Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Wade-DevCode/awesome-coding-skills-cn --skill domestic-stackgit clone --depth 1 https://github.com/Wade-DevCode/awesome-coding-skills-cnWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wade-devcode/awesome-coding-skills-cn/domestic-stack)<a href="https://agentmods.dev/skills/wade-devcode/awesome-coding-skills-cn/domestic-stack"><img src="https://agentmods.dev/badge/skills/wade-devcode/awesome-coding-skills-cn/domestic-stack/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wade-devcode/awesome-coding-skills-cn/domestic-stack"><img src="https://agentmods.dev/badge/skills/wade-devcode/awesome-coding-skills-cn/domestic-stack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.03034 |
| Opus 5.5 | $0.00013 | $0.01214 |
| Sonnet 5.5 | $0.00006 | $0.00607 |
| Haiku 4.5 | $0.00003 | $0.00303 |
Grade A, and why
domestic-stack scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
国内技术栈适配
何时用
- 开发微信小程序或 uniapp 项目,涉及页面、组件、API 调用时。
- 写 uniapp 多端适配逻辑,需要区分 APP / 小程序 / H5 平台差异时。
- 开发 SpringBoot 后端接口,涉及 Controller / Service / Mapper 分层设计时。
- 项目上线前检查合规、依赖源、CDN 等国内环境配置时。
核心规则
1. 小程序/uniapp 不照搬 web
规则: 微信小程序和 uniapp 运行在专属运行时,没有 window、document、localStorage 等 DOM/BOM 对象;setData 是性能敏感操作,频繁调用或传大对象会直接卡顿;整包 + 分包体积有硬性上限(主包 2 MB,总包 20 MB)。
为什么: AI 训练数据以 web 代码为主,极容易写出 document.querySelector、window.location.href、localStorage.setItem 这类在小程序里直接报 ReferenceError 的代码。对 setData 的误用更隐蔽:AI 常常在循环里每次更新一个字段就调用一次 setData,或者把整个巨型列表塞进去,运行时帧率立刻掉到个位数。
怎么做:
- 访问本地存储用
wx.setStorageSync/uni.setStorageSync,路由用wx.navigateTo/uni.navigateTo,DOM 操作改用数据绑定驱动视图。 - 批量更新时合并成一次
setData,用 path 精确更新而非替换整个对象(见正例)。 - 拆分包:业务模块放分包,避免主包塞太多资源;图片走 CDN 不打进包里。
2. uniapp 跨端用条件编译
规则: uniapp 跨 APP / 微信小程序 / H5 时,平台差异必须用 #ifdef APP-PLUS / #ifdef MP-WEIXIN / #ifdef H5 等条件编译块处理,不写死只在单端能跑的逻辑。
为什么: AI 在生成 uniapp 代码时经常直接调用 wx.* API 而不加条件编译,在 APP 端或 H5 端运行时这些调用会静默失败或抛异常。反过来也会犯:只写了 plus.* 的 APP 专属逻辑,发布 H5 版时整块功能缺失。这类 bug 在单端开发阶段完全看不出来,到多端上线时才暴露。
怎么做:
- 平台专属 API 用条件编译包裹,公共逻辑放在块外。
- 样式差异用
/* #ifdef MP-WEIXIN */包裹对应 CSS。 - 构建产物检查:每次改动后分别在小程序、H5 模式各跑一遍,确认两端都正常。
3. 微信登录走官方流程
规则: 微信登录必须走 wx.login 获取 code,再由后端调用 code2session 换取 openid 和 session_key;openid 和 session_key 不得存在前端,不得绕过授权步骤直接用 union_id 或手机号作为身份标识。
为什么: AI 经常写出把 session_key 存进 wx.setStorageSync 的代码——这违反微信安全规范,session_key 会失效且不能直接暴露给客户端。还有一种常见错误:前端直接拿 getUserInfo 返回的 openid(旧接口早已废弃)当登录凭证,绕过后端校验,既不安全也不符合现行微信能力。
怎么做:
- 前端只负责:
wx.login→ 拿到 code → 发给自己后端。 - 后端用 appid + appsecret + code 请求微信
code2session接口,换回 openid / session_key,生成自己的登录态 token 返回前端。 - 前端持久化自己后端颁发的 token,不存 openid,不存 session_key。
- 需要手机号时走
getPhoneNumber组件 + 后端解密,不走已废弃的getUserInfo。
4. SpringBoot 分层清晰
规则: Controller 只做参数接收与响应封装,业务逻辑全部下沉到 Service,数据库操作放 Mapper / Repository;统一异常处理用 @ControllerAdvice,参数校验用 @Valid + ConstraintValidator,不在 Controller 里写业务代码。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 249 lines · 32 tokens per session scan A 7cd8d75007d9
domestic-stack is a skill published in the GitHub repository Wade-DevCode/awesome-coding-skills-cn (7 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 3,034 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
domestic-stack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| domestic-stackWade-DevCode/awesome-coding-skills-cn | Skill | 7 | 5mo ago | MIT | A | 32 | Claude Code, Codex |
| cqrs-implementationfindscripter/everything-skills | Skill | 11 | today | none | A | 111 | Claude Code |
| ddd-context-mappingfindscripter/everything-skills | Skill | 11 | today | none | A | 98 | Claude Code |
| golang-profindscripter/everything-skills | Skill | 11 | today | none | A | 119 | Claude Code |
| openapi-doc-generatorfindscripter/everything-skills | Skill | 11 | today | none | A | 123 | Claude Code |
| ddd-strategic-designfindscripter/everything-skills | Skill | 11 | today | none | A | 101 | Claude Code |
| javascript-modern-profindscripter/everything-skills | Skill | 11 | today | none | A | 104 | Claude Code |