-100000) |
category | string | (optional) | Category slug to narrow disambiguation |
The query is fuzzy-matched automatically:
1. Nominee deep-dive (mode: "nominee") -- single match:
{
"mode": "nominee",
"nominee": { "name": "Timothee Chalamet", "category": "best-actor", "categoryName": "Best Actor", "ticker": "KXOSCARACTO-26-TIM" },
"odds": { "current": 62, "impliedProbability": "62%", "trend7d": -5, "trendDirection": "falling", "rank": 1, "categorySize": 9 },
"risk": {
"tier": "lean", "tier_emoji": "🟠",
"win_pct": 62, "loss_pct": 38,
"roi_pct": 61, "payout_per_100": 161,
"gap_to_second": 40,
"runner_up": { "name": "Sean Penn", "price": 22 }
},
"category_volatility": "low",
"category_volatility_reason": "Category tends to follow precursors and consensus",
"precursors": { "wins": ["globe", "cc"], "winCount": 2, "results": [...] },
"whaleActivity": { "tradeCount": 3, "totalVolumeUsd": 20200, "sentiment": "mixed", "directionRatio": 0.59, "recentTrades": [...] },
"orderBook": { "bestAsk": 62, "depthAtBest": 847, "slippageAnalysis": [{ "budgetUsd": 500, "avgFillPrice": 62.4, "slippagePct": 0.6, "assessment": "healthy" }] },
"news": [{ "title": "...", "source": "THR", "sentiment": "negative" }],
"assessment": { "summary": "...", "edgeIndicator": "strong_value | fair_value | overpriced | uncertain", "risks": [...], "catalysts": [...] }
}2. Category overview (mode: "category") -- query is a category:
{
"mode": "category",
"categoryName": "Best Picture",
"nominees": [
{ "rank": 1, "name": "One Battle After Another", "price": 45, "trend7d": 3, "trendDirection": "rising" },
{ "rank": 2, "name": "Sinners", "price": 22, "trend7d": -2, "trendDirection": "falling" }
]
}3. Disambiguation (mode: "disambiguation") -- multiple matches:
{
"mode": "disambiguation",
"query": "Wicked",
"matches": [
{ "name": "Wicked: For Good", "category": "best-picture", "categoryName": "Best Picture" },
{ "name": "Wicked: For Good", "category": "best-adapted-screenplay", "categoryName": "Best Adapted Screenplay" }
],
"hint": "Narrow with category param"
}When you get disambiguation, ask the user which category they mean, then re-call with &category=best-picture.
Nominee deep-dive -- present in this order:
Category overview -- present as a ranked table with price and trend.
Disambiguation -- list the matches and ask user to pick a category.
# Nominee deep-dive
curl -s "https://waitingformacguffin.com/api/oscar/research?query=Chalamet"
# Category overview
curl -s "https://waitingformacguffin.com/api/oscar/research?query=best-picture"
# With custom slippage budget
curl -s "https://waitingformacguffin.com/api/oscar/research?query=Chalamet&budget_for_slippage=2000"
# Narrow disambiguation
curl -s "https://waitingformacguffin.com/api/oscar/research?query=Wicked&category=best-picture"
# Skip order book (faster)
curl -s "https://waitingformacguffin.com/api/oscar/research?query=Chalamet&include_orderbook=false"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.
What it returns: A slippage-aware portfolio simulation with EV calculations, position sizing (Kelly-inspired), order book slippage, and recommendation labels for each position.
curl -s "https://waitingformacguffin.com/api/oscar/simulate?precursor=dga&budget=500"| Param | Type | Default | Description |
|---|---|---|---|
precursor | string | (required) | Which precursor to base the simulation on: dga, sag, pga, critics-choice, golden-globes, bafta, or all |
budget | number | (required) | USD budget for the portfolio (50-100000) |
risk_tolerance | string | "moderate" | conservative (safe, 20% reserve), moderate (balanced), aggressive (max deployment) |
categories | string | all applicable | Comma-separated category slugs to limit simulation |
| Level | Max Single Position | Reserve | Min Edge | Best For |
|---|---|---|---|---|
| Conservative | 50% of budget | 20% | 10%+ edge | "I want to sleep at night" |
| Moderate | 70% of budget | 10% | 5%+ edge | Balanced risk/reward (recommended) |
| Aggressive | 90% of budget | 5% | 0%+ edge | "I trust the data, deploy everything" |
{
"strategy": {
"name": "DGA Awards Portfolio Simulation",
"precursor": "dga",
"riskTolerance": "moderate",
"totalBudget": 500,
"deployedBudget": 450,
"reserveBudget": 50,
"expectedReturn": 520,
"expectedROI": 15.6
},
"positions": [
{
"nominee": "Paul Thomas Anderson",
"category": "best-director",
"categoryName": "Best Director",
"ticker": "KXOSCARDIR-26-PAU",
"currentPrice": 72,
"impliedProb": 72.0,
"precursorProb": 88.0,
"precursorSource": "DGA Awards",
"edge": 16.0,
"allocatedBudget": 300,
"contracts": 416,
"avgFillPrice": 72.2,
"slippagePct": 0.3,
"kalshiFee": 5.92,
"netExpectedProfit": 66.08,
"recommendation": "strong_buy",
"reasoning": "Paul Thomas Anderson won DGA Awards (88% Oscar correlation). 16.0% edge over market price. Strong setup: large edge with healthy liquidity."
