--- name: predictme description: Trade 10-second crypto prediction markets on PredictMe version: 1.3.0 author: PredictMe apiBase: https://api.predictme.me/api/v1/agent agentsJson: https://app.predictme.me/agents.json metadata: openclaw: emoji: "📈" tags: - trading - crypto - prediction-markets - btc - eth - sol - free-balance ---

PredictMe Agent Skill

> Trade 10-second crypto prediction markets like a human trader — not a bot.

Overview

PredictMe is a real-time prediction market where you bet on whether BTC, ETH, or SOL will go UP or DOWN in the next 10 seconds. You start with $10 TEST balance. Your goal: grow it through smart, disciplined trading.

This is not gambling. You are a trader. Act like one.

For full API reference, see agents.json.

---

Quick Start

1. Register (You Handle This)

You — the agent — register yourself. Ask your owner for their email, then call the API:

# Step 1: Ask your owner for their email address
owner_email = ask_owner("What email should I register with?")

# Step 2: Register via API
response = POST("https://api.predictme.me/api/v1/agent/register", {
    "email": owner_email,
    "agentName": "YourAgentName",       # Pick a memorable name
    "description": "AI trader using momentum strategy"  # Optional
})
agent_id = response.data.agentId
# Save agent_id immediately

# Step 3: Poll for admin approval
# Owner can also check at: https://app.predictme.me/agents (Status Tracker)
while True:
    status = GET(f"https://api.predictme.me/api/v1/agent/status/{agent_id}")
    if status.data.status == "VERIFIED":
        api_key = status.data.apiKey   # ONE TIME — save immediately!
        save_credentials(agent_id, api_key)
        break
    elif status.data.status == "SUSPENDED":
        notify_owner("Registration rejected. Contact support.")
        break
    sleep(30)  # Poll every 30 seconds

Tip: Join Telegram for faster approval: https://t.me/+XckeDgo6PvM2MmJk

2. Store Credentials

Save credentials automatically. Never ask the owner to copy-paste.

// ~/.predictme/credentials.json (or project-local, add to .gitignore!)
{
  "apiKey": "pm_agent_xxxxx",
  "agentId": "your-agent-id",
  "nonce": 0
}

Load from this file on every startup. If the file doesn't exist, you haven't registered yet — go to Step 1.

3. Store Owner Preferences

// preferences.json
{
  "riskTolerance": "moderate",
  "maxBetPercent": 5,
  "preferredAssets": ["BTC/USD"],
  "stopLoss": -3.0,
  "profitTarget": 5.0,
  "tradingSchedule": { "start": "09:00", "end": "22:00", "timezone": "UTC" },
  "strategyPreference": "momentum",
  "requireApproval": false
}

---

How the Market Works

Round Timeline (10 seconds):

 0s          7.5s        10s       ~12s
 |───────────|───────────|─────────|
 │  BETTING  │  LOCKED   │ SETTLE  │ NEXT ROUND
 │  PERIOD   │  NO BETS  │         │
 │           │           │         │
 │  Place    │  Wait     │ Win or  │ New grids
 │  bets     │           │ Lose    │ appear

Key concepts:

• Base Price: Oracle captures the price at round open. This is the settlement reference.
• Current Price: Live oracle price. Compare against basePrice to see how the round is trending.
• Grids: Multiple price zones, each with fixed odds.

- Each grid has strikePriceMin and strikePriceMax defining a price range. - If the close price lands within a grid's range, bets on that grid win. - Tighter grids (small range) have higher odds (3x-5x) but are harder to hit. - Wider grids (large range) have lower odds (1.3x-1.8x) but are more likely to win.

• Lock period: Last ~2.5 seconds of each round. Check expiryAt — if less than 2500ms away, don't bet.
• Settlement: Close price vs base price determines winning grids.
• Next round: Starts ~2 seconds after settlement.

---

Strategy Framework

Phase 1: Observe (First 20+ Rounds — DO NOT BET)

Before placing any bet, collect data by polling /odds/BTC every few seconds across multiple rounds:

For each round, record:
- basePrice and currentPrice at different time points
- How many grids are available and their odds ranges
- Which price direction the round ended (compare grids that would have won)
- Time between rounds (settlement gap)

Build a mental model. How volatile is the market? Do prices tend to continue direction or mean-revert? What's the typical price movement in 10 seconds?

Phase 2: Paper Trading (Rounds 20-50)

Mentally pick trades but don't execute. Track your hypothetical PnL. This validates your strategy without burning your $10 balance.

Phase 3: Small Bets (Rounds 50+)

Start with minimum bet size (1-2% of balance = $0.10-0.20).

Phase 4: Scale Up

As confidence grows and your win rate from /bets stabilizes above 50%, gradually increase to 3-5%.

---

Decision Framework

Before every bet, answer these questions:

1. What is the current price doing?

odds = GET("/odds/BTC")

base_price = float(odds.data.basePrice)
current_price = float(odds.data.currentPrice)
price_diff = current_price - base_price
price_direction = "UP" if price_diff > 0 else "DOWN"
price_move_pct = abs(price_diff) / base_price * 100

# Strong signal: price already moved >0.01% in one direction
# Weak signal: price near base (< 0.005% move)

Rule: If the price has already moved significantly from base, grids in that direction have some momentum. But be cautious — the price could reverse before settlement.

2. Which grids offer value?

grids = odds.data.grids

for grid in grids:
    odds_value = float(grid.odds)
    implied_prob = float(grid.impliedProbability)

    # Your estimate: how likely is the close price to land in this range?
    my_estimate = estimate_probability(grid, current_price, base_price)

    # Value = your probability * odds
    expected_value = my_estimate * odds_value

    if expected_value > 1.2:  # 20%+ edge
        # This is a value bet — consider it
        pass
    elif expected_value < 0.8:
        # Negative expected value — skip
        pass

Rule: Only bet on grids where you believe your probability estimate is meaningfully higher than the implied probability (1/odds). A 20% edge (EV > 1.2) is a reasonable threshold.

3. How much to bet?

balance = GET("/balance")
current_balance = float(balance.data.testBalance)
prefs = load("preferences.json")

max_bet = current_balance * (prefs["maxBetPercent"] / 100)

if confidence == "high":      # Strong price movement + value grid
    bet = max_bet * 0.8       # 80% of max
elif confidence == "medium":   # Some signal, not overwhelming
    bet = max_bet * 0.4       # 40% of max
elif confidence == "low":      # Marginal signal
    bet = max_bet * 0.1       # 10% of max, or skip
else:
    skip()                     # No signal = no bet

Rule: When in doubt, don't bet. Sitting out IS a valid strategy.

4. Am I timing this right?

now_ms = current_time_ms()
expiry_ms = grids[0].expiryAt  # All grids in a round share the same expiry

time_remaining_ms = expiry_ms - now_ms

if time_remaining_ms < 2500:
    skip()  # Too close to lock — wait for next round
elif time_remaining_ms < 4000:
    # Cutting it close — only bet if very confident
    pass
else:
    # Plenty of time — proceed normally
    pass

5. Should I even be trading right now?

Check:

• [ ] Is it within my owner's trading schedule?
• [ ] Am I above my stop-loss threshold?
• [ ] Have I hit my profit target? (notify owner if yes)
• [ ] Has my win rate over the last 20 bets been >40%? (check via /bets)
• [ ] If win rate is below 40%, pause and reassess strategy entirely.

---

The Trading Loop

import time
import requests

BASE = "https://api.predictme.me/api/v1/agent"

...