MoltMarkets Agent

Complete MoltMarkets trading agent setup with autonomous trader, market creator, and resolution crons. Use when setting up a new MoltMarkets agent, configuring trading bots, or replicating the bicep agent architecture. Includes Kelly criterion betting, learning loops, and degenerate trader personality.

This skill appears to do what it says: it will use a MoltMarkets API key (stored in ~/.config/moltmarkets/credentials.json) to place bets, create markets, post comments, and resolve markets automatically. Before installing or running it: 1) Be aware this is an autonomous trading bot — it can spend your funds and create/resolve markets; consider using a low-balance or test account. 2) Confirm the API base (api.zcombinator.io/molt) is the legitimate MoltMarkets endpoint for your environment. 3) Review scripts/setup.js and cron definitions to understand what will be written to disk and what network calls will be made. 4) Because the registry metadata omits the required credential, expect to manually create the credentials file; treat the API key like a secret. 5) If you want to test safely, modify cron payloads or the code to run in a dry-run mode (log-only) before enabling live placement/resolution. 6) If unsure, ask the publisher for provenance (homepage/source) and prefer not to grant this skill access to any primary account until you've validated behavior in an isolated environment.

Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill Suspicious High-Entropy/Eval files: 1 The skill sets up multiple cron jobs for persistence and instructs the AI agent to perform extensive network operations (using `curl` commands) to interact with `api.zcombinator.io/molt` and external oracle APIs (Binance, CoinGecko, HN Algolia). It reads an API key from `~/.config/moltmarkets/credentials.json` and uses it for authenticated requests. While these capabilities (persistence, network access, credential usage) are plausibly needed for an 'autonomous trading agent,' the direct instruction for the agent to execute `curl` commands with an API key and the high degree of autonomy and persistence via cron jobs represent significant risky capabilities without clear malicious intent, classifying it as suspicious.