Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill implements a systematic fraud-detection checklist for A-share annual reports, based on Tang Chao's methodology. It fetches structured financial data via Tushare API, optionally downloads the annual report PDF, and runs 28 rules across 7 layers. The output is a formatted report with per-rule verdicts from PASS to FAIL and an overall risk rating. It helps financial risk specialists, equity research analysts, and Chinese value investors screen companies for red flags before making decisions.
WHO IT'S FOR
Financial Risk Specialists
analyze A-share fraud risks using checklist
A-Share Equity Researchers
screen A-share stocks for financial red flags
Audit Professionals
validate financial statement integrity with checklist
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
Claude Code one-click installation
Installs: Installs the Financial Report Minesweeper bundle, including the minesweeper skill and the annual-report download skill. · Claude Code
Before you start
Claude Code CLI
Python 3.9+
Tushare Pro Token
Git CLI to run the documented clone command
In a terminal, clone the repository, enter its project directory, and run the installer. During installation, provide your Tushare Pro Token when prompted; the script saves it to `.env`.
git clone https://github.com/terancejiang/financial-report-minesweeper.git
cd financial-report-minesweeper
bash install.sh
Claude