This generates lottery number predictions for Chinese games like Double Color Ball and Super Lotto by scraping historical data from sites like zhcw.com and 500.com, then analyzing hot and cold numbers to produce recommendations. It has a four-level fallback system that tries direct scraping first, then search engines like DuckDuckGo, then WebSearch APIs, and finally falls back to static analysis if everything fails. The Node.js implementation handles edge cases like Spring Festival休市 periods when lotteries don't run. Obviously this is entertainment only since lottery draws are random, but the data retrieval strategy is surprisingly robust with cross-validation between sources. You get markdown reports in Chinese with budget-based buying suggestions.
npx skills add https://github.com/konata9/chinese-lottery-predict-skills --skill chinese-lottery-predict