Use when an agent needs to blend multiple evaluated quantitative factor signals into a single composite alpha signal (signal-level merge, not portfolio-level combination). Covers factor selection, redundancy removal, weighting, and composite evaluation.
Discover and validate cross-sectional alpha factors for Hong Kong and US equities - generate candidate factors, compute them, and screen by IC, decay, and turnover. Use when a user wants to mine, test, or rank overseas equity factors from Pandadata HK/US price and fundamental data rather than apply a fixed factor set.
Run one round of factor-pool recommendation from an existing stock alpha set. Use when an agent needs to start from user-provided seed factors, prepare mutation and crossover prompt packs for the current model to reason over, then evaluate generated factors by RankIC and RankICIR and output recommended factors for the…
A rule for improving stock-trading factors through changes, combinations, and performance checks. RankIC measures whether a factor correctly ranks investments; RankICIR compares that result with its consistency.
A natural-language screener for shares listed in mainland China’s A-share market. It turns written investment filters into verified Pandadata API queries and returns matching stocks with supporting evidence.
Use this prompt in Claude Code, Hermes, OpenClaw, or any agent runtime that does not natively discover SKILL.md folders. If the runtime supports native skill folders, install the full folder unchanged and load SKILL.md directly.