菜单
Tiny demo skill bundled with `simmer backtest --demo`. Buys YES on liquid favorites to exercise the full backtest pipeline offline.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Pre-trade readiness check for autonomous agents. One call returns wallet identity, venue status, spendable balance, open exposure, and a structured ok_to_trade verdict. Run before every real-money trade to prevent cap overruns and catch config issues before they become P&L issues.
Mirror positions from top Polymarket traders. Polling mode (free) for portfolio-style copying, Reactor mode (Pro) for event-driven real-time mirroring via Simmer's on-chain signal infrastructure.
Trade Polymarket weather markets using NOAA (US) and Open-Meteo (international) forecasts via Simmer API. Inspired by gopfan2's weather trading approach. Use when user wants to trade temperature markets, automate weather bets, check forecasts, or run weather-based strategies.
Generate complete, installable OpenClaw trading skills from natural language strategy descriptions. Use when your human wants to create a new trading strategy, build a bot, generate a skill, automate a trade idea, turn a tweet into a strategy, or asks "build me a skill that...". Produces a full skill folder (SKILL.md + Python script + config) ready to install and run.
One-shot bootstrap for the Simmer MCP server. Detects your agent runtime (Claude Code / Cursor / OpenClaw / Hermes / Codex), installs simmer-mcp via npm, writes the right MCP config, prompts a restart, and verifies the tool handshake. Use after registering an agent on simmer.markets to run pre-built Simmer trading strategies through your MCP-aware agent.
The prediction market interface for AI agents. Trade Polymarket and Kalshi through one API with self-custody wallets, safety rails, and smart context.
| name | backtest-demo-favorites |
| description | Tiny demo skill bundled with `simmer backtest --demo`. Buys YES on liquid favorites to exercise the full backtest pipeline offline. |
| metadata | {"version":"1.0.0"} |
This is not a real trading strategy. It exists so simmer backtest --demo
produces a meaningful report (decisions, trades, settlements, hit_rate, pnl,
baselines) with no network access and no tape download.
Each tick it buys a small fixed amount of YES on the most liquid markets trading as favorites (YES price in a mid-to-high band), skipping anything it already holds. Run against the bundled 10-market demo slice, a handful of those favorites resolve YES (wins) and a handful resolve NO (losses), so the demo shows a realistic mixed outcome rather than "0 trades, stayed flat".
Entrypoint: favorites_demo.py (reads SIMMER_API_URL / SIMMER_API_KEY from
the replay harness; accepts and ignores --live / --quiet).
