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

A-Share Mainboard Multi-Swing Defensive Signals

Generates buy candidates and exit signals for China A-share mainboard stocks using a daily trend-pullback strategy, plus batch real-time price snapshots.

Data & AnalyticsIntermediate★ 242⑂ 46AI score 9/10Last updated: Sep 28, 2026

What it does

  • Builds a daily universe from the top N most liquid mainboard stocks (default 120).
  • Runs the trend_pullback strategy on daily bars to produce two buy lists: from_previous_day_close (signal from the last completed session — closest to a real trading plan) and from_last_close (latest bar, for pattern viewing).
  • Applies two extra filters: round-trip cost (edge_after_cost > 0) and parameter-neighborhood consensus (entry_consensus_ratio).
  • Reads a holdings file (--holdings) and flags positions that meet exit rules (slow-MA break, overheated RSI, etc.).
  • realtime_quotes.py fetches concurrent price snapshots (last price, change %, limit-up/down reference) with optional last intraday bar.

Who it's for

  • Retail traders active in China A-shares who want a short, filtered morning watchlist.
  • Quant beginners wiring a Python signal pipeline into a Claude Code agent.
  • Users who keep the signal layer separate from execution (e.g. pairing with a-share-paper-trading).

Examples

  1. "Give me today's buy candidates" → python3 scripts/daily_decisions.py --top-n 120 --json, then review the up-to-5 filtered names.
  2. "Should I exit anything in my portfolio?" → run with --holdings ~/my_holdings.txt to list positions triggering exit conditions.
  3. "Quote 600519 and 000001" → python3 scripts/realtime_quotes.py 600519 000001 --json --intraday.

· · · 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/shouldnotappearcalm/a-share-skill/HEAD/a-share-strategy-mainboard-multi-swing-defensive/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 a-share-strategy-mainboard-multi-swing-defensive folder from the GitHub repo shouldnotappearcalm/a-share-skill into my ~/.claude/skills/a-share-strategy-mainboard-multi-swing-defensive/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/shouldnotappearcalm/a-share-skill.git && mkdir -p ~/.claude/skills && cp -r a-share-skill/a-share-strategy-mainboard-multi-swing-defensive ~/.claude/skills/

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

  1. Open a terminal and move to the folder where you keep projects.
  2. Clone the repo: git clone https://github.com/shouldnotappearcalm/a-share-skill.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy this skill only: cp -r a-share-skill/a-share-strategy-mainboard-multi-swing-defensive ~/.claude/skills/
  5. Install Python dependencies: pip install akshare pandas numpy requests
  6. Restart Claude Code and ask something like "pick A-share buy candidates for today" to confirm the skill triggers.
  7. For sell signals, create ~/my_holdings.txt with one ticker per line (comments start with #) and pass it via --holdings.
View source on GitHub ↗License: MIT