PM Paper Trade Ops
Run, monitor, intervene in, and archive simulated prediction-market trading on oracle3. Simulation only: no real money, no live credentials.
- What
- Run, monitor, intervene in, and archive simulated prediction-market trading on oracle3. Simulation only: no real money, no live credentials.
- Cost
- Free
- Needs
- Use "PM Paper Trade Ops" with your Muse. This is a simulation skill: no real money is involved, and live credentials must never be used for a paper run.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
⚠️ **Trading warning / Avertissement trading** : informational only, not investment advice. This skill is a SIMULATION: paper trading uses no real money and places no real orders, and that is exactly its job; simulated fills are usually kinder than real ones, so good paper results are a filter, not a forecast of profit. Curated by Skill Harbor: the paper-trading runbook of oracle3, the open-source prediction-market engine for Polymarket, Kalshi, Solana and RSS event feeds. It starts a validated strategy in paper mode for a set duration, with an optional live monitor view, and runs the same control surface a live desk would use: status and state snapshots, pause and resume, hot-swapping the strategy mid-run, and stop. On any anomaly the rule is pause first, then decide. At the end, the run is archived properly: configuration, a state snapshot and the end-of-run summary go to a research folder, so every result can be replayed from its exact configuration (strategy reference, parameters, duration, venue). Two preconditions gate the start: the strategy passes validation, and at least one backtest or auto-tune result exists that a human can interpret. The skill's own hard rule is the safety core: never use live credentials during paper trading. From the YichengYang-Ethan/oracle3-prediction-market-agent repository (Apache-2.0). Honest caveats: a paper engine cannot reproduce a thin book fighting back, partial fills at the worst moment, or your own behaviour when real money moves; treat a stable paper run as permission to consider the next gate, nothing more. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into MuseThe install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Use "PM Paper Trade Ops" with your Muse. This is a simulation skill: no real money is involved, and live credentials must never be used for a paper run. Prerequisites: Python with the oracle3 package installed (pip install oracle3); a strategy that passes oracle3 strategy validate, plus at least one backtest or auto-tune result you have actually read. No venue account and no API keys are required. 1. Open the skill: https://github.com/YichengYang-Ethan/oracle3-prediction-market-agent/blob/main/skills/pm-paper-trade-ops/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Start this strategy in paper mode on Polymarket for one hour with the monitor on, and show me status and state snapshots as it runs." 3. At the end, archive the run (configuration, state snapshot, summary) and write down what would have to be true before you would even consider the live gates. Tip: on any anomaly, pause first and look, in that order; the skill is built around that reflex. Safety: a skill is plain-text instructions; it runs nothing by itself. Simulation only; the live path is a separate skill with explicit approval gates. Informational only, not investment advice.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.