stock-deep-research-analysis-skills

A-share stock deep-dive analysis standardizes inputs like stock code and benchmark date to execute serial, iterative dimension exploration. This builds a high-density research thesis with explicit evidence standards and confidence levels.

The 唐氏 deep research method applies serial, convergent and divergent exploration across fixed dimensions to gather evidence fast. It validates source credibility and clearly states confidence levels alongside evidence gaps when data is incomplete.

High-density stock research reports are generated by ingesting latest stock-specific information through first-round exploration dimensions. The output integrates fundamental and technical evidence while explicitly stating timelines, confidence levels, and data gaps.

Yes, the deep-dive analysis skill is designed to handle incomplete data by validating source credibility and clearly stating confidence levels and evidence gaps. It requires initializing current time and benchmark dates to ensure context timeliness.

You must initialize current time, stock name, stock code, benchmark date, and user requirements to ensure context is current. These initialization inputs define the scope before executing first-round exploration dimensions.

Yes, the stock deep-dive research skill supports integrating both fundamental and technical evidence to produce action-oriented insights. It standardizes evidence gathering to ensure conclusions are timely and evidence-based.