PaperclipOrg
Claude Agent Skill · by Aradotso

Trump Code Market Signals

Install Trump Code Market Signals skill for Claude Code from aradotso/trending-skills.

Works with Paperclip

How Trump Code Market Signals fits into a Paperclip company.

Trump Code Market Signals drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.

S
SaaS FactoryPaired

Pre-configured AI company — 18 agents, 18 skills, one-time purchase.

$27$59
Explore pack
Source file
SKILL.md349 lines
Expand
---name: trump-code-market-signalsdescription: AI-powered analysis of Trump's social media posts to predict stock market movements using 31.5M brute-force tested rulestriggers:  - analyze trump posts for market signals  - run trump code prediction  - check today's trading signals from trump  - decode trump truth social posts  - trump market signal analysis  - run overnight brute force model search  - check surviving trading rules  - trump code cli predict --- # Trump Code — Market Signal Analysis > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. Trump Code is an open-source system that applies brute-force computation to find statistically significant patterns between Trump's Truth Social/X posting behavior and S&P 500 movements. It has tested 31.5M model combinations, maintains 551 surviving rules, and has a verified 61.3% hit rate across 566 predictions (z=5.39, p<0.05). ## Installation ```bashgit clone https://github.com/sstklen/trump-code.gitcd trump-codepip install -r requirements.txt``` ### Environment Variables ```bash# Required for AI briefing and chatbotexport GEMINI_KEYS="key1,key2,key3"       # Comma-separated Gemini API keys # Optional: for Claude Opus deep analysisexport ANTHROPIC_API_KEY="your-key-here" # Optional: for Polymarket/Kalshi integrationexport POLYMARKET_API_KEY="your-key-here"``` ## CLI — Key Commands ```bash# Today's detected signals from Trump's postspython3 trump_code_cli.py signals # Model performance leaderboard (all 11 named models)python3 trump_code_cli.py models # Get LONG/SHORT consensus predictionpython3 trump_code_cli.py predict # Prediction market arbitrage opportunitiespython3 trump_code_cli.py arbitrage # System health check (circuit breaker state)python3 trump_code_cli.py health # Full daily report (trilingual)python3 trump_code_cli.py report # Dump all data as JSONpython3 trump_code_cli.py json``` ## Core Scripts ```bash# Real-time Trump post monitor (polls every 5 min)python3 realtime_loop.py # Brute-force model search (~25 min, tests millions of combos)python3 overnight_search.py # Individual analysespython3 analysis_06_market.py        # Posts vs S&P 500 correlationpython3 analysis_09_combo_score.py   # Multi-signal combo scoring # Web dashboard + AI chatbot on port 8888export GEMINI_KEYS="key1,key2,key3"python3 chatbot_server.py# → http://localhost:8888``` ## REST API (Live at trumpcode.washinmura.jp) ```pythonimport requests BASE = "https://trumpcode.washinmura.jp" # All dashboard data in one calldata = requests.get(f"{BASE}/api/dashboard").json() # Today's signals + 7-day historysignals = requests.get(f"{BASE}/api/signals").json() # Model performance rankingsmodels = requests.get(f"{BASE}/api/models").json() # Latest 20 Trump posts with signal tagsposts = requests.get(f"{BASE}/api/recent-posts").json() # Live Polymarket Trump prediction markets (316+)markets = requests.get(f"{BASE}/api/polymarket-trump").json() # LONG/SHORT playbooksplaybook = requests.get(f"{BASE}/api/playbook").json() # System health / circuit breaker statestatus = requests.get(f"{BASE}/api/status").json()``` ### AI Chatbot API ```pythonimport requests response = requests.post(    "https://trumpcode.washinmura.jp/api/chat",    json={"message": "What signals fired today and what's the consensus?"})print(response.json()["reply"])``` ## MCP Server (Claude Code / Cursor Integration) Add to `~/.claude/settings.json`: ```json{  "mcpServers": {    "trump-code": {      "command": "python3",      "args": ["/path/to/trump-code/mcp_server.py"]    }  }}``` Available MCP tools: `signals`, `models`, `predict`, `arbitrage`, `health`, `events`, `dual_platform`, `crowd`, `full_report` ## Open Data Files All data lives in `data/` and is updated daily: ```pythonimport json, pathlib DATA = pathlib.Path("data") # 44,000+ Truth Social postsposts = json.loads((DATA / "trump_posts_all.json").read_text()) # Posts with signals pre-taggedposts_lite = json.loads((DATA / "trump_posts_lite.json").read_text()) # 566 verified predictions with outcomespredictions = json.loads((DATA / "predictions_log.json").read_text()) # 551 active rules (brute-force + evolved)rules = json.loads((DATA / "surviving_rules.json").read_text()) # 384 features × 414 trading daysfeatures = json.loads((DATA / "daily_features.json").read_text()) # S&P 500 OHLC historymarket = json.loads((DATA / "market_SP500.json").read_text()) # Circuit breaker / system healthcb = json.loads((DATA / "circuit_breaker_state.json").read_text()) # Rule evolution log (crossover/mutation)evo = json.loads((DATA / "evolution_log.json").read_text())``` ## Download Data via API ```pythonimport requests BASE = "https://trumpcode.washinmura.jp" # List available datasetscatalog = requests.get(f"{BASE}/api/data").json() # Download