金融投研 Skill：用股票代码生成量化分析与 Word 投研报告
金融投研 Skill（@user_5e4a0654/baiji1）是 SkillHub 上的 professional 类社区技能，封装「智研助手」投研流水线：识别美港 A 股市场，经 yfinance/akshare 取数，计算技术、估值与风险指标并五维评分，可选 DeepSeek/OpenAI 解读，输出 PNG 图表与九章 Word 报告。本文说明 SkillHub 安装命令、Cursor 等 skills 目录、Python 依赖与环境变量，并给出 CLI 与 Streamlit 典型用法及数据延迟、字体与免责等注意点。
Read More咚指标编辑：在对话里生成咚语言指标公式
咚指标编辑是 SkillHub 上的专业类 Agent Skill，用于生成咚语言技术指标公式，语法基本兼容通达信、文华麦语言、同花顺与东方财富。支持模板调用、自然语言自定义编写及中英文语法查询，无需 API Key。本文说明其定位、核心能力，以及按 skillhub.cn 文档安装到 Cursor 等客户端 skills 目录的步骤，并给出官方示例 /dong-formula macd 与昨日最高价水平线用法及兼容性注意。
Read MoreA股量化数据分析：用 AkShare 把行情与财务查询交给 Agent
SkillHub 社区 Skill「A股量化数据分析」（@user_9e3b7930/akshare-stock-cn，v1.1.0）基于 AkShare 获取 A 股行情、财务与板块信息，提供可执行 CLI 并内置重试与错误处理，无需 API Key。文章说明其定位、核心能力、通过 skillhub 安装到 Cursor/Claude/Codex 等 skills 目录的方法，以及股票查询、行情、财务分析与选股类对话用法与使用注意。
Read Moredsh-bayes-predict: Estimating Individual Stock Rise Probability Using Bayes' Theorem in DSH
In DSH (DeepSeek Harness), when an agent analyzes a stock, it typically yields only a qualitative description. To determine the probability of a rise within the next N days, assess the current trend, or gauge the risk of holding the position, one must either run a separate quantitative script or switch to market software to manually track indicators. dsh-bayes-predict turns this into a DSH plugin: centered on the Bayesian theorem, it fuses multiple technical indicators into a posterior probability estimate for a "rise within N days" and outputs the results directly via two entry points: the chat interface and the browser panel. The following sections introduce its positioning, core features, and installation instructions. dsh-bayes-predict is a DSH individual stock prediction plugin based on the Bayesian theorem.
Read Moredsh-invest-research: DSH's End-to-End A-Share Investment Research Plugin
dsh-invest-research is an open-source investment research plugin for DeepSeek Harness (DSH) that integrates the "market, value, risk, institutional consensus, and valuation" five-layer research pipeline into a single call to output structured data. Its core functions include providing market snapshots (such as current price, PE, and PB), value scoring based on the Buffett 7-dimension framework (out of 100), risk scanning with six categories of alerts (including ST, valuation, and liquidity) scored on a scale of 0-100, displaying institutional consensus ratings and target prices, and conducting DCF-based conservative valuation and margin of safety analysis. Additionally, the plugin supports K-line technical indicators, hot sector rankings, multi-stock comparison, and Markdown research report generation. It supports codes for A-shares, Hong Kong, and US stocks, and features a single-layer data source independent fault tolerance mechanism to ensure that failures in individual data sources do not affect the overall process.
Read More