Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
bighardperson avatar

Stock Research Engine

  • 8 installs
  • 33 repo stars
  • Updated April 26, 2026
  • bighardperson/computer-science-skills-collection

Stock Research Engine is a Claude Code skill that produces a buy-side fund-manager-style deep-research brief on a single stock across A-share, HK, and US markets.

About

Stock Research Engine is a Claude Code skill that generates a buy-side fund-manager-style research brief on a single ticker across A-share, Hong Kong, and US markets. It runs a six-step framework covering market sentiment, fundamentals, management assessment, business breakdown, catalyst calendar, and a data-only valuation section, and it enforces dated, cross-verified sources with no fabrication. A developer uses it to quickly build up a fundamentals view on one or several stocks.

  • Buy-side fund-manager-style deep research on a single stock across A-shares, HK, and US markets
  • Enforces data discipline: dated sources, cross-verification, no fabrication
  • Six-step framework ending in a valuation-only data section with no buy/sell call

Stock Research Engine by the numbers

  • 8 all-time installs (skills.sh)
  • Ranked #820 of 1,106 Finance & Trading skills by installs in the Skillselion catalog
  • Data as of Jul 30, 2026 (Skillselion catalog sync)
At a glance

stock-research-engine capabilities & compatibility

Capabilities
trading · research · data analysis
Use cases
trading · research · data analysis
Runs
Runs locally
Pricing
Free
From the docs

What stock-research-engine says it does

买方基金经理视角的个股深度研究工具。
SKILL.md
**数据纪律**:所有财务数据标注时间节点和口径,无法获取的直接注明,绝不编造
SKILL.md
**第六步:估值水平展示** — 当前估值指标、历史分位、同业可比对比(纯数据,不下买卖结论)
SKILL.md
npx skills add https://github.com/bighardperson/computer-science-skills-collection --skill stock-research-engine

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs8
repo stars33
Last updatedApril 26, 2026
Repositorybighardperson/computer-science-skills-collection

What it does

Generate a buy-side deep-research brief on a single equity across A-share, HK, or US markets.

Who is it for?

Building a disciplined fundamentals brief on a single ticker with dated, cross-verified data.

Skip if: Producing a buy/sell recommendation; the valuation section is deliberately data-only and leaves the decision to the user.

When should I use this skill?

A user gives a stock code or company name or asks to analyze whether a stock is worth buying.

What you get

A 2000-4000 word Markdown brief covering sentiment, fundamentals, management, business, catalysts, and valuation data.

  • 2000-4000 word deep-research brief
  • catalyst calendar
  • valuation data section

By the numbers

  • 6-step research framework
  • target length 2000-4000 words
  • data older than two quarters is flagged with a warning

Files

SKILL.mdMarkdownGitHub ↗

个股研究引擎 3.0

买方基金经理视角的个股深度研究工具。用户输入公司代码或简称,按以下框架执行分析并输出Markdown格式简报。

核心原则

  • 投资决策导向:所有分析服务于"这个价格该不该买、买什么、赚什么钱"
  • 数据纪律:所有财务数据标注时间节点和口径,无法获取的直接注明,绝不编造
  • 数据时效性:搜索query必须带具体时间关键词;核心数据至少两个来源交叉验证;输出前自检数据新鲜度,超过两个季度的标注警告
  • 用户数据优先:如用户在对话中提供了数据,优先使用,不再重复搜索同一指标
  • 区分事实与观点:事实用客观陈述,观点用"我们认为/我们判断"明确标识
  • 信息密度优先:2000-4000字,杜绝套话,有观点有判断

角色设定

你是一位从业15年以上的买方基金经理,覆盖A股/H股/美股市场。分析风格:逻辑严密、观点锐利、不说废话、区分事实与传言。

数据来源优先级

根据标的所在市场选择数据源:

  • A股:tushare/akshare > 东方财富 > 雪球 > Yahoo Finance
  • 港股/美股:FMP > Yahoo Finance > 公司IR页面 > 东方财富
  • 公告原文:A股从巨潮资讯网获取,H股/美股从公司官网Investor Relations获取

分析框架(按顺序执行)

详细的分析框架见 references/analysis-framework.md

概要流程:

1. 第〇步:时间校准与数据锚定 — 确认日期,搜索最新收盘价、市值、核心估值指标 2. 第一步:市场情绪标签 — 搜索多渠道,输出主题标签,区分事实与传言,判断预期驱动还是业绩验证 3. 第二步:公司基本面速写 — 一句话定位、发展简史、股东治理、业务结构、产业链位置 4. 第三步:管理层评估 — 战略判断力、承诺兑现率、资本配置能力、激励机制、关键人物风险 5. 第四步:核心业务投资价值拆解 — 供需分析、盈利能力与财务健康度、竞争力、关键驱动因子、新业务/转型 6. 第五步:投资结论与跟踪框架 — 一句话本质、业务重点、催化剂日历、跟踪清单、风险分级 7. 第六步:估值水平展示 — 当前估值指标、历史分位、同业可比对比(纯数据,不下买卖结论)

输出规范

  • 格式:Markdown,结构清晰,重点加粗
  • 篇幅:2000-4000字
  • 态度:有观点有判断,不做面面俱到的研报式罗列;不确定的事项诚实标注
  • 估值模块:放在最末尾,客观呈现数据,不做值不值的判断,决策留给用户

Related skills

FAQ

Which markets does it cover?

A-shares, Hong Kong, and US stocks, choosing data sources such as tushare/akshare, Eastmoney, FMP, and Yahoo Finance by market.

Does it recommend buying or selling?

No. The valuation module presents data only and leaves the decision to the user.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.