HN Showcase
Back to browse
Stock skill for OpenClaw 6,500 stocks, 900 days of data

Stock skill for OpenClaw 6,500 stocks, 900 days of data

by AaronBMoore·Feb 12, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidNiche GemSolve My Problem
The Take

You get momentum scores, RSI, EMA alignment, coil-breakout detection and concise bull/bear briefs out of the box — plus an OpenClaw skill so an LLM agent can answer “how's $NVDA looking?” immediately. The author ships 900+ days of backtested signals and open, dependency-free Python scripts which is refreshingly transparent, but the headline win-rate/return claims need independent audit (survivorship and lookahead bias are the obvious caveats) and the product looks focused on US/end-of-day use-cases.

Category
Finance
Target Audience

Backend developers, AI agent builders, quant/retail traders, bot makers integrating trading signals into apps or agents

Post Description

Hey HN. I built a financial intelligence skill for OpenClaw that turns your AI agent into a stock analyst.

Ask your agent 'how's $NVDA looking?' and you get back: momentum score (0-100), RSI, EMA alignment, coil breakout detection, bull/bear cases, and what to watch for. Not a price quote — a full intelligence briefing.

ClawHub has 5,700+ skills but zero equities intelligence. 672 financial skills were excluded for malware. I wanted to build something legitimate and transparent.

The data: 900+ days of backtested signals. 12,450+ total. 80% 5-day win rate, +4.51% average return. Win rate improves with holding period (76.5% at 1 day to 80.1% at 1 month). Every win and every loss tracked.

Technical: 7 Python scripts, zero pip dependencies (stdlib only). MIT licensed. VirusTotal verified clean.

Free tier available, no credit card. For comparison: Polygon.io charges $79-199/mo for raw data with no intelligence layer.

Would love feedback on the skill structure or scoring methodology. Happy to answer technical questions.

Similar Projects