skills
Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data
- 248
- Shell
- MIT
- 6 mo ago
Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data
我把 Serenity 的研究方法做成了一个 AI Skill:输入任意一只 A股、港股、美股代码,它会告诉你这家公司是不是真卡点、值不值得深挖、估值还有多少空间,以及出现什么情况说明看错了。
AI agent plugins & managed-agent templates for China A-share market research and financial modeling, powered by Tushare. Research workflows and valuation tools for professional analyst review—not investment advice. | 面向中国 A 股市场的 AI 智能体插件与管理代理模板,基于 Tushare 数据驱动,提供行业研究与财务建模工具链。所有输出仅供专业分析师审阅参考,不构成任何投资建议。
Bottom-up driver-based revenue forecasting: base × penetration × share × price, with structural residual alignment, A/B/C data grading, Monte Carlo + tornado sensitivity, and annual-report segment extraction. Pure Python stdlib.
Evidence-backed finance research terminal: screen markets, dig into companies, and run an AI analyst where every number traces back to its source.
Open-source content pipeline for finance. Turns a company's SEC filings into a written equity-research brief with an audio edition and an optional narrated video, plus blog posts, product demo videos and social images. Authored in Claude Code over the RoboSystems and xbrlkit MCP servers, rendered locally in headless Chrome and ffmpeg.
Multi-stage LLM equity research agent that anchors deterministic bytes32 commitments of its trading decisions on Mantle for post-hoc verification, executes paper trades on Alpaca, and enforces a fractional-Kelly risk kernel. Built for the DoraHacks Turing Test Hackathon 2026.
AI-powered Indian stock research skill for Claude — verified live prices, GTT setups, confidence scoring & sentiment analysis for Nifty 100 stocks.
Live quant scoring, OOS pairs stat-arb, volatility cones
Runs in the browser on Hugging Face