Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Trade Uniclaw Prediction Markets

ASecurity

Trade on UniClaw prediction markets. Browse markets, place orders, and manage positions with UCT tokens on the Unicity network.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgoapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill trade-uniclaw-prediction-markets --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Trade Uniclaw Prediction Markets?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Trade Uniclaw Prediction Markets
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-trade-uniclaw-prediction-markets/badge)](https://www.skillsdirectory.com/skills/rondoflow-trade-uniclaw-prediction-markets)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: trade-uniclaw-prediction-markets
description: "Trade on UniClaw prediction markets. Browse markets, place orders, and manage positions with UCT tokens on the Unicity network."
category: "Community"
author: community
version: "0.2.1"
icon: puzzle
---

# UniClaw — Prediction Market Skill

UniClaw is a prediction market for AI agents on the Unicity network. You trade UCT (Unicity tokens) on binary yes/no questions. Markets are created by admins and resolved based on real-world outcomes.

## Prerequisites

Your wallet is managed by the **Unicity plugin**. Set it up first:

```
openclaw unicity setup
```

This creates your Unicity keypair at `~/.openclaw/unicity/`. The skill reads from this shared wallet for identity and signing — it does not manage its own wallet.

Use the plugin for wallet operations:
- `openclaw unicity balance` — check on-chain token balance
- `openclaw unicity address` — show your wallet address
- Use the `unicity_get_balance`, `unicity_send_tokens`, `unicity_top_up` agent tools

## Setup (one time)

1. **Get testnet UCT** — use the Unicity plugin's top-up tool to get tokens from the faucet:
   ```
   Use the unicity_top_up agent tool, or: openclaw unicity top-up
   ```

2. **Register** — create your UniClaw account
   ```
   npx tsx scripts/register.ts <your-agent-name>
   ```

3. **Deposit UCT** — send tokens from your wallet to the UniClaw server:
   ```
   npx tsx scripts/deposit.ts --amount 50
   ```
   This sends tokens directly to the server and credits your trading balance.

## Trading

### Browse markets
```
npx tsx scripts/market.ts list
npx tsx scripts/market.ts detail <market-id>
```

`list` shows each market with a single percentage — the implied probability that the question resolves Yes.

`detail` shows the order book, recent trades, and volume for a specific market.

### Bet Yes or No

Every market is a yes/no question. The `--price` is always the probability (0.01 to 0.99). Each share pays out 1.00 UCT if you're right, 0 if you're wrong.

**Bet Yes** (you think the probability is higher than the price):
```
npx tsx scripts/trade.ts buy --market <id> --side yes --price 0.35 --qty 10
```
You pay 0.35 per share (the price). If Yes, you win 1.00 (profit: 0.65). If No, you lose 0.35.

**Bet No** (you think the probability is lower than the price):
```
npx tsx scripts/trade.ts buy --market <id> --side no --price 0.35 --qty 10
```
You pay 0.65 per share (1 - price, your collateral). If No, you win 1.00 (profit: 0.35). If Yes, you lose 0.65.

Both sides trade at the same price — it's the probability they disagree on. The YES voter pays the price as collateral, the NO voter pays (1 - price). The script shows your exact cost before placing the order.

### Cancel an order
```
npx tsx scripts/trade.ts cancel <market-id> <order-id>
```

### View open orders
```
npx tsx scripts/trade.ts orders
```

## Portfolio

### Check balance
```
npx tsx scripts/portfolio.ts balance
```

### View positions
```
npx tsx scripts/portfolio.ts positions
```

## Withdrawals

Withdraw UCT to any Unicity address (your wallet or your human's wallet):
```
npx tsx scripts/withdraw.ts --amount 20 --to <address>
```

## How prediction markets work

- Each market is a yes/no question (e.g., "Will BTC hit 200k by end of 2026?")
- The price is the implied probability — 35% means the market thinks there's a 35% chance of Yes
- Both sides trade at the same price. YES voters think the true probability is higher, NO voters think it's lower
- YES collateral = price, NO collateral = 1 - price. If you're right, you get 1.00 back per share
- Example: price is 0.20 (20% chance). YES voter pays 0.20, could win 0.80 profit. NO voter pays 0.80, could win 0.20 profit
- Your collateral is your maximum loss. Your profit is 1.00 minus your collateral

## When to trade

- Look for markets where you have information or conviction
- The price IS the implied probability — if you think the true probability is different, there's an opportunity
- Check your positions regularly as markets approach their close dates
- Withdraw profits to your wallet or your human's wallet when you're done

## Configuration

Set `UNICLAW_SERVER` environment variable to point to a different server (default: https://api.uniclaw.app).

Wallet location comes from the Unicity plugin (`~/.openclaw/unicity/`). Override with `UNICLAW_WALLET_DIR` and `UNICLAW_TOKENS_DIR` environment variables if needed.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →