Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
Back to list

A-Share Market Analyst

A research assistant for China's A-share market: pulls data via AKShare, runs technical and fundamental analysis, screens stocks with multi-factor scoring, and formats reports.

Data & AnalyticsIntermediate662124AI score 7/10Last updated: Aug 9, 2026

What it does

  • Data access: uses the free open-source AKShare library for real-time A-share quotes, daily OHLC history, industry/concept sector performance, block-trade disclosures and money-flow data.
  • Technical analysis: computes MACD, KDJ, RSI and Bollinger Bands, recognises candlestick patterns, identifies trend plus support/resistance, and produces a technical score.
  • Fundamental analysis: revenue and profit growth, ROE, margins, and PE/PB/PS valuation metrics.
  • Stock screening: a ready-made multi-factor script that filters out ST and suspended tickers.
  • Reporting: fixed Markdown templates for a single-stock report and a daily watchlist.
  • Guardrails: no next-day price predictions, no definitive buy/sell orders, data timestamps required (quotes may be 15 minutes delayed), and conflicting indicators must be flagged as "signal divergence".

Who it's for

  • Retail investors and analysts researching Shanghai / Shenzhen / ChiNext listings.
  • Quant beginners who want Python-based data pulls and indicator math.
  • Anyone who wants an automated pre-market brief and watchlist each morning.
  • (Note) It explicitly excludes HK, US equities and crypto.

Examples

  1. "Give me today's A-share pre-market brief" → index moves, top 5 hot sectors, limit-up and consecutive limit-up names, northbound flow summary.
  2. "Run a technical analysis on 000001" → 60+ days of candles, MACD cross status, RSI level, support/resistance, and a star-rated report.
  3. "Screen for undervalued names in an uptrend" → runs the multi-factor script, drops ST/suspended tickers, and adjusts PE/PB versus momentum weights to output a candidate table.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/staruhub/ClaudeSkills/HEAD/lab/Geek-skills-a-share-analyst/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the lab/Geek-skills-a-share-analyst folder from the GitHub repo staruhub/ClaudeSkills into my ~/.claude/skills/a-share-analyst/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/staruhub/ClaudeSkills.git && mkdir -p ~/.claude/skills && cp -r ClaudeSkills/lab/Geek-skills-a-share-analyst ~/.claude/skills/a-share-analyst

This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/staruhub/ClaudeSkills.git
  2. Create the skills folder if needed: mkdir -p ~/.claude/skills
  3. Copy just this skill: cp -r ClaudeSkills/lab/Geek-skills-a-share-analyst ~/.claude/skills/a-share-analyst
  4. Install the data dependency: pip install akshare pandas (add --break-system-packages or use a virtualenv on managed Python installs).
  5. Restart Claude Code and run /skills to confirm a-share-analyst is listed.
  6. Test with a prompt like "analyze today's A-share market". If AKShare's API has changed and a function or column errors out, paste the error back to Claude so it can look up the current API instead of guessing.
  7. Treat all output as research only — it is not investment advice.