a specific fileraw = requests.get(f"{BASE}/api/data/surviving_rules.json").contentrules = json.loads(raw)``` ## Real Code Examples ### Parse Today's Signals ```pythonimport requests signals_data = requests.get("https://trumpcode.washinmura.jp/api/signals").json() today = signals_data.get("today", {})print("Signals fired today:", today.get("signals", []))print("Consensus:", today.get("consensus"))        # "LONG" / "SHORT" / "NEUTRAL"print("Confidence:", today.get("confidence"))      # 0.0–1.0print("Active models:", today.get("active_models", []))``` ### Find Top Performing Rules from Surviving Rules ```pythonimport json rules = json.loads(open("data/surviving_rules.json").read()) # Sort by hit rate descendingtop_rules = sorted(rules, key=lambda r: r.get("hit_rate", 0), reverse=True) for rule in top_rules[:10]:    print(f"Rule: {rule['id']} | Hit Rate: {rule['hit_rate']:.1%} | "          f"Trades: {rule['n_trades']} | Avg Return: {rule['avg_return']:.3%}")``` ### Check Prediction Market Opportunities ```pythonimport requests arb = requests.get("https://trumpcode.washinmura.jp/api/insights").json()markets = requests.get("https://trumpcode.washinmura.jp/api/polymarket-trump").json() # Markets sorted by volumeactive = [m for m in markets.get("markets", []) if m.get("active")]by_volume = sorted(active, key=lambda m: m.get("volume", 0), reverse=True) for m in by_volume[:5]:    print(f"{m['title']}: YES={m['yes_price']:.0%} | Vol=${m['volume']:,.0f}")``` ### Correlate Post Features with Returns ```pythonimport jsonimport numpy as np features = json.loads(open("data/daily_features.json").read())market   = json.loads(open("data/market_SP500.json").read()) # Build date-indexed return mapreturns = {d["date"]: d["close_pct"] for d in market} # Example: correlate post_count with next-day returnxs, ys = [], []for day in features:    date = day["date"]    if date in returns:        xs.append(day.get("post_count", 0))        ys.append(returns[date]) correlation = np.corrcoef(xs, ys)[0, 1]print(f"Post count vs same-day return: r={correlation:.3f}")``` ### Run a Backtest on a Custom Signal ```pythonimport json posts    = json.loads(open("data/trump_posts_lite.json").read())market   = json.loads(open("data/market_SP500.json").read()) returns  = {d["date"]: d["close_pct"] for d in market} # Find days with RELIEF signal before 9:30 AM ETrelief_days = [    p["date"] for p in posts    if "RELIEF" in p.get("signals", []) and p.get("hour", 24) < 9] hits = [returns[d] for d in relief_days if d in returns]if hits:    print(f"RELIEF pre-market: n={len(hits)}, "          f"avg={sum(hits)/len(hits):.3%}, "          f"hit_rate={sum(1 for h in hits if h > 0)/len(hits):.1%}")``` ## Key Signal Types | Signal | Description | Typical Impact ||--------|-------------|----------------|| `RELIEF` pre-market | "Relief" language before 9:30 AM | Avg +1.12% same-day || `TARIFF` market hours | Tariff mention during trading | Avg -0.758% next day || `DEAL` | Deal/agreement language | 52.2% hit rate || `CHINA` (Truth Social only) | China mentions (never on X) | 1.5× weight boost || `SILENCE` | Zero-post day | 80% bullish, avg +0.409% || Burst → silence | Rapid posting then goes quiet | 65.3% LONG signal | ## Model Reference | Model | Strategy | Hit Rate | Avg Return ||-------|----------|----------|------------|| A3 | Pre-market RELIEF → surge | 72.7% | +1.206% || D3 | Volume spike → panic bottom | 70.2% | +0.306% || D2 | Signature switch → formal statement | 70.0% | +0.472% || C1 | Burst → long silence → LONG | 65.3% | +0.145% || C3 ⚠️ | Late-night tariff (anti-indicator) | 37.5% | −0.414% | > **Note:** C3 is an anti-indicator — if it fires, the circuit breaker auto-inverts it to LONG (62% accuracy after inversion). ## System Architecture Flow ```Truth Social post detected (every 5 min)    → Classify signals (RELIEF / TARIFF / DEAL / CHINA / etc.)    → Dual-platform boost (TS-only China = 1.5× weight)    → Snapshot Polymarket + S&P 500    → Run 551 surviving rules → generate prediction    → Track at 1h / 3h / 6h    → Verify outcome → update rule weights    → Circuit breaker: if system degrades → pause/invert    → Daily: evolve rules (crossover / mutation / distillation)    → Sync data to GitHub``` ## Troubleshooting **`realtime_loop.py` not detecting new posts**- Check your network access to Truth Social scraper endpoints- Verify `data/trump_posts_all.json` timestamp is recent- Run `python3 trump_code_cli.py health` to see circuit breaker state **`chatbot_server.py` fails to start**- Ensure `GEMINI_KEYS` env var is set: `export GEMINI_KEYS="key1,key2"`- Port 8888 may be in use: `lsof -i :8888` **`overnight_search.py` runs out of memory**- Runs ~31.5M combinations — needs ~4GB RAM- Run on a machine with 8GB+ or reduce search space in script config **Hit rate dropping below 55%**- Check `data/circuit_breaker_state.json` — system may have auto-paused- Review `data/learning_report.json` for demoted rules- Re-run `overnight_search.py` to refresh surviving rules **Stale data in `data/` directory**- Daily pipeline syncs to GitHub automatically if running- Manually trigger: `python3 trump_code_cli.py report` to force refresh- Or pull latest from remote: `git pull origin main`