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

A-Share All-Market Multi-Swing Defensive Signals

Screens the whole China A-share market for liquid trend-pullback buy candidates and flags rule-based exit signals for the stocks you already hold.

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

What it does

  • Builds a daily universe from the top N most liquid A-share stocks (default 120), including ChiNext and STAR Market names.
  • Computes daily-bar trend_pullback entry/exit conditions and returns two buy lists: from_previous_day_close (signal on the last closed bar, closer to a pre-planned setup) and from_last_close (latest bar, mostly for pattern display).
  • Applies a round-trip cost filter (default 45 bps, keeps only edge_after_cost > 0) and a parameter-neighborhood consensus filter (--entry-consensus-min, default 0.67); JSON output keeps both raw and filtered candidates.
  • Reads a holdings file (--holdings) and marks tickers whose latest bar meets the exit rule (loss of the slow MA, overheated RSI, etc.).
  • realtime_quotes.py pulls concurrent price snapshots (last price, % change, limit-up/down reference) and can append the latest intraday bar.
  • No backtesting, no equity curves, no automatic order placement — routing goes through your broker or the a-share-paper-trading skill.

Who it's for

  • Retail traders active in China A-shares who want a shortlist before the open.
  • Python/CLI-comfortable users who want JSON signals to plug into their own workflow.
  • Anyone who wants mechanical, rule-based exit checks on an existing portfolio.

Example uses

  1. python3 scripts/daily_decisions.py --top-n 120 --json — get buy candidates plus per-candidate filter flags as JSON.
  2. python3 scripts/daily_decisions.py --holdings ~/my_holdings.txt — see which held tickers triggered the strategy exit.
  3. python3 scripts/realtime_quotes.py 600519 000001 601318 --json --intraday — snapshot quotes with the latest 5-minute bar for cross-checking.

· · · 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-allmarket-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-allmarket-multi-swing-defensive folder from the GitHub repo shouldnotappearcalm/a-share-skill into my ~/.claude/skills/a-share-strategy-allmarket-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 /tmp/a-share-skill && mkdir -p ~/.claude/skills && cp -r /tmp/a-share-skill/a-share-strategy-allmarket-multi-swing-defensive ~/.claude/skills/

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

  1. Make sure Python 3 and git are installed: python3 --version, git --version.
  2. Clone the repository: git clone https://github.com/shouldnotappearcalm/a-share-skill.git
  3. Copy the skill into your Claude skills folder: mkdir -p ~/.claude/skills && cp -r a-share-skill/a-share-strategy-allmarket-multi-swing-defensive ~/.claude/skills/
  4. Install dependencies: pip install akshare pandas numpy requests
  5. Smoke-test it: python3 ~/.claude/skills/a-share-strategy-allmarket-multi-swing-defensive/scripts/daily_decisions.py --top-n 30 --json
  6. (Optional) Create a holdings file: one ticker per line, lines starting with # are comments.
  7. Restart Claude Code and ask something like "screen A-shares for buy candidates" or "check my holdings for exit signals" to trigger the skill.
View source on GitHub ↗License: MIT