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.

skills.sh installs
547
GitHub stars
36
last updated
Aug 21, 2026

Install

$ npx -y skills add konata9/chinese-lottery-predict-skills --skill chinese-lottery-predict --agent claude-code

Installs into .claude/skills of the current project.

Files

中文彩票号码推荐

用于基于真实开奖数据为中国彩票生成仅供娱乐的号码推荐:

  • 双色球(SSQ)
  • 大乐透(DLT)

彩票开奖具有随机性。此 skill 必须始终包含清晰的风险提示,且不能声称结果“准确”“必中”或有任何保证。

何时使用

  • 用户要求基于真实开奖数据预测双色球或大乐透号码
  • 用户希望根据预算得到若干组推荐号码
  • 用户接受“仅供娱乐”的统计型建议,且允许联网获取真实数据

何时不要使用

  • 用户只是询问彩票规则、玩法、开奖时间或概率原理
  • 用户要求保证中奖、承诺准确率或提供带有误导性的结论
  • 用户未授权联网获取真实数据
  • 无法获取真实数据,但仍要求给出号码推荐

输入

  • 彩票类型:SSQ(双色球)或 DLT(大乐透)
  • 预算(可选):例如 10 元、50 元;如果用户未提供,默认按 10 元 处理
  • 推荐注数(可选):默认根据预算自动推导;按 2 元 / 组 计算

输出

返回一份中文报告,包含:

  • 数据来源标识(必须是真实数据)
  • 热号 / 冷号摘要
  • 推荐号码,并给出每组的简短理由
  • 预算建议
  • 风险提示

安全与确认

在执行联网数据获取前,先获得用户明确确认。

必须说明将按以下优先级获取真实数据:

  1. WebSearch
  2. WebFetch
  3. duckducksearch
  4. tavily-search

如果用户未授权联网,则直接停止,不允许退回模拟数据。

异常与停止条件

  • 无法识别彩票类型时,先用一句话澄清,不要继续生成号码
  • 预算不是有效整数时,要求用户重新提供
  • 用户未提供预算时,默认按 10 元 处理,并至少输出 5 组号码
  • 用户拒绝联网时,直接终止,不生成任何推荐号码
  • 任一优先级工具不可用时,按下一优先级继续尝试
  • 所有工具都无法获取真实数据时,直接报错终止,不允许使用模拟数据
  • 真实数据抓取成功但关键字段缺失、号码范围错误、号码数量错误或多来源结果冲突时,直接终止,并明确说明失败原因
  • 未能清晰标注数据来源 URL、抓取时间或来源名称时,不得输出推荐结果

工作流

Sponsors

Details

Repository
github.com/konata9/chinese-lottery-predict-skills
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs