← 返回 Skills 市场
94
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install kuanshu-tiku
功能描述
宽数题库项目入口，涵盖四套量化题库来源、仓库结构、常用命令与当前公网部署信息。
使用说明 (SKILL.md)
宽数题库
用途
当你需要查看、运行、扩展或部署“宽数题库”这个多来源量化题库项目时，使用这个技能。
适合这些场景：
- 需要快速理解项目是什么、当前公开站点是什么
- 需要确认仓库中已经接入了哪些题库来源
- 需要知道原始抓取、标准化数据和页面代码分别放在哪里
- 需要重新抓取、构建或检查部署前置条件
项目资源
- GitHub 仓库：https://github.com/aznikline/kuanshu-tiku
- 当前公开站点：https://quantics-bank.vercel.app
当前接入的题库来源
- OpenQuant：
openquant.co/questions - Brainstellar：
brainstellar.com/puzzles - QuantQuestion：
quantquestion.com - Jane Street：
janestreet.com/puzzles
当前总题量：1304 道。
目录结构
data/raw/说明：四套来源的原始索引与详情数据data/translations/说明：中文翻译与分批翻译产物src/data/questions.json说明：OpenQuant 标准化数据src/data/brainstellar-questions.json说明：Brainstellar 标准化数据src/data/quantquestion-questions.json说明：QuantQuestion 标准化数据src/data/janestreet-questions.json说明：Jane Street 标准化数据src/pages/index.astro说明：首页src/pages/questions/[slug].astro说明：统一详情页scripts/说明：抓取、构建、翻译和部署检查脚本
常用命令
安装依赖：
npm install
抓取与构建：
npm run data:index
npm run data:details
npm run data:brainstellar:index
npm run data:brainstellar:details
npm run data:brainstellar:build
npm run data:quantquestion:fetch
npm run data:janestreet:index
npm run data:janestreet:details
npm run data:janestreet:translate
npm run data:janestreet:build
npm run data:validate
npm run data:build
本地开发与验证：
npm run dev
npm run test
npm run check
npm run build
托管与发布
- GitHub 仓库保持 private
- 公网托管走 Vercel
Vercel 常用命令：
npx vercel whoami
npx vercel deploy dist --prod --yes
工作建议
如果你是第一次接手这个项目，建议按这个顺序：
- 读
README.md - 跑
npm run data:validate - 跑
npm run build - 看
src/pages/index.astro与src/pages/questions/[slug].astro - 如果改抓取链，再读
scripts/
什么时候用这个技能
- 想快速知道这个项目现在有哪些题库来源
- 想确认某道题属于哪个来源
- 想重新拉取 Brainstellar / Jane Street 等来源
- 想把本地最新内容重新部署到 Vercel
安全使用建议
This skill is an instructions-only helper for a repo; it appears coherent. Before running any commands it recommends, review the repository (especially scripts/ and package.json) to confirm what network requests and shell commands the data-fetch/build scripts perform. Running npm install and the data scripts will fetch external data and dependencies; run them in a controlled environment (container/VM) if you are concerned. If you plan to deploy to Vercel, be aware that npx vercel deploy will use your Vercel account and credentials — do not expose secrets to any unreviewed scripts. In short: the skill itself is benign and aligns with its description, but exercise standard caution and inspect the repo code before executing build/fetch/deploy commands.
功能分析
Type: OpenClaw Skill
Name: kuanshu-tiku
Version: 0.1.1
The skill bundle serves as a documentation and operational guide for a quantitative finance question bank project. It contains standard project metadata, directory structures, and common development/deployment commands (npm, Vercel) consistent with its stated purpose. No malicious code, data exfiltration patterns, or harmful prompt injections were found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name/description match SKILL.md content: it documents repository structure, data sources, common commands and deployment info. It does not request unrelated credentials, binaries, or system access.
Instruction Scope
Runtime instructions are limited to repository navigation, npm scripts, and Vercel deploy commands. They reference repo files and external data sources (the four listed providers) which is consistent with the stated purpose. Note: following the documented commands will execute project scripts and network fetches (expected for a data-scraping/build workflow).
Install Mechanism
No install spec or code files are included — the skill is instruction-only, so nothing is written to disk by an installer. This is the lowest-risk install model.
Credentials
The skill declares no required environment variables or credentials. However, practical use (npm install, running data-fetch scripts, or npx vercel deploy) typically requires network access and, for deployment, Vercel/GitHub credentials — those are not requested by the skill itself, which is appropriate.
Persistence & Privilege
always:false and normal model invocation settings. The skill does not request persistent system-level privileges or modify other skills' configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install kuanshu-tiku - 安装完成后，直接呼叫该 Skill 的名称或使用
/kuanshu-tiku触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.1
Refresh project metadata for four-source puzzle sync and Vercel hosting.
v0.1.0
- Initial release of kuanshu-tiku skill.
- Provides concise entry instructions and usage scenarios for the Kuanshu Tiku Chinese quantitative interview question bank project.
- Lists project resources, including GitHub repository and Pages site.
- Details directory structure and describes the purpose of key folders and files.
- Includes common commands for data fetching, validation, site development, and deployment.
- Offers workflow conventions and step-by-step suggestions for new contributors.
元数据
常见问题
宽数题库 是什么？
宽数题库项目入口，涵盖四套量化题库来源、仓库结构、常用命令与当前公网部署信息。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 94 次。
如何安装 宽数题库？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install kuanshu-tiku」即可一键安装，无需额外配置。
宽数题库 是免费的吗？
是的，宽数题库 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
宽数题库 支持哪些平台？
宽数题库 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 宽数题库？
由 Mason（@aznikline）开发并维护，当前版本 v0.1.1。
推荐 Skills