}
],
"warnings": [],
"disclaimer": "This is a simulation for educational purposes only...",
"meta": {
"generated_at": "2026-02-19T...",
"data_sources": { "precursor_data": "2026-02-09", "live_odds": true, "order_books": 2 },
"latency_ms": 2100
}
}| Label | Criteria | Icon |
|---|---|---|
strong_buy | Edge 20%+ AND slippage <= 3% | !!! |
buy | Edge 10%+ | !! |
speculative | Edge > 0% | ! |
skip | No edge or below risk threshold | -- |
{recommendation_icon} **{nominee}** -- {categoryName}
├─ Price: {currentPrice}c (market says {impliedProb}% / precursor says {precursorProb}%)
├─ Edge: {edge}% | Allocated: ${allocatedBudget}
├─ Fill: {contracts} contracts @ {avgFillPrice}c avg ({slippagePct}% slippage)
├─ Kalshi fee: ${kalshiFee} | Net expected profit: ${netExpectedProfit}
└─ {reasoning}# DGA just announced — what's the play with $500?
curl -s "https://waitingformacguffin.com/api/oscar/simulate?precursor=dga&budget=500"
# SAG winners, conservative, acting categories only
curl -s "https://waitingformacguffin.com/api/oscar/simulate?precursor=sag&budget=1000&risk_tolerance=conservative&categories=best-actor,best-actress,supporting-actor,supporting-actress"
# All precursors combined, aggressive $2000 portfolio
curl -s "https://waitingformacguffin.com/api/oscar/simulate?precursor=all&budget=2000&risk_tolerance=aggressive"
# PGA for Best Picture only
curl -s "https://waitingformacguffin.com/api/oscar/simulate?precursor=pga&budget=300&categories=best-picture"Raw precursor data enriched with live odds and correlation scores. Use when you need precursor details without a full portfolio simulation.
curl -s "https://waitingformacguffin.com/api/precursors"| Param | Type | Default | Description |
|---|---|---|---|
category | string | all big 6 | Single category slug to filter |
precursor | string | all | Single precursor ID to filter winners |
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.
# All categories with all precursor data
curl -s "https://waitingformacguffin.com/api/precursors"
# Just Best Director
curl -s "https://waitingformacguffin.com/api/precursors?category=best-director"
# Only DGA winners across all categories
curl -s "https://waitingformacguffin.com/api/precursors?precursor=dga"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
| Level | Slippage | Meaning |
|---|---|---|
| healthy | <= 1% | Clean fill, safe to size up |
| moderate | 1-3% | Acceptable for most bets |
| thin | 3-7% | Consider splitting into smaller orders |
| dangerous | > 7% | Order book too thin, risk of bad fill |
| Indicator | Meaning |
|---|---|
| strong_value | Multiple bullish signals, price may be undervalued |
| fair_value | Signals balanced, price reflects available data |
| overpriced | Risk signals outweigh catalysts |
| uncertain | Mixed or insufficient signals |
Switch to bet recommendation mode when the user's query matches any of these patterns:
Stay in informational mode for:
risk objectFor each recommended pick, present as a structured tree:
{tier_emoji} **{Name}** -- {Category}
├─ Price: {current}c ({win_pct}% win / {loss_pct}% loss)
├─ ROI: ${payout_per_100} back on $100 bet (+{roi_pct}%)
├─ Gap: {gap_to_second}pts ahead of {runner_up.name} ({runner_up.price}c)
├─ Precursors: {winCount} wins ({wins list})
├─ Whales: {sentiment} ({totalVolumeUsd} volume)
├─ Volatility: {category_volatility} -- {category_volatility_reason}
└─ Verdict: {1-sentence assessment summary}Always show this legend when presenting 2+ picks:
| Tier | Emoji | Win % Range | Meaning |
|---|---|---|---|
| Near lock | 🟢 | 85%+ | Highest confidence, lowest ROI |
| Strong favorite | 🟡 | 70-84% | Solid pick, moderate ROI |
| Lean | 🟠 | 45-69% | Has edge but real downside |
| Toss-up | 🔴 | <45% | High risk, high reward |
When presenting 3 or more picks, always include a summary comparison table:
| Pick | Tier | Price | Win% | ROI | Gap | Precursors |
