A-Share Turtle Trading Analysis

Problem it solves

A-share swing and short-term decisions often suffer from single-indicator bias: chasing hot themes without checking float size and seal quality, or holding a position and only seeking confirmation. Manual watchlists, stock screening, earnings checks, and risk checks can also become fragmented. This skill turns stock selection, analysis, monitoring, and review into an executable workflow, helping verify signals before entry and track entries/exits after position.

How it works

The skill centers on analyze.py and offers three scan levels: quick scans for watchlists, standard scans for curated pools, and detailed analyses for seven-stage reports. Key steps include:

• Industry research: outputs a TOP10 ranking for preset sectors such as robotics, AI compute, and new energy.
• Stock analysis: scores narrative logic, event catalysts, technicals, fundamentals, capital flow, and risk items.
• Signal grading: maps results into medium-term, short-term momentum, and hot-money signals with color-coded actions.
• Screenshot import: recognizes Shanghai, Shenzhen, and BSE codes from market screenshots or watchlist images.
• Adversarial review: when asked whether to buy, it forces counterarguments and flags confirmation bias instead of agreeing.

Data sources prefer free market data via data_fetcher, with optional TDX or natural-language financial search.

Boundaries

The output is probabilistic analysis, not investment advice. Hot-money signals are short-cycle and volatile, so stop-loss discipline matters. Daily scores change with price, volume, and capital flow; avoid overreacting to single-day moves. Automation depends on data-source stability, and key trades still need human confirmation.