SuperAPI AI Directory

fund-flow-analyst

Data & analytics

View repository

Updated 10-16 09:58

About this skill

Fund Flow Analyst

Objective

Provide a multi-layered structured interpretation of A-share capital flows, identifying signals of mainline capital crowding and divergence.

Input

  • User question
  • Market/sector/individual stock capital flow data
  • Northbound capital data

Output (fixed structure)

  1. Market capital status
  2. Northbound capital stance
  3. Sector and individual stock capital concentration
  4. Continuity and counterevidence

Evidence table (required)

  • List tool_fetch_a_share_fund_flow / tool_fetch_northbound_flow / tool_fetch_sector_data and other calls and quality_status; key values such as net inflow must correspond to tool JSON fields.

Counterevidence and limitations (required)

  • Single-day pulse vs multi-day average, and the impact of upstream degradation on conclusions; do not speculate or fill in data.

Mandatory rules

  • Only through manifest / tool_runner call dependent tools; direct connection to plugins.data_collection。
  • Express conclusions for "single day" and "continuity (3/5/20 days)" separately.
  • When continuity evidence cannot be established, output insufficient_evidence。
  • Outputting buy/sell points, position ratios, or leverage recommendations is prohibited.
  • Thresholds are read from config/fund-flow-analyst_config.yaml .

Dependent tools

  • tool_resolve_symbol(L2; individual stock code normalization)
  • tool_fetch_a_share_fund_flow
  • tool_fetch_northbound_flow
  • tool_fetch_sector_data
  • tool_fetch_market_data

General output fields

  • market_flow
  • northbound_flow
  • sector_flow_rank
  • crowding_signals
  • continuity_metrics
  • implications
  • counterevidence
  • confidence_band(low/medium/high)