|------|------|-------|------|-----|-----|------------|
| Name | 🟢 | 89c | 89% | +12%| 72 | 5 wins |
| Name | 🟡 | 74c | 74% | +35%| 45 | 3 wins |
| Name | 🟠 | 55c | 55% | +82%| 20 | 2 wins |When users ask for portfolio-style recommendations or "how to bet $X", offer tiered portfolio options:
Conservative (lowest risk)
Balanced (recommended)
Aggressive (highest ROI)
Example portfolio format:
**Balanced Portfolio -- $100 budget**
| Pick | Tier | Allocation | If Win |
|------|------|-----------|--------|
| Name | 🟢 | $40 | $45 |
| Name | 🟡 | $35 | $47 |
| Name | 🟠 | $25 | $45 |
| **Total** | | **$100** | **$137** (+37%) |Even if the user asks about betting, stay informational if:
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.
When uncertain, ask: "Are you reading this on Telegram or a desktop app? I'll format for your screen."
When the user is on Telegram, apply ALL of the following rules. These override the default formatting above.
| col | col | tables. Use stacked lists instead.├─ / └─ structures with compact indented lines using bullet emojis or ▸.**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.--- or ────.📊 Oscar Markets — {overall_sentiment}
🐋 {whale_trade_count_24h} whale trades (24h)
Frontrunners:
▸ Best Picture: {name} {price}c
▸ Best Director: {name} {price}c
▸ Best Actor: {name} {price}c
▸ Best Actress: {name} {price}c
▸ Supporting Actor: {name} {price}c
▸ Supporting Actress: {name} {price}c
{if signals exist}
Signals:
🔴 {major signal headline}
🟡 {significant signal headline}
⚪ {notable signal headline}
{if no signals}
No significant moves — markets are quiet.{name} — {categoryName}
Ticker: {ticker}
💰 {current}c ({win_pct}% win / {loss_pct}% loss)
📈 7d trend: {trend7d > 0 ? "▲" : "▼"}{abs(trend7d)}pts — rank #{rank}/{categorySize}
🏆 Precursors: {winCount} wins ({wins list})
🐋 Whales: {sentiment} — {tradeCount} trades, ${totalVolumeUsd}
📖 Book: best ask {bestAsk}c, {slippage assessment}
📰 {news headline} ({source}, {sentiment})
Assessment: {edgeIndicator}
{summary}
Risks: {risks as comma-separated}
Catalysts: {catalysts as comma-separated}{categoryName}
1. {name} — {price}c {trend > 0 ? "▲" : "▼"}{abs(trend)}
2. {name} — {price}c {trend > 0 ? "▲" : "▼"}{abs(trend)}
3. {name} — {price}c {trend > 0 ? "▲" : "▼"}{abs(trend)}
...Keep to top 5–6 nominees max. If more exist, add: "... and {n} more below 5c"
Replace the tree format and comparison table with a compact stacked card per pick:
{tier_emoji} {Name} — {Category}
💰 {current}c ({win_pct}% W / {loss_pct}% L)
💵 $100 → ${payout_per_100} (+{roi_pct}%)
📊 Gap: {gap_to_second}pts over {runner_up.name}
🏆 {winCount} precursors | 🐋 {sentiment}
⚡ {category_volatility} volatility
→ {1-sentence verdict}When presenting 3+ picks, replace the markdown comparison table with a compact numbered list:
Quick Compare:
1. {tier_emoji} {Name} {price}c | +{roi_pct}% | {winCount}🏆
2. {tier_emoji} {Name} {price}c | +{roi_pct}% | {winCount}🏆
3. {tier_emoji} {Name} {price}c | +{roi_pct}% | {winCount}🏆Replace table with stacked allocations:
{Portfolio Type} — ${budget} budget
▸ {tier_emoji} {Name}: ${allocation} → ${if_win} if win
▸ {tier_emoji} {Name}: ${allocation} → ${if_win} if win
▸ {tier_emoji} {Name}: ${allocation} → ${if_win} if win
Total: ${budget} → ${total_if_win} (+{roi}%){strategy name}
Budget: ${totalBudget} | Deployed: ${deployedBudget} | Reserve: ${reserveBudget}
{recommendation_icon} {nominee} — {categoryName}
💰 {currentPrice}c (mkt {impliedProb}% / precursor {precursorProb}%)
📊 Edge: {edge}% | ${allocatedBudget} allocated
📦 {contracts} contracts @ {avgFillPrice}c ({slippagePct}% slip)
💸 Fee: ${kalshiFee} | Net profit: ${netExpectedProfit}
→ {reasoning}
{repeat for each position}
{if 2+ positions}
Summary:
▸ {nominee}: ${allocatedBudget} → ${netExpectedProfit} net
▸ {nominee}: ${allocatedBudget} → ${netExpectedProfit} net
Expected return: ${expectedReturn} (+{expectedROI}%)
{warnings if any}
⚠️ Simulation only — not financial advice.When presenting 2+ picks, include this compact legend instead of the markdown table:
🟢 Near lock (85%+) · 🟡 Favorite (70-84%)
🟠 Lean (45-69%) · 🔴 Toss-up (<45%)Use a shorter version that fits one screen:
🎬 Oscar Market Intelligence
▸ "What's happening?" — market pulse
▸ "Tell me about Chalamet" — deep dive
▸ "Best Oscar bets" — risk-tiered picks
▸ "DGA just announced, $500" — precursor sim
What are you curious about?© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/waitingformacguffin of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Waitingformacguffin next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Waitingformacguffin this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~6.5k | Automated safety check: Pass | MIT | |
| Prediction Market Oracle Researchaffaan-m/ECC | 276k | 1 repos | ~577 | Automated safety check: Pass | MIT | |
| Genomic IntelligenceK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~6.2k | Automated safety check: Notes | MIT | |
| Autopilot Predictruvnet/ruflo | 74k | — | ~337 | Automated safety check: Pass | MIT | |
| Lead Intelligenceaffaan-m/ECC | 276k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Threat Intelligencesickn33/agentic-awesome-skills | 47k | 1 repos | ~1.1k | Automated safety check: Pass | MIT |
affaan-m/ECC
Research prediction markets as data sources or oracle signals for products, agents, dashboards, and corporate decision intelligence.
K-Dense-AI/scientific-agent-skills
Predicts regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights.
ruvnet/ruflo
Use learned patterns and current state to predict the optimal next action
affaan-m/ECC
AI原生的潜在客户情报与外联管道。取代Apollo、Clay和ZoomInfo,提供基于代理的信号评分、相互排名、温暖路径发现、来源驱动的语音建模以及跨电子邮件、LinkedIn和X的渠道特定外联。当用户想要查找、筛选并联系高价值联系人时使用。
sickn33/agentic-awesome-skills
Authorized OSINT and cyber threat intelligence: enriching IOCs, campaigns, impersonation, scams, and threat-actor profiles from public sources with defined boundaries.
affaan-m/ECC
Review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Oscar prediction market intelligence from waitingformacguffin.com. Waitingformacguffin is an agent skill from LeoYeAI/openclaw-master-skills.com.
Waitingformacguffin fits situations like: user asks about Oscar markets; wants a market update.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill waitingformacguffin -a claude-code`. Or copy the skill folder (skills/waitingformacguffin in LeoYeAI/openclaw-master-skills) into .claude/skills/waitingformacguffin in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill waitingformacguffin -a codex`. Or copy the skill folder (skills/waitingformacguffin in LeoYeAI/openclaw-master-skills) into .agents/skills/waitingformacguffin in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill waitingformacguffin -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/waitingformacguffin, .gemini/skills/waitingformacguffin, .github/skills/waitingformacguffin and .opencode/skills/waitingformacguffin in your project.
Going by SKILL.md and its folder, Waitingformacguffin needs the command-line tools its instructions call (curl). Its frontmatter pre-approves these tools: Bash(curl *), Read.
SKILL.md names 1 domain. In commands or code: waitingformacguffin.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Waitingformacguffin is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 6.5k tokens (SKILL.md is roughly 26k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Waitingformacguffin: Prediction Market Oracle Research (affaan-m/ECC, 276k stars), Genomic Intelligence (K-Dense-AI/scientific-agent-skills, 48k stars), Autopilot Predict (ruvnet/ruflo, 74k stars) and Lead Intelligence